Gotowa bibliografia na temat „Compositional generalization”
Utwórz poprawne odniesienie w stylach APA, MLA, Chicago, Harvard i wielu innych
Spis treści
Zobacz listy aktualnych artykułów, książek, rozpraw, streszczeń i innych źródeł naukowych na temat „Compositional generalization”.
Przycisk „Dodaj do bibliografii” jest dostępny obok każdej pracy w bibliografii. Użyj go – a my automatycznie utworzymy odniesienie bibliograficzne do wybranej pracy w stylu cytowania, którego potrzebujesz: APA, MLA, Harvard, Chicago, Vancouver itp.
Możesz również pobrać pełny tekst publikacji naukowej w formacie „.pdf” i przeczytać adnotację do pracy online, jeśli odpowiednie parametry są dostępne w metadanych.
Artykuły w czasopismach na temat "Compositional generalization"
1
Chai, Yuyang, Zhuang Li, Jiahui Liu, Lei Chen, Fei Li, Donghong Ji i Chong Teng. "Compositional Generalization for Multi-Label Text Classification: A Data-Augmentation Approach". Proceedings of the AAAI Conference on Artificial Intelligence 38, nr 16 (24.03.2024): 17727–35. http://dx.doi.org/10.1609/aaai.v38i16.29725.
Pełny tekst źródłaStreszczenie:
Despite significant advancements in multi-label text classification, the ability of existing models to generalize to novel and seldom-encountered complex concepts, which are compositions of elementary ones, remains underexplored. This research addresses this gap. By creating unique data splits across three benchmarks, we assess the compositional generalization ability of existing multi-label text classification models. Our results show that these models often fail to generalize to compositional concepts encountered infrequently during training, leading to inferior performance on tests with these new combinations. To address this, we introduce a data augmentation method that leverages two innovative text generation models designed to enhance the classification models' capacity for compositional generalization. Our experiments show that this data augmentation approach significantly improves the compositional generalization capabilities of classification models on our benchmarks, with both generation models surpassing other text generation baselines. Our codes available at https://github.com/yychai74/LD-VAE.
2
Baroni, Marco. "Linguistic generalization and compositionality in modern artificial neural networks". Philosophical Transactions of the Royal Society B: Biological Sciences 375, nr 1791 (16.12.2019): 20190307. http://dx.doi.org/10.1098/rstb.2019.0307.
Pełny tekst źródłaStreszczenie:
In the last decade, deep artificial neural networks have achieved astounding performance in many natural language-processing tasks. Given the high productivity of language, these models must possess effective generalization abilities. It is widely assumed that humans handle linguistic productivity by means of algebraic compositional rules: are deep networks similarly compositional? After reviewing the main innovations characterizing current deep language-processing networks, I discuss a set of studies suggesting that deep networks are capable of subtle grammar-dependent generalizations, but also that they do not rely on systematic compositional rules. I argue that the intriguing behaviour of these devices (still awaiting a full understanding) should be of interest to linguists and cognitive scientists, as it offers a new perspective on possible computational strategies to deal with linguistic productivity beyond rule-based compositionality, and it might lead to new insights into the less systematic generalization patterns that also appear in natural language. This article is part of the theme issue ‘Towards mechanistic models of meaning composition’.
3
Zheng, Yafang, Lei Lin, Shuangtao Li, Yuxuan Yuan, Zhaohong Lai, Shan Liu, Biao Fu, Yidong Chen i Xiaodong Shi. "Layer-Wise Representation Fusion for Compositional Generalization". Proceedings of the AAAI Conference on Artificial Intelligence 38, nr 17 (24.03.2024): 19706–14. http://dx.doi.org/10.1609/aaai.v38i17.29944.
Pełny tekst źródłaStreszczenie:
Existing neural models are demonstrated to struggle with compositional generalization (CG), i.e., the ability to systematically generalize to unseen compositions of seen components. A key reason for failure on CG is that the syntactic and semantic representations of sequences in both the uppermost layer of the encoder and decoder are entangled. However, previous work concentrates on separating the learning of syntax and semantics instead of exploring the reasons behind the representation entanglement (RE) problem to solve it. We explain why it exists by analyzing the representation evolving mechanism from the bottom to the top of the Transformer layers. We find that the ``shallow'' residual connections within each layer fail to fuse previous layers' information effectively, leading to information forgetting between layers and further the RE problems. Inspired by this, we propose LRF, a novel Layer-wise Representation Fusion framework for CG, which learns to fuse previous layers' information back into the encoding and decoding process effectively through introducing a fuse-attention module at each encoder and decoder layer. LRF achieves promising results on two realistic benchmarks, empirically demonstrating the effectiveness of our proposal. Codes are available at https://github.com/thinkaboutzero/LRF.
4
Kim, Segwang, Joonyoung Kim i Kyomin Jung. "Compositional Generalization via Parsing Tree Annotation". IEEE Access 9 (2021): 24326–33. http://dx.doi.org/10.1109/access.2021.3055513.
Pełny tekst źródła
5
Liu, Xinpeng, Yong-Lu Li i Cewu Lu. "Highlighting Object Category Immunity for the Generalization of Human-Object Interaction Detection". Proceedings of the AAAI Conference on Artificial Intelligence 36, nr 2 (28.06.2022): 1819–27. http://dx.doi.org/10.1609/aaai.v36i2.20075.
Pełny tekst źródłaStreszczenie:
Human-Object Interaction (HOI) detection plays a core role in activity understanding. As a compositional learning problem (human-verb-object), studying its generalization matters. However, widely-used metric mean average precision (mAP) fails to model the compositional generalization well. Thus, we propose a novel metric, mPD (mean Performance Degradation), as a complementary of mAP to evaluate the performance gap among compositions of different objects and the same verb. Surprisingly, mPD reveals that previous methods usually generalize poorly. With mPD as a cue, we propose Object Category (OC) Immunity to boost HOI generalization. The idea is to prevent model from learning spurious object-verb correlations as a short-cut to over-fit the train set. To achieve OC-immunity, we propose an OC-immune network that decouples the inputs from OC, extracts OC-immune representations, and leverages uncertainty quantification to generalize to unseen objects. In both conventional and zero-shot experiments, our method achieves decent improvements. To fully evaluate the generalization, we design a new and more difficult benchmark, on which we present significant advantage. The code is available at https://github.com/Foruck/OC-Immunity.
6
Jing, Chenchen, Yukun Li, Hao Chen i Chunhua Shen. "Retrieval-Augmented Primitive Representations for Compositional Zero-Shot Learning". Proceedings of the AAAI Conference on Artificial Intelligence 38, nr 3 (24.03.2024): 2652–60. http://dx.doi.org/10.1609/aaai.v38i3.28043.
Pełny tekst źródłaStreszczenie:
Compositional zero-shot learning (CZSL) aims to recognize unseen attribute-object compositions by learning from seen compositions. Composing the learned knowledge of seen primitives, i.e., attributes or objects, into novel compositions is critical for CZSL. In this work, we propose to explicitly retrieve knowledge of seen primitives for compositional zero-shot learning. We present a retrieval-augmented method, which augments standard multi-path classification methods with two retrieval modules. Specifically, we construct two databases storing the attribute and object representations of training images, respectively. For an input training/testing image, we use two retrieval modules to retrieve representations of training images with the same attribute and object, respectively. The primitive representations of the input image are augmented by using the retrieved representations, for composition recognition. By referencing semantically similar images, the proposed method is capable of recalling knowledge of seen primitives for compositional generalization. Experiments on three widely-used datasets show the effectiveness of the proposed method.
7
Cui, Ruixiang, Rahul Aralikatte, Heather Lent i Daniel Hershcovich. "Compositional Generalization in Multilingual Semantic Parsing over Wikidata". Transactions of the Association for Computational Linguistics 10 (2022): 937–55. http://dx.doi.org/10.1162/tacl_a_00499.
Pełny tekst źródłaStreszczenie:
Abstract Semantic parsing (SP) allows humans to leverage vast knowledge resources through natural interaction. However, parsers are mostly designed for and evaluated on English resources, such as CFQ (Keysers et al., 2020), the current standard benchmark based on English data generated from grammar rules and oriented towards Freebase, an outdated knowledge base. We propose a method for creating a multilingual, parallel dataset of question-query pairs, grounded in Wikidata. We introduce such a dataset, which we call Multilingual Compositional Wikidata Questions (MCWQ), and use it to analyze the compositional generalization of semantic parsers in Hebrew, Kannada, Chinese, and English. While within- language generalization is comparable across languages, experiments on zero-shot cross- lingual transfer demonstrate that cross-lingual compositional generalization fails, even with state-of-the-art pretrained multilingual encoders. Furthermore, our methodology, dataset, and results will facilitate future research on SP in more realistic and diverse settings than has been possible with existing resources.
8
Guo, Yinuo, Hualei Zhu, Zeqi Lin, Bei Chen, Jian-Guang Lou i Dongmei Zhang. "Revisiting Iterative Back-Translation from the Perspective of Compositional Generalization". Proceedings of the AAAI Conference on Artificial Intelligence 35, nr 9 (18.05.2021): 7601–9. http://dx.doi.org/10.1609/aaai.v35i9.16930.
Pełny tekst źródłaStreszczenie:
Human intelligence exhibits compositional generalization (i.e., the capacity to understand and produce unseen combinations of seen components), but current neural seq2seq models lack such ability. In this paper, we revisit iterative back-translation, a simple yet effective semi-supervised method, to investigate whether and how it can improve compositional generalization. In this work: (1) We first empirically show that iterative back-translation substantially improves the performance on compositional generalization benchmarks (CFQ and SCAN). (2) To understand why iterative back-translation is useful, we carefully examine the performance gains and find that iterative back-translation can increasingly correct errors in pseudo-parallel data. (3) To further encourage this mechanism, we propose curriculum iterative back-translation, which better improves the quality of pseudo-parallel data, thus further improving the performance.
9
Logeswaran, Lajanugen, Wilka Carvalho i Honglak Lee. "Learning Compositional Tasks from Language Instructions". Proceedings of the AAAI Conference on Artificial Intelligence 37, nr 11 (26.06.2023): 13300–13308. http://dx.doi.org/10.1609/aaai.v37i11.26561.
Pełny tekst źródłaStreszczenie:
The ability to combine learned knowledge and skills to solve novel tasks is a key aspect of generalization in humans that allows us to understand and perform tasks described by novel language utterances. While progress has been made in supervised learning settings, no work has yet studied compositional generalization of a reinforcement learning agent following natural language instructions in an embodied environment. We develop a set of tasks in a photo-realistic simulated kitchen environment that allow us to study the degree to which a behavioral policy captures the systematicity in language by studying its zero-shot generalization performance on held out natural language instructions. We show that our agent which leverages a novel additive action-value decomposition in tandem with attention based subgoal prediction is able to exploit composition in text instructions to generalize to unseen tasks.
10
Petit, Alban, i Caio Corro. "On Graph-based Reentrancy-free Semantic Parsing". Transactions of the Association for Computational Linguistics 11 (2023): 703–22. http://dx.doi.org/10.1162/tacl_a_00570.
Pełny tekst źródłaStreszczenie:
Abstract We propose a novel graph-based approach for semantic parsing that resolves two problems observed in the literature: (1) seq2seq models fail on compositional generalization tasks; (2) previous work using phrase structure parsers cannot cover all the semantic parses observed in treebanks. We prove that both MAP inference and latent tag anchoring (required for weakly-supervised learning) are NP-hard problems. We propose two optimization algorithms based on constraint smoothing and conditional gradient to approximately solve these inference problems. Experimentally, our approach delivers state-of-the-art results on GeoQuery, Scan, and Clevr, both for i.i.d. splits and for splits that test for compositional generalization.
Rozprawy doktorskie na temat "Compositional generalization"
1
Petit, Alban. "Structured prediction methods for semantic parsing". Electronic Thesis or Diss., université Paris-Saclay, 2024. http://www.theses.fr/2024UPASG002.
Pełny tekst źródłaStreszczenie:
L'analyse sémantique est une tâche qui consiste à produire une représentation formelle manipulable par un ordinateur à partir d'un énoncé en langage naturel. Il s'agit d'une tâche majeure dans le traitement automatique des langues avec plusieurs applications comme le développement de systèmes de question-réponse ou la génération de code entre autres. Ces dernières années, les approches fondées sur les réseaux de neurones, et en particulier les architectures séquence-à-séquence, ont démontré de très bonnes performances pour cette tâche. Cependant, plusieurs travaux ont mis en avant les limites de ces analyseurs sémantiques sur des exemples hors distribution. En particulier, ils échouent lorsque la généralisation compositionnelle est requise. Il est donc essentiel de développer des analyseurs sémantiques qui possèdent de meilleures capacités de composition.La représentation du contenu sémantique est une autre préoccupation lorsque l'on aborde l'analyse sémantique. Comme différentes structures syntaxiques peuvent être utilisées pour représenter le même contenu sémantique, il est souhaitable d'utiliser des structures qui peuvent à la fois représenter précisément le contenu sémantique et s'ancrer facilement sur le langage naturel. À ces égards, cette thèse utilise des représentations fondées sur les graphes pour l'analyse sémantique et se concentre sur deux tâches. La première concerne l'entrainement des analyseurs sémantiques fondés sur les graphes. Ils doivent apprendre une correspondance entre les différentes parties du graphe sémantique et l'énoncé en langage naturel. Comme cette information est généralement absente des données d'apprentissage, nous proposons des algorithmes d'apprentissage qui traitent cette correspondance comme une variable latente. La deuxième tâche se concentre sur l'amélioration des capacités de composition des analyseurs sémantiques fondés sur les graphes dans deux contextes différents. Notons que dans la prédiction de graphes, la méthode traditionnelle consiste à prédire d'abord les nœuds, puis les arcs du graphe. Dans le premier contexte, nous supposons que les graphes à prédire sont nécessairement des arborescences et nous proposons un algorithme d'optimisation basé sur le lissage des contraintes et la méthode du graident conditionnel qui permet de prédire l'ensemble du graphe de manière jointe. Dans le second contexte, nous ne faisons aucune hypothèse quant à la nature des graphes sémantiques. Dans ce cas, nous proposons d'introduire une étape intermédiaire de superétiquetage dans l'algorithme d'inférence. Celle-ci va imposer des contraintes supplémentaires sur l'étape de prédiction des arcs. Dans les deux cas, nos contributions peuvent être vues comme l'introduction de contraintes locales supplémentaires pour garantir la validité de la prédiction globale. Expérimentalement, nos contributions améliorent de manière significative les capacités de composition des analyseurs sémantiques fondés sur les graphes et surpassent les approches comparables sur plusieurs jeux de données conçus pour évaluer la généralisation compositionnelleSemantic parsing is the task of mapping a natural language utterance into a formal representation that can be manipulated by a computer program. It is a major task in Natural Language Processing with several applications, including the development of questions answers systems or code generation among others.In recent years, neural-based approaches and particularly sequence-to-sequence architectures have demonstrated strong performances on this task. However, several works have put forward the limitations of neural-based parsers on out-of-distribution examples. In particular, they fail when compositional generalization is required. It is thus essential to develop parsers that exhibit better compositional abilities.The representation of the semantic content is another concern when tackling semantic parsing. As different syntactic structures can be used to represent the same semantic content, one should focus on structures that can both accurately represent the semantic content and align well with natural language. In that regard, this thesis relies on graph-based representations for semantic parsing and focuses on two tasks.The first one deals with the training of graph-based semantic parsers. They need to learn a correspondence between the parts of the semantic graph and the natural language utterance. As this information is usually absent in the training data, we propose training algorithms that treat this correspondence as a latent variable.The second task focuses on improving the compositional abilities of graph-based semantic parsers in two different settings. Note that in graph prediction, the traditional pipeline is to first predict the nodes and then the arcs of the graph. In the first setting, we assume that the graphs that must be predicted are trees and propose an optimization algorithm based on constraint smoothing and conditional gradient that allows to predict the entire graph jointly. In the second setting, we do not make any assumption regarding the nature of the semantic graphs. In that case, we propose to introduce an intermediate supertagging step in the inference pipeline that constrains the arc prediction step. In both settings, our contributions can be viewed as introducing additional local constraints to ensure the well-formedness the overall prediction. Experimentally, our contributions significantly improve the compositional abilities of graph-based semantic parsers and outperform comparable baselines on several datasets designed to evaluate compositional generalization
2
Tarrago, Pierre. "Non-commutative generalization of some probabilistic results from representation theory". Thesis, Paris Est, 2015. http://www.theses.fr/2015PESC1123/document.
Pełny tekst źródłaStreszczenie:
Le sujet de cette thèse est la généralisation non-commutative de résultats probabilistes venant de la théorie des représentations. Les résultats obtenus se divisent en trois parties distinctes. Dans la première partie de la thèse, le concept de groupe quantique easy est étendu au cas unitaire. Tout d'abord, nous donnons une classification de l'ensemble des groupes quantiques easy unitaires dans le cas libre et classique. Nous étendons ensuite les résultats probabilistes de au cas unitaire. La deuxième partie de la thèse est consacrée à une étude du produit en couronne libre. Dans un premier temps, nous décrivons les entrelaceurs des représentations dans le cas particulier d'un produit en couronne libre avec le groupe symétrique libre: cette description permet également d'obtenir plusieurs résultats probabilistes. Dans un deuxième temps, nous établissons un lien entre le produit en couronne libre et les algèbres planaires: ce lien mène à une preuve d'une conjecture de Banica et Bichon. Dans la troisième partie de la thèse, nous étudions un analoque du graphe de Young qui encode la structure multiplicative des fonctions fondamentales quasi-symétriques. La frontière minimale de ce graphe a déjà été décrite par Gnedin et Olshanski. Nous prouvons que la frontière minimale coïncide avec la frontière de Martin. Au cours de cette preuve, nous montrons plusieurs résultats combinatoires asymptotiques concernant les diagrammes de Young en rubanThe subject of this thesis is the non-commutative generalization of some probabilistic results that occur in representation theory. The results of the thesis are divided into three different parts. In the first part of the thesis, we classify all unitary easy quantum groups whose intertwiner spaces are described by non-crossing partitions, and develop the Weingarten calculus on these quantum groups. As an application of the previous work, we recover the results of Diaconis and Shahshahani on the unitary group and extend those results to the free unitary group. In the second part of the thesis, we study the free wreath product. First, we study the free wreath product with the free symmetric group by giving a description of the intertwiner spaces: several probabilistic results are deduced from this description. Then, we relate the intertwiner spaces of a free wreath product with the free product of planar algebras, an object which has been defined by Bisch and Jones. This relation allows us to prove the conjecture of Banica and Bichon. In the last part of the thesis, we prove that the minimal and the Martin boundaries of a graph introduced by Gnedin and Olshanski are the same. In order to prove this, we give some precise estimates on the uniform standard filling of a large ribbon Young diagram. This yields several asymptotic results on the filling of large ribbon Young diagrams
3
Casquilho, José Pinto. "Ecomosaico: indíces para diagnóstico de proporções de composição". Doctoral thesis, ISA/UTL, 1999. http://hdl.handle.net/10400.5/6932.
Pełny tekst źródłaStreszczenie:
Doutoramento em Engenharia Florestal - Instituto Superior de AgronomiaNeste trabalho desenvolvem-se generalizações das funções de Shannon e de Simpson e estudam-se as suas propriedades, nomeadamente de caracterização de valores extremos. Aquelas funções, definidas desde o final dos anos quarenta, têm sido utilizadas em ecologia quantitativa como medidas (ou índices) de diversidade, equitabilidade e de dominância. Apresentam uma única solução crítica designada por solução equitativa, que é interpretável como um ponto de equilíbrio de um sistema dinâmico. Nos anos oitenta, aquelas funções foram introduzidas na Ecologia da Paisagem como medidas (ou índices) de avaliação da diversidade de mosaicos de paisagem. Essas medidas só introduzem informação de ordem corológica - proporções de ocupação do solo por k diferentes habitats - e ignoram qualquer caracterização de ordem topológica das componentes do mosaico, por exemplo relativa à biodiversidade característica dos diferentes elementos do mosaico de paisagem. Os desenvolvimentos que agora se apresentam visam contribuir para o preenchimento dessa lacuna. Nas generalizações estudadas o lugar das soluções de equilíbrio passa a depender da valorização atribuída a cada componente e, como consequência, a solução equitativa passa a ser apenas uma solução, dentro da variedade dos equilíbrios da generalização efectuada. As funções aqui apresentadas, que designamos por índices de diversidade sistémica e índices de valor sistémico do mosaico de paisagem permitem aprofundar o estudo das soluções de composição de um mosaico por k componentes, distintas e espacialmente intersubstituíveis. Daí a designação conjunta de índices para o diagnóstico de proporções do ecomosaico. Os resultados teóricos estabelecidos permitem controlo conceptual e analítico sobre as relações envolvidas na caracterização quantitativa das componentes do mosaico e do seu efeito no valor do índice. Ilustra-se computacionalmente o estudo feito, com um conjunto de simulações envolvendo 4 variáveis. Os índices são utilizados num exemplo relativo ao diagnóstico do mosaico de paisagem no Norte do concelho de Nisa colocado a propósito da expansão do eucaliptal (Eucalyptus globulus) no período 1970-1990. S5o apresentadas outras perspectivas com que estas funções podem vir a ser utilizadas noutros campos da Ecologia, em particular permitindo revisitar o paradigma diversidade-estabilidade---------------------------------------ABSTRACT - In this work we build generalizations of Shannon and Simpson's functions with emphasis on the study of extreme values and the characterization of extreme points. Shannon and Simpson's functions were defined in the late forties and have been used in quantitative ecology as measures (or indices) of diversity, evenness and dominance. They present a single critical solution, the equitable solution, which may be interpreted as the equilibrium point of a dynamic system. About the beginning of the eighties, those functions were introduced in Landscape Ecology, as measures (or indices) of diversity in landscape mosaics. Those measures just deal with information at the chorological level of landscape - the proportions of area of k different habitats - and ignore any characterization of the topological level of the elements of the mosaic, such as the biodiversity of the different ecosystems. This work makes a contribution toward solving that omission. In the generalizations we have studied the equilibrium points depend on the values attached to each element, and, as a consequence, the equitable solution is just a solution in the equilibrium manifold of the respective generalization. We name the new functions as systemic diversity indices and systemic value indices of the landscape mosaic, and they allow for the study of the relative composition of a mosaic with k distinct components, spatially interchangeable. We name globally those indices as indices for the diagnosis of proportions of composition of the ecomosaic. The theoretical results allow for conceptual and analytical control over the quantitative relationships involved in the value of the indices. We present simulations of the behavior of the new functions reaching a total of 4 variables in presence. The indices are used in an example relative to the diagnosis of a landscape mosaic at the North of Alentejo (Nisa), motivated by the expansion of Eucalyptus globulus in the region, in the period 1970-1990. We refer to other fields of Ecology where these functions could be used, in particular allowing revisiting the paradigm diversity-stability.
4
Johanek, Cynthia L. "Cross-cultural learning styles studies and composition : re- examining definitions, generalizations, and applications of past field dependence-independence research". Virtual Press, 1993. http://liblink.bsu.edu/uhtbin/catkey/864905.
Pełny tekst źródłaStreszczenie:
In recent years, the media have publicized the social problem of physical child abuse. This study examined three artifacts of physical abuse: the children's book Robin's Story, the popular song "Luka," and the television documentary Scared Silent: Exposing and Ending Child Abuse. Chapter One described each artifact and provided a literature review which detailed the writings about physical child abuse and artifacts discussing this topic. The chapter then posed research questions about how the artifacts viewed abused children and their abusers, the causes of abuse, and the solutions proposed for ending physical abuse.Chapter One finally discussed the narrative framework of rhetorical analysis used to examine the three artifacts. The narrative method used in this analysis employed three steps: 1) An examination of narrative structure, which discussed the plot of the story, the crucial points of the story and the events which supplemented those points, and the steps of breach, crisis, redress, and reintegration in the narrative; 2) An examination of narrative rationality, which talked about the completeness and true to life quality of the story and evaluated the reasons the rhetors gave for following the course of action endorsed by the story; and 3) An examination of narrative standards, including truth standard or how the narrative compares with what the audience believes is true; aesthetic standard or the grammar, setting, and characterization within the story, and ethical standard or the values expressed within the narrative. Chapter Two applied this framework to the children's book Robin's Story. Chapter Three viewed the popular song "Luka" through the narrative framework. Chapter Four discussed the documentary Scared Silent in terms of narrative analysis.Chapter Five then discussed the conclusions of the analysis for each artifact, artifacts discussing physical abuse, and for rhetoric. Some of the conclusions reached were that artifacts discussing physical child abuse should attempt to make their stories universal, that such artifacts need to distinguish between abuse and physical punishment, and that artifacts dealing with this problem must provide concrete courses of action to end physical abuse. This analysis concluded that, while narrative analysis provided the answers to the research questions, this framework needs to be made into a concrete method of rhetorical analysis to ensure that narratives are effectively evaluated. Narrative analysis was positive in this analysis, however, in that it supported the definitions of rhetoric as value, epistemology, motive, drama, meaning, and argument. This analysis found that, to end the problem of physical child abuse, rhetors must work with experts in this field and tailor artifacts from different perspectives to various audiences using different forms of media.Department of English
5
Křehlík, Štěpán. "Strukturované multisystémy a multiautomaty indukované časovými procesy". Doctoral thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2015. http://www.nusl.cz/ntk/nusl-234457.
Pełny tekst źródłaStreszczenie:
In the thesis we discuss binary hyperstructures of linear differential operators of the second order both in general and (inspired by models of specific time processes) in a special case of the Jacobi form. We also study binary hyperstructures constructed from distributive lattices and suggest transfer of this construction to n-ary hyperstructures. We use these hyperstructures to construct multiautomata and quasi-multiautomata. The input sets of all these automata structures are constructed so that the transfer of information for certain specific modeling time functions is facilitated. For this reason we use smooth positive functions or vectors components of which are real numbers or smooth positive functions. The above hyperstructures are state-sets of these automata structures. Finally, we investigate various types of compositions of the above multiautomata and quasi-multiautomata. In order to this we have to generalize the classical definitions of Dörfler. While some of the concepts can be transferred to the hyperstructure context rather easily, in the case of Cartesian composition the attempt to generalize it leads to some interesting results.
Książki na temat "Compositional generalization"
1
Bird, Steven. Phonology. Redaktor Ruslan Mitkov. Oxford University Press, 2012. http://dx.doi.org/10.1093/oxfordhb/9780199276349.013.0001.
Pełny tekst źródłaStreszczenie:
This article presents the fundamentals of descriptive phonology and gives an overview of computational phonology. Phonology is the systematic study of sounds used in language, and their composition into syllables, words, and phrases. It introduces some of the key concepts of phonology by simple examples involving real data and gives a brief discussion of early generative phonology. It analyses the autosegmental phonology using some data from African tone language. This article considers in detail one level of phonological hierarchy, namely, the syllable. It reveals many interesting issues that are confronted by phonological analysis. Some of these theoretical frameworks include: lexical phonology, underspecification phonology, government phonology, declarative phonology, and optimality theory. The article provides a means for phonological generalizations such as rules and constraints to give a finite-state interpretation.
2
Espiritu, Yen Le. Race and U.S. Panethnic Formation. Redaktor Ronald H. Bayor. Oxford University Press, 2014. http://dx.doi.org/10.1093/oxfordhb/9780199766031.013.013.
Pełny tekst źródłaStreszczenie:
Panethnicity refers to the development of bridging organizations and the generalization of solidarity among subgroups that are racialized to be homogeneous by outsiders. This chapter argues that while the formation of a consolidated white identity in the United States is self-motivated and linked to white privilege, panethnicity for people of color is a product of racial categorization and bound up with power relations. As the influx of new immigrants transforms the demographic composition of existing groups such as Asian Americans and Latinos, group members face the challenge of bridging the class, ethnic, and generational chasms dividing the immigrants and the U.S.-born. In all, existing data confirm the plural and ambivalent nature of panethnicity: it is a highly contested terrain on which different groups merge and clash over terms of inclusion but also an effective site from which to forge alliances with other groups both within and across the U.S. borders.
3
Chodat, Robert. Introduction. Oxford University Press, 2017. http://dx.doi.org/10.1093/oso/9780190682156.003.0001.
Pełny tekst źródłaStreszczenie:
Literary works since the rise of high modernism have been intensely hostile to abstract generalization, and have focused attention on the unique experience and singular expression. This nominalist impulse—summed up in the cry “show, don’t tell!”—has encouraged a deep wariness toward broad normative concepts: “good,” “bad,” “courage,” “justice,” etc. More than is often recognized, however, this literary skepticism parallels the skepticism toward such concepts in the natural sciences, which accords no place to such abstract “high words” in a world of matter and calculable motions. Against this dual literary and scientific inheritance, the postwar sage offers a “weak realism” about normative concepts and a “reflective” mode of composition: a movement between the particular and the general, art and argument. Such a literary–intellectual project is risky, and opens the sage to charges of sentimentalism. Closely attending to their works, however, suggests that we should avoid entering this protest too quickly.
4
Ledger-Lomas, Michael. Introduction. Oxford University Press, 2017. http://dx.doi.org/10.1093/oso/9780199683710.003.0001.
Pełny tekst źródłaStreszczenie:
The nineteenth century was a very good century for Congregationalism in England and Wales. This chapter documents the significant numerical growth it achieved during this period, and its energetic efforts in the area of missions, both foreign and domestic. Congregationalists provided the lifeblood of the large, well-funded London Missionary Society, and the most celebrated missionary of the age, David Livingstone, was a Scottish Congregationalist. Throughout this chapter the question of whether generalizations about Congregationalism in England were also true of Wales, Scotland, and Ireland is kept in view. This chapter explores the denomination’s raison d’être in its distinctive view of church polity as local and the way that it was increasingly in tension with the strong trend towards greater union among the churches. Founded in 1831, the Congregational Union of England and Wales waxed stronger and stronger as the century progressed, and Congregational activities became progressively more centralized. Although women were excluded from almost all official positions in the churches and the Congregational Unions and generally were erased from denominational histories, they were nevertheless often members with full voting rights at a time when this was not true in civic elections. Women were also the force behind the social life of the congregations, including the popular institutions of the church bazaar and tea meeting. They were the main energizing power behind works of service and innumerable charitable and outreach efforts and organizations, as well as playing a significant part in fundraising. The self-image of Victorian Congregationalism as representing the middle classes is explored, including the move towards Gothic architecture and the ideal of the learned ministry. A mark of their social aspirations, the Congregational Mansfield College, founded in 1886, was the first Protestant Dissenting Oxbridge college. Congregationalists also gave leadership to the movement towards a more liberal theological vision, to an emphasis on ‘Life’ over dogma. English, Welsh, Scottish, and Irish Congregationalists all participated in a move away from the Calvinist verities of their forebears. Increasingly, many Congregational theologians and ministers were unwilling to defend traditional doctrines in regards to substitutionary atonement; biblical inspiration, historicity, authorship, dating, and composition; and eternal punishment. A particularly important theme is Congregationalism’s prominent place of leadership in Dissenting politics. The Liberation Society, which led the campaign for the disestablishment of the Church of England, was founded by the Congregational minister Edward Miall in 1844, and Dissenting Members of Parliament were disproportionately Congregationalists. Many Christians emphatically and passionately knew themselves to be Dissenters who were relatively indifferent about which Nonconformist denomination they made their spiritual home. In such an environment, Congregationalism reaped considerable, tangible benefits for being widely recognized as the quintessential Dissenting denomination.
Części książek na temat "Compositional generalization"
1
Quatmann, Tim, i Joost-Pieter Katoen. "Multi-objective Optimization of Long-run Average and Total Rewards". W Tools and Algorithms for the Construction and Analysis of Systems, 230–49. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-72016-2_13.
Pełny tekst źródłaStreszczenie:
AbstractThis paper presents an efficient procedure for multi-objective model checking of long-run average reward (aka: mean pay-off) and total reward objectives as well as their combination. We consider this for Markov automata, a compositional model that captures both traditional Markov decision processes (MDPs) as well as a continuous-time variant thereof. The crux of our procedure is a generalization of Forejt et al.’s approach for total rewards on MDPs to arbitrary combinations of long-run and total reward objectives on Markov automata. Experiments with a prototypical implementation on top of the Storm model checker show encouraging results for both model types and indicate a substantial improved performance over existing multi-objective long-run MDP model checking based on linear programming.
2
Bhargava, Manjul. "Gauss Composition and Generalizations". W Lecture Notes in Computer Science, 1–8. Berlin, Heidelberg: Springer Berlin Heidelberg, 2002. http://dx.doi.org/10.1007/3-540-45455-1_1.
Pełny tekst źródła
3
Golasiński, Marek, i Francisco Gómez Ruiz. "Algebraic Generalizations of Matrix Varieties". W Grassmann and Stiefel Varieties over Composition Algebras, 195–249. Cham: Springer Nature Switzerland, 2023. http://dx.doi.org/10.1007/978-3-031-36405-1_5.
Pełny tekst źródła
4
Golasiński, Marek, i Francisco Gómez Ruiz. "Stiefel, Grassmann Manifolds and Generalizations". W Grassmann and Stiefel Varieties over Composition Algebras, 111–68. Cham: Springer Nature Switzerland, 2023. http://dx.doi.org/10.1007/978-3-031-36405-1_3.
Pełny tekst źródła
5
Haltermann, Jan, Marie-Christine Jakobs, Cedric Richter i Heike Wehrheim. "Parallel Program Analysis via Range Splitting". W Fundamental Approaches to Software Engineering, 195–219. Cham: Springer Nature Switzerland, 2023. http://dx.doi.org/10.1007/978-3-031-30826-0_11.
Pełny tekst źródłaStreszczenie:
AbstractRanged symbolic execution has been proposed as a way of scaling symbolic execution by splitting the task of path exploration onto several workers running in parallel. The split is conducted along path ranges which – simply speaking – describe sets of paths. Workers can then explore path ranges in parallel.In this paper, we propose ranged analysis as the generalization of ranged symbolic execution to arbitrary program analyses. This allows us to not only parallelize a single analysis, but also run different analyses on different ranges of a program in parallel. Besides this generalization, we also provide a novel range splitting strategy operating along loop bounds, complementing the existing random strategy of the original proposal. We implemented ranged analysis within the tool CPAchecker and evaluated it on programs from the SV-COMP benchmark. The evaluation in particular shows the superiority of loop bounds splitting over random splitting. We furthermore find that compositions of ranged analyses can solve analysis tasks that none of the constituent analysis alone can solve.
6
Finkbeiner, Bernd, i Ernst-Rüdiger Olderog. "Concurrent Hyperproperties". W Theories of Programming and Formal Methods, 211–31. Cham: Springer Nature Switzerland, 2023. http://dx.doi.org/10.1007/978-3-031-40436-8_8.
Pełny tekst źródłaStreszczenie:
AbstractTrace properties, which are sets of execution traces, are often used to analyze systems, but their expressiveness is limited. Clarkson and Schneider defined hyperproperties as a generalization of trace properties to sets of sets of traces. Typical applications of hyperproperties are found in information flow security. We introduce an analogous definition of concurrent hyperproperties, by generalizing traces to concurrent traces, which we define as partially ordered multisets. We take Petri nets as the basic semantic model. Concurrent traces are formalized via causal nets. To check concurrent hyperproperties, we define may and must testing of sets of concurrent traces in the style of DeNicola and Hennessy, using the parallel composition of Petri nets. In our approach, we thus distinguish nondeterministic and concurrent behavior. We discuss examples where concurrent hyperproperties are needed.
7
Unno, Hiroshi, Tachio Terauchi i Eric Koskinen. "Constraint-Based Relational Verification". W Computer Aided Verification, 742–66. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-81685-8_35.
Pełny tekst źródłaStreszczenie:
AbstractIn recent years they have been numerous works that aim to automate relational verification. Meanwhile, although Constrained Horn Clauses ($$\mathrm {CHCs}$$ CHCs ) empower a wide range of verification techniques and tools, they lack the ability to express hyperproperties beyond k-safety such as generalized non-interference and co-termination.This paper describes a novel and fully automated constraint-based approach to relational verification. We first introduce a new class of predicate Constraint Satisfaction Problems called $$\mathrm {pfwCSP}$$ pfwCSP where constraints are represented as clauses modulo first-order theories over predicate variables of three kinds: ordinary, well-founded, or functional. This generalization over $$\mathrm {CHCs}$$ CHCs permits arbitrary (i.e., possibly non-Horn) clauses, well-foundedness constraints, functionality constraints, and is capable of expressing these relational verification problems. Our approach enables us to express and automatically verify problem instances that require non-trivial (i.e., non-sequential and non-lock-step) self-composition by automatically inferring appropriate schedulers (or alignment) that dictate when and which program copies move. To solve problems in this new language, we present a constraint solving method for $$\mathrm {pfwCSP}$$ pfwCSP based on stratified CounterExample-Guided Inductive Synthesis (CEGIS) of ordinary, well-founded, and functional predicates.We have implemented the proposed framework and obtained promising results on diverse relational verification problems that are beyond the scope of the previous verification frameworks.
8
Barthe, Gilles, Raphaëlle Crubillé, Ugo Dal Lago i Francesco Gavazzo. "On the Versatility of Open Logical Relations". W Programming Languages and Systems, 56–83. Cham: Springer International Publishing, 2020. http://dx.doi.org/10.1007/978-3-030-44914-8_3.
Pełny tekst źródłaStreszczenie:
AbstractLogical relations are one among the most powerful techniques in the theory of programming languages, and have been used extensively for proving properties of a variety of higher-order calculi. However, there are properties that cannot be immediately proved by means of logical relations, for instance program continuity and differentiability in higher-order languages extended with real-valued functions. Informally, the problem stems from the fact that these properties are naturally expressed on terms of non-ground type (or, equivalently, on open terms of base type), and there is no apparent good definition for a base case (i.e. for closed terms of ground types). To overcome this issue, we study a generalization of the concept of a logical relation, called open logical relation, and prove that it can be fruitfully applied in several contexts in which the property of interest is about expressions of first-order type. Our setting is a simply-typed $$\lambda $$ λ -calculus enriched with real numbers and real-valued first-order functions from a given set, such as the one of continuous or differentiable functions. We first prove a containment theorem stating that for any collection of real-valued first-order functions including projection functions and closed under function composition, any well-typed term of first-order type denotes a function belonging to that collection. Then, we show by way of open logical relations the correctness of the core of a recently published algorithm for forward automatic differentiation. Finally, we define a refinement-based type system for local continuity in an extension of our calculus with conditionals, and prove the soundness of the type system using open logical relations.
9
Herzig, Jonathan, Jonathan Berant i Ben Bogin. "Chapter 29. Latent Trees for Compositional Generalization". W Frontiers in Artificial Intelligence and Applications. IOS Press, 2023. http://dx.doi.org/10.3233/faia230161.
Pełny tekst źródłaStreszczenie:
Despite the success of neural networks in many natural language processing tasks, recent work has shown that they often fail in compositional generalization, i.e., the ability to generalize to new structures built from components observed during training. In this chapter, we posit that this behavior, in standard architectures such as LSTMs and Transformers, stems from the fact that fragments on the output side are not explicitly tied to fragments on the input side. To address this, we introduce models that explicitly construct latent trees over the input, which are used to compositionally compute representations necessary for predicting the output. We show the compositional generalization abilities of our models exceed the abilities of pre-trained Transformer models on several datasets for both semantic parsing and grounded question answering.
10
Quek, Chai, Zaiyi Guo i Douglas L. Maskell. "A Novel Fuzzy Associative Memory Architecture for Stock Market Prediction and Trading". W Contemporary Theory and Pragmatic Approaches in Fuzzy Computing Utilization, 87–104. IGI Global, 2013. http://dx.doi.org/10.4018/978-1-4666-1870-1.ch007.
Pełny tekst źródłaStreszczenie:
In this paper, a novel stock trading framework based on a neuro-fuzzy associative memory (FAM) architecture is proposed. The architecture incorporates the approximate analogical reasoning schema (AARS) to resolve the problem of discontinuous (staircase) response and inefficient memory utilization with uniform quantization in the associative memory structure. The resultant structure is conceptually clearer and more computationally efficient than the Compositional Rule Inference (CRI) and Truth Value Restriction (TVR) fuzzy inference schemes. The local generalization characteristic of the associative memory structure is preserved by the FAM-AARS architecture. The prediction and trading framework exploits the price percentage oscillator (PPO) for input preprocessing and trading decision making. Numerical experiments conducted on real-life stock data confirm the validity of the design and the performance of the proposed architecture.
Streszczenia konferencji na temat "Compositional generalization"
1
Li, Yuanpeng, Liang Zhao, Jianyu Wang i Joel Hestness. "Compositional Generalization for Primitive Substitutions". W Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Stroudsburg, PA, USA: Association for Computational Linguistics, 2019. http://dx.doi.org/10.18653/v1/d19-1438.
Pełny tekst źródła
2
Nikolaus, Mitja, Mostafa Abdou, Matthew Lamm, Rahul Aralikatte i Desmond Elliott. "Compositional Generalization in Image Captioning". W Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL). Stroudsburg, PA, USA: Association for Computational Linguistics, 2019. http://dx.doi.org/10.18653/v1/k19-1009.
Pełny tekst źródła
3
Zheng, Hao, i Mirella Lapata. "Compositional Generalization via Semantic Tagging". W Findings of the Association for Computational Linguistics: EMNLP 2021. Stroudsburg, PA, USA: Association for Computational Linguistics, 2021. http://dx.doi.org/10.18653/v1/2021.findings-emnlp.88.
Pełny tekst źródła
4
Goodwin, Emily, Siva Reddy, Timothy O’Donnell i Dzmitry Bahdanau. "Compositional Generalization in Dependency Parsing". W Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Stroudsburg, PA, USA: Association for Computational Linguistics, 2022. http://dx.doi.org/10.18653/v1/2022.acl-long.448.
Pełny tekst źródła
5
Liu, Chenyao, Shengnan An, Zeqi Lin, Qian Liu, Bei Chen, Jian-Guang Lou, Lijie Wen, Nanning Zheng i Dongmei Zhang. "Learning Algebraic Recombination for Compositional Generalization". W Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. Stroudsburg, PA, USA: Association for Computational Linguistics, 2021. http://dx.doi.org/10.18653/v1/2021.findings-acl.97.
Pełny tekst źródła
6
Yin, Yongjing, Jiali Zeng, Yafu Li, Fandong Meng, Jie Zhou i Yue Zhang. "Consistency Regularization Training for Compositional Generalization". W Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Stroudsburg, PA, USA: Association for Computational Linguistics, 2023. http://dx.doi.org/10.18653/v1/2023.acl-long.72.
Pełny tekst źródła
7
Han, Hojae, Seung-won Hwang, Shuai Lu, Nan Duan i Seungtaek Choi. "Towards Compositional Generalization in Code Search". W Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, PA, USA: Association for Computational Linguistics, 2022. http://dx.doi.org/10.18653/v1/2022.emnlp-main.737.
Pełny tekst źródła
8
Ray, Avik, Yilin Shen i Hongxia Jin. "Compositional Generalization in Spoken Language Understanding". W INTERSPEECH 2023. ISCA: ISCA, 2023. http://dx.doi.org/10.21437/interspeech.2023-1419.
Pełny tekst źródła
9
Oren, Inbar, Jonathan Herzig, Nitish Gupta, Matt Gardner i Jonathan Berant. "Improving Compositional Generalization in Semantic Parsing". W Findings of the Association for Computational Linguistics: EMNLP 2020. Stroudsburg, PA, USA: Association for Computational Linguistics, 2020. http://dx.doi.org/10.18653/v1/2020.findings-emnlp.225.
Pełny tekst źródła
10
Zhou, Xiang, Yichen Jiang i Mohit Bansal. "Data Factors for Better Compositional Generalization". W Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, PA, USA: Association for Computational Linguistics, 2023. http://dx.doi.org/10.18653/v1/2023.emnlp-main.898.
Pełny tekst źródłaRaporty organizacyjne na temat "Compositional generalization"
1
Howland, Scott, Jessica Yaros i Noriaki Kono. MetaText: Compositional Generalization in Deep Language Models. Office of Scientific and Technical Information (OSTI), październik 2022. http://dx.doi.org/10.2172/1987883.
Pełny tekst źródła