Thematische Bibliographien / Deep semantic parsing

Inhaltsverzeichnis

Zeitschriftenartikel
Dissertationen
Bücher
Buchteile
Konferenzberichte

Auswahl der wissenschaftlichen Literatur zum Thema „Deep semantic parsing“

Autor: Grafiati

Veröffentlicht am 25. Mai 2024

Geben Sie eine Quelle nach APA, MLA, Chicago, Harvard und anderen Zitierweisen an

Wählen Sie eine Art der Quelle aus:

Machen Sie sich mit den Listen der aktuellen Artikel, Bücher, Dissertationen, Berichten und anderer wissenschaftlichen Quellen zum Thema "Deep semantic parsing" bekannt.

Neben jedem Werk im Literaturverzeichnis ist die Option "Zur Bibliographie hinzufügen" verfügbar. Nutzen Sie sie, wird Ihre bibliographische Angabe des gewählten Werkes nach der nötigen Zitierweise (APA, MLA, Harvard, Chicago, Vancouver usw.) automatisch gestaltet.

Sie können auch den vollen Text der wissenschaftlichen Publikation im PDF-Format herunterladen und eine Online-Annotation der Arbeit lesen, wenn die relevanten Parameter in den Metadaten verfügbar sind.

Zeitschriftenartikel zum Thema "Deep semantic parsing"

Laukaitis, Algirdas, Egidijus Ostašius und Darius Plikynas. „Deep Semantic Parsing with Upper Ontologies“. Applied Sciences 11, Nr. 20 (11.10.2021): 9423. http://dx.doi.org/10.3390/app11209423.

Der volle Inhalt der Quelle

Annotation:

This paper presents a new method for semantic parsing with upper ontologies using FrameNet annotations and BERT-based sentence context distributed representations. The proposed method leverages WordNet upper ontology mapping and PropBank-style semantic role labeling and it is designed for long text parsing. Given a PropBank, FrameNet and WordNet-labeled corpus, a model is proposed that annotates the set of semantic roles with upper ontology concept names. These annotations are used for the identification of predicates and arguments that are relevant for virtual reality simulators in a 3D world with a built-in physics engine. It is shown that state-of-the-art results can be achieved in relation to semantic role labeling with upper ontology concepts. Additionally, a manually annotated corpus was created using this new method and is presented in this study. It is suggested as a benchmark for future studies relevant to semantic parsing.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

BALLESTEROS, MIGUEL, BERND BOHNET, SIMON MILLE und LEO WANNER. „Data-driven deep-syntactic dependency parsing“. Natural Language Engineering 22, Nr. 6 (18.08.2015): 939–74. http://dx.doi.org/10.1017/s1351324915000285.

Der volle Inhalt der Quelle

Annotation:

Abstract‘Deep-syntactic’ dependency structures that capture the argumentative, attributive and coordinative relations between full words of a sentence have a great potential for a number of NLP-applications. The abstraction degree of these structures is in between the output of a syntactic dependency parser (connected trees defined over all words of a sentence and language-specific grammatical functions) and the output of a semantic parser (forests of trees defined over individual lexemes or phrasal chunks and abstract semantic role labels which capture the frame structures of predicative elements and drop all attributive and coordinative dependencies). We propose a parser that provides deep-syntactic structures. The parser has been tested on Spanish, English and Chinese.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

Luo, Ling, Dingyu Xue und Xinglong Feng. „EHANet: An Effective Hierarchical Aggregation Network for Face Parsing“. Applied Sciences 10, Nr. 9 (30.04.2020): 3135. http://dx.doi.org/10.3390/app10093135.

Der volle Inhalt der Quelle

Annotation:

In recent years, benefiting from deep convolutional neural networks (DCNNs), face parsing has developed rapidly. However, it still has the following problems: (1) Existing state-of-the-art frameworks usually do not satisfy real-time while pursuing performance; (2) similar appearances cause incorrect pixel label assignments, especially in the boundary; (3) to promote multi-scale prediction, deep features and shallow features are used for fusion without considering the semantic gap between them. To overcome these drawbacks, we propose an effective and efficient hierarchical aggregation network called EHANet for fast and accurate face parsing. More specifically, we first propose a stage contextual attention mechanism (SCAM), which uses higher-level contextual information to re-encode the channel according to its importance. Secondly, a semantic gap compensation block (SGCB) is presented to ensure the effective aggregation of hierarchical information. Thirdly, the advantages of weighted boundary-aware loss effectively make up for the ambiguity of boundary semantics. Without any bells and whistles, combined with a lightweight backbone, we achieve outstanding results on both CelebAMask-HQ (78.19% mIoU) and Helen datasets (90.7% F1-score). Furthermore, our model can achieve 55 FPS on a single GTX 1080Ti card with 640 × 640 input and further reach over 300 FPS with a resolution of 256 × 256, which is suitable for real-world applications.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

Abdelaziz, Ibrahim, Srinivas Ravishankar, Pavan Kapanipathi, Salim Roukos und Alexander Gray. „A Semantic Parsing and Reasoning-Based Approach to Knowledge Base Question Answering“. Proceedings of the AAAI Conference on Artificial Intelligence 35, Nr. 18 (18.05.2021): 15985–87. http://dx.doi.org/10.1609/aaai.v35i18.17988.

Der volle Inhalt der Quelle

Annotation:

Knowledge Base Question Answering (KBQA) is a task where existing techniques have faced significant challenges, such as the need for complex question understanding, reasoning, and large training datasets. In this work, we demonstrate Deep Thinking Question Answering (DTQA), a semantic parsing and reasoning-based KBQA system. DTQA (1) integrates multiple, reusable modules that are trained specifically for their individual tasks (e.g. semantic parsing, entity linking, and relationship linking), eliminating the need for end-to-end KBQA training data; (2) leverages semantic parsing and a reasoner for improved question understanding. DTQA is a system of systems that achieves state-of-the-art performance on two popular KBQA datasets.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

Huang, Lili, Jiefeng Peng, Ruimao Zhang, Guanbin Li und Liang Lin. „Learning deep representations for semantic image parsing: a comprehensive overview“. Frontiers of Computer Science 12, Nr. 5 (30.08.2018): 840–57. http://dx.doi.org/10.1007/s11704-018-7195-8.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

Fernández-Martínez, Nicolás José, und Pamela Faber. „Who stole what from whom?“ Languages in Contrast 20, Nr. 1 (05.06.2019): 107–40. http://dx.doi.org/10.1075/lic.19002.fer.

Der volle Inhalt der Quelle

Annotation:

Abstract Drawing on the Lexical Grammar Model, Frame Semantics and Corpus Pattern Analysis, we analyze and contrast verbs of stealing in English and Spanish from a lexico-semantic perspective. This involves looking at the lexical collocates and their corresponding semantic categories that fill the argument slots of verbs of stealing. Our corpus search is performed with the Word Sketch tool on Sketch Engine. To the best of our knowledge, no study has yet taken advantage of the Word Sketch tool in the study of the selection preferences of verbs of stealing, let alone a semantic, cross-linguistic study of those verbs. Our findings reveal that English and Spanish verbs of stealing map out the same underlying semantic space. This shared conceptual layer can thus be incorporated into an ontology based on deep semantics, which could in turn enhance NLP tasks such as word sense disambiguation, machine translation, semantic tagging, and semantic parsing.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

Zhao, H., X. Zhang und C. Kit. „Integrative Semantic Dependency Parsing via Efficient Large-scale Feature Selection“. Journal of Artificial Intelligence Research 46 (20.02.2013): 203–33. http://dx.doi.org/10.1613/jair.3717.

Der volle Inhalt der Quelle

Annotation:

Semantic parsing, i.e., the automatic derivation of meaning representation such as an instantiated predicate-argument structure for a sentence, plays a critical role in deep processing of natural language. Unlike all other top systems of semantic dependency parsing that have to rely on a pipeline framework to chain up a series of submodels each specialized for a specific subtask, the one presented in this article integrates everything into one model, in hopes of achieving desirable integrity and practicality for real applications while maintaining a competitive performance. This integrative approach tackles semantic parsing as a word pair classification problem using a maximum entropy classifier. We leverage adaptive pruning of argument candidates and large-scale feature selection engineering to allow the largest feature space ever in use so far in this field, it achieves a state-of-the-art performance on the evaluation data set for CoNLL-2008 shared task, on top of all but one top pipeline system, confirming its feasibility and effectiveness.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

Zhang, Xun, Yantao Du, Weiwei Sun und Xiaojun Wan. „Transition-Based Parsing for Deep Dependency Structures“. Computational Linguistics 42, Nr. 3 (September 2016): 353–89. http://dx.doi.org/10.1162/coli_a_00252.

Der volle Inhalt der Quelle

Annotation:

Derivations under different grammar formalisms allow extraction of various dependency structures. Particularly, bilexical deep dependency structures beyond surface tree representation can be derived from linguistic analysis grounded by CCG, LFG, and HPSG. Traditionally, these dependency structures are obtained as a by-product of grammar-guided parsers. In this article, we study the alternative data-driven, transition-based approach, which has achieved great success for tree parsing, to build general dependency graphs. We integrate existing tree parsing techniques and present two new transition systems that can generate arbitrary directed graphs in an incremental manner. Statistical parsers that are competitive in both accuracy and efficiency can be built upon these transition systems. Furthermore, the heterogeneous design of transition systems yields diversity of the corresponding parsing models and thus greatly benefits parser ensemble. Concerning the disambiguation problem, we introduce two new techniques, namely, transition combination and tree approximation, to improve parsing quality. Transition combination makes every action performed by a parser significantly change configurations. Therefore, more distinct features can be extracted for statistical disambiguation. With the same goal of extracting informative features, tree approximation induces tree backbones from dependency graphs and re-uses tree parsing techniques to produce tree-related features. We conduct experiments on CCG-grounded functor–argument analysis, LFG-grounded grammatical relation analysis, and HPSG-grounded semantic dependency analysis for English and Chinese. Experiments demonstrate that data-driven models with appropriate transition systems can produce high-quality deep dependency analysis, comparable to more complex grammar-driven models. Experiments also indicate the effectiveness of the heterogeneous design of transition systems for parser ensemble, transition combination, as well as tree approximation for statistical disambiguation.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

Zhou, Fan, Enbo Huang, Zhuo Su und Ruomei Wang. „Multiscale Meets Spatial Awareness: An Efficient Attention Guidance Network for Human Parsing“. Mathematical Problems in Engineering 2020 (16.10.2020): 1–12. http://dx.doi.org/10.1155/2020/5794283.

Der volle Inhalt der Quelle

Annotation:

Human parsing, which aims at resolving human body and clothes into semantic part regions from an human image, is a fundamental task in human-centric analysis. Recently, the approaches for human parsing based on deep convolutional neural networks (DCNNs) have made significant progress. However, hierarchically exploiting multiscale and spatial contexts as convolutional features is still a hurdle to overcome. In order to boost the scale and spatial awareness of a DCNN, we propose two effective structures, named “Attention SPP and Attention RefineNet,” to form a Mutual Attention operation, to exploit multiscale and spatial semantics different from the existing approaches. Moreover, we propose a novel Attention Guidance Network (AG-Net), a simple yet effective architecture without using bells and whistles (such as human pose and edge information), to address human parsing tasks. Comprehensive evaluations on two public datasets well demonstrate that the AG-Net outperforms the state-of-the-art networks.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

Yang, Haitong, Tao Zhuang und Chengqing Zong. „Domain Adaptation for Syntactic and Semantic Dependency Parsing Using Deep Belief Networks“. Transactions of the Association for Computational Linguistics 3 (Dezember 2015): 271–82. http://dx.doi.org/10.1162/tacl_a_00138.

Der volle Inhalt der Quelle

Annotation:

In current systems for syntactic and semantic dependency parsing, people usually define a very high-dimensional feature space to achieve good performance. But these systems often suffer severe performance drops on out-of-domain test data due to the diversity of features of different domains. This paper focuses on how to relieve this domain adaptation problem with the help of unlabeled target domain data. We propose a deep learning method to adapt both syntactic and semantic parsers. With additional unlabeled target domain data, our method can learn a latent feature representation (LFR) that is beneficial to both domains. Experiments on English data in the CoNLL 2009 shared task show that our method largely reduced the performance drop on out-of-domain test data. Moreover, we get a Macro F1 score that is 2.32 points higher than the best system in the CoNLL 2009 shared task in out-of-domain tests.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

Mehr Quellen

Dissertationen zum Thema "Deep semantic parsing"

He, Haoyu. „Deep learning based human parsing“. Thesis, University of Sydney, 2020. https://hdl.handle.net/2123/24262.

Der volle Inhalt der Quelle

Annotation:

Human parsing, or human body part semantic segmentation, has been an active research topic due to its wide potential applications. Although prior works have made significant progress by introducing large-scale datasets and deep learning to solve the problem, there are still two challenges remain unsolved. Firstly, to better exploit the existing parsing annotations, prior methods learn a knowledge-sharing mechanism to improve semantic structures in cross-dataset human parsing. However, the modeling for such mechanism remains inefficient for not considering classes' granularity difference in different domains. Secondly, the trained models are limited to parsing humans into classes pre-defined in the training data, which lacks the generalization ability to the unseen fashion classes. Targeting at improving feature representations from multi-domain annotations more efficiently, in this thesis, we propose a novel GRAph PYramid Mutual Learning (Grapy-ML) method to address the cross-dataset human parsing problem, where we model the granularity difference through a graph pyramid. Starting from the prior knowledge of the human body hierarchical structure, we devise a graph pyramid module (GPM) by stacking three levels of graph structures from coarse granularity to fine granularity subsequently. Specifically, the network weights of the first two levels are shared to exchange the learned coarse-granularity information across different datasets. At each level, GPM utilizes the self-attention mechanism to model the correlations between context nodes. Then, it adopts a top-down mechanism to progressively refine the hierarchical features through all the levels. GPM also enables efficient mutual learning. By making use of the multi-granularity labels, Grapy-ML learns a more discriminative feature representation and achieves state-of-the-art performance, which is demonstrated by extensive experiments on the three popular benchmarks, e.g., CIHP dataset. To bridge the generalizability gap, in this thesis, we propose a new problem named one-shot human parsing (OSHP) that requires to parse human into an open set of reference classes defined by any single reference example. During training, only base classes defined in the training set are exposed, which can overlap with part of reference classes. In this thesis, we devise a novel Progressive One-shot Parsing network (POPNet) to address two critical challenges in this problem, i.e., testing bias and small size. POPNet consists of two collaborative metric learning modules named Attention Guidance Module (AGM) and Nearest Centroid Module (NCM), which can learn representative prototypes for base classes and quickly transfer the ability to the unseen classes during testing, thereby reducing the testing bias. Moreover, POPNet adopts a progressive human parsing framework that can incorporate the learned knowledge of parent classes at the coarse granularity to help recognize the unseen descendant classes at the fine granularity, thereby handling the small size issue. Experiments on the ATR-OS benchmark tailoring for OSHP, demonstrate POPNet outperforms other representative one-shot segmentation models by large margins and establishes a strong baseline for the new problem.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

Billingsley, Richard John. „Deep Learning for Semantic and Syntactic Structures“. Thesis, The University of Sydney, 2014. http://hdl.handle.net/2123/12825.

Der volle Inhalt der Quelle

Annotation:

Deep machine learning has enjoyed recent success in vision and speech-to-text tasks, using deep multi-layered neural networks. They have obtained remarkable results particularly where the internal representation of the task is unclear. In parsing, where the structure of syntax is well studied and understood from linguistics, neural networks have so far not performed so well. State-of-the-art parsers use a tree-based graphical model that requires a large number of equivalent classes to represent each parse node and its phrase label. A recursive neural network (RNN) parser has been developed that works well on short sentences, but falls short of the state-of-the-art results on longer sentences. This thesis aims to investigate deep learning and improve parsing by examining how neural networks could perform state-of-the-art parsing by comparison with PCFG parsers. We hypothesize that a neural network could be configured to implement an algorithm parallel to PCFG parsers, and examine their suitability to this task from an analytic perspective. This highlights a missing term that the RNN parser is unable to model, and we identify the role of this missing term in parsing. We finally present two methods to improve the RNN parser by building upon the analysis in earlier chapters, one using an iterative process similar to belief propagation that yields a 0.38% improvement and another replacing the scoring method with a deeper neural model yielding a 0.83% improvement. By examining an RNN parser as an exemplar of a deep neural network, we gain insights to deep machine learning and some of the approximations it must make by comparing it with well studied non-neural parsers that achieve state-of-the-art results. In this way, our research provides a better understanding of deep machine learning and a step towards improvements in parsing that will lead to smarter algorithms that can learn more accurate representations of information and the syntax and semantics of text.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

Xiao, Chunyang. „Neural-Symbolic Learning for Semantic Parsing“. Thesis, Université de Lorraine, 2017. http://www.theses.fr/2017LORR0268/document.

Der volle Inhalt der Quelle

Annotation:

Notre but dans cette thèse est de construire un système qui réponde à une question en langue naturelle (NL) en représentant sa sémantique comme une forme logique (LF) et ensuite en calculant une réponse en exécutant cette LF sur une base de connaissances. La partie centrale d'un tel système est l'analyseur sémantique qui transforme les questions en formes logiques. Notre objectif est de construire des analyseurs sémantiques performants en apprenant à partir de paires (NL, LF). Nous proposons de combiner des réseaux neuronaux récurrents (RNN) avec des connaissances préalables symboliques exprimées à travers des grammaires hors-contexte (CFGs) et des automates. En intégrant des CFGs contrôlant la validité des LFs dans les processus d'apprentissage et d'inférence des RNNs, nous garantissons que les formes logiques générées sont bien formées; en intégrant, par le biais d'automates pondérés, des connaissances préalables sur la présence de certaines entités dans la LF, nous améliorons encore la performance de nos modèles. Expérimentalement, nous montrons que notre approche permet d'obtenir de meilleures performances que les analyseurs sémantiques qui n'utilisent pas de réseaux neuronaux, ainsi que les analyseurs à base de RNNs qui ne sont pas informés par de telles connaissances préalables
Our goal in this thesis is to build a system that answers a natural language question (NL) by representing its semantics as a logical form (LF) and then computing the answer by executing the LF over a knowledge base. The core part of such a system is the semantic parser that maps questions to logical forms. Our focus is how to build high-performance semantic parsers by learning from (NL, LF) pairs. We propose to combine recurrent neural networks (RNNs) with symbolic prior knowledge expressed through context-free grammars (CFGs) and automata. By integrating CFGs over LFs into the RNN training and inference processes, we guarantee that the generated logical forms are well-formed; by integrating, through weighted automata, prior knowledge over the presence of certain entities in the LF, we further enhance the performance of our models. Experimentally, we show that our approach achieves better performance than previous semantic parsers not using neural networks as well as RNNs not informed by such prior knowledge

APA, Harvard, Vancouver, ISO und andere Zitierweisen

Roxbo, Daniel. „A Detailed Analysis of Semantic Dependency Parsing with Deep Neural Networks“. Thesis, Linköpings universitet, Interaktiva och kognitiva system, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-156831.

Der volle Inhalt der Quelle

Annotation:

The use of Long Short Term Memory (LSTM) networks continues to yield better results in natural language processing tasks. One area which recently has seen significant improvements is semantic dependency parsing, where the current state-of-the-art model uses a multilayer LSTM combined with an attention-based scoring function to predict the dependencies. In this thesis the state of the art model is first replicated and then extended to include features based on syntactical trees, which was found to be useful in a similar model. In addition, the effect of part-of-speech tags is studied. The replicated model achieves a labeled F1 score of 93.6 on the in-domain data and 89.2 on the out-of-domain data on the DM dataset, which shows that the model is indeed replicable. Using multiple features extracted from syntactic gold standard trees of the DELPH-IN Derivation Tree (DT) type increased the labeled scores to 97.1 and 94.1 respectively, while the use of predicted trees of the Stanford Basic (SB) type did not improve the results at all. The usefulness of part-of-speech tags was found to be diminished in the presence of other features.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

Buys, Jan Moolman. „Incremental generative models for syntactic and semantic natural language processing“. Thesis, University of Oxford, 2017. https://ora.ox.ac.uk/objects/uuid:a9a7b5cf-3bb1-4e08-b109-de06bf387d1d.

Der volle Inhalt der Quelle

Annotation:

This thesis investigates the role of linguistically-motivated generative models of syntax and semantic structure in natural language processing (NLP). Syntactic well-formedness is crucial in language generation, but most statistical models do not account for the hierarchical structure of sentences. Many applications exhibiting natural language understanding rely on structured semantic representations to enable querying, inference and reasoning. Yet most semantic parsers produce domain-specific or inadequately expressive representations. We propose a series of generative transition-based models for dependency syntax which can be applied as both parsers and language models while being amenable to supervised or unsupervised learning. Two models are based on Markov assumptions commonly made in NLP: The first is a Bayesian model with hierarchical smoothing, the second is parameterised by feed-forward neural networks. The Bayesian model enables careful analysis of the structure of the conditioning contexts required for generative parsers, but the neural network is more accurate. As a language model the syntactic neural model outperforms both the Bayesian model and n-gram neural networks, pointing to the complementary nature of distributed and structured representations for syntactic prediction. We propose approximate inference methods based on particle filtering. The third model is parameterised by recurrent neural networks (RNNs), dropping the Markov assumptions. Exact inference with dynamic programming is made tractable here by simplifying the structure of the conditioning contexts. We then shift the focus to semantics and propose models for parsing sentences to labelled semantic graphs. We introduce a transition-based parser which incrementally predicts graph nodes (predicates) and edges (arguments). This approach is contrasted against predicting top-down graph traversals. RNNs and pointer networks are key components in approaching graph parsing as an incremental prediction problem. The RNN architecture is augmented to condition the model explicitly on the transition system configuration. We develop a robust parser for Minimal Recursion Semantics, a linguistically-expressive framework for compositional semantics which has previously been parsed only with grammar-based approaches. Our parser is much faster than the grammar-based model, while the same approach improves the accuracy of neural Abstract Meaning Representation parsing.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

Kočiský, Tomáš. „Deep learning for reading and understanding language“. Thesis, University of Oxford, 2017. http://ora.ox.ac.uk/objects/uuid:cc45e366-cdd8-495b-af42-dfd726700ff0.

Der volle Inhalt der Quelle

Annotation:

This thesis presents novel tasks and deep learning methods for machine reading comprehension and question answering with the goal of achieving natural language understanding. First, we consider a semantic parsing task where the model understands sentences and translates them into a logical form or instructions. We present a novel semi-supervised sequential autoencoder that considers language as a discrete sequential latent variable and semantic parses as the observations. This model allows us to leverage synthetically generated unpaired logical forms, and thereby alleviate the lack of supervised training data. We show the semi-supervised model outperforms a supervised model when trained with the additional generated data. Second, reading comprehension requires integrating information and reasoning about events, entities, and their relations across a full document. Question answering is conventionally used to assess reading comprehension ability, in both artificial agents and children learning to read. We propose a new, challenging, supervised reading comprehension task. We gather a large-scale dataset of news stories from the CNN and Daily Mail websites with Cloze-style questions created from the highlights. This dataset allows for the first time training deep learning models for reading comprehension. We also introduce novel attention-based models for this task and present qualitative analysis of the attention mechanism. Finally, following the recent advances in reading comprehension in both models and task design, we further propose a new task for understanding complex narratives, NarrativeQA, consisting of full texts of books and movie scripts. We collect human written questions and answers based on high-level plot summaries. This task is designed to encourage development of models for language understanding; it is designed so that successfully answering their questions requires understanding the underlying narrative rather than relying on shallow pattern matching or salience. We show that although humans solve the tasks easily, standard reading comprehension models struggle on the tasks presented here.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

Kurita, Shuhei. „Neural Approaches for Syntactic and Semantic Analysis“. Kyoto University, 2019. http://hdl.handle.net/2433/242436.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

Marzinotto, Gabriel. „Semantic frame based analysis using machine learning techniques : improving the cross-domain generalization of semantic parsers“. Electronic Thesis or Diss., Aix-Marseille, 2019. http://www.theses.fr/2019AIXM0483.

Der volle Inhalt der Quelle

Annotation:

Rendre les analyseurs sémantiques robustes aux variations lexicales et stylistiques est un véritable défi pour de nombreuses applications industrielles. De nos jours, l'analyse sémantique nécessite de corpus annotés spécifiques à chaque domaine afin de garantir des performances acceptables. Les techniques d'apprenti-ssage par transfert sont largement étudiées et adoptées pour résoudre ce problème de manque de robustesse et la stratégie la plus courante consiste à utiliser des représentations de mots pré-formés. Cependant, les meilleurs analyseurs montrent toujours une dégradation significative des performances lors d'un changement de domaine, mettant en évidence la nécessité de stratégies d'apprentissage par transfert supplémentaires pour atteindre la robustesse. Ce travail propose une nouvelle référence pour étudier le problème de dépendance de domaine dans l'analyse sémantique. Nous utilisons un nouveau corpus annoté pour évaluer les techniques classiques d'apprentissage par transfert et pour proposer et évaluer de nouvelles techniques basées sur les réseaux antagonistes. Toutes ces techniques sont testées sur des analyseurs sémantiques de pointe. Nous affirmons que les approches basées sur les réseaux antagonistes peuvent améliorer les capacités de généralisation des modèles. Nous testons cette hypothèse sur différents schémas de représentation sémantique, langages et corpus, en fournissant des résultats expérimentaux à l'appui de notre hypothèse
Making semantic parsers robust to lexical and stylistic variations is a real challenge with many industrial applications. Nowadays, semantic parsing requires the usage of domain-specific training corpora to ensure acceptable performances on a given domain. Transfer learning techniques are widely studied and adopted when addressing this lack of robustness, and the most common strategy is the usage of pre-trained word representations. However, the best parsers still show significant performance degradation under domain shift, evidencing the need for supplementary transfer learning strategies to achieve robustness. This work proposes a new benchmark to study the domain dependence problem in semantic parsing. We use this bench to evaluate classical transfer learning techniques and to propose and evaluate new techniques based on adversarial learning. All these techniques are tested on state-of-the-art semantic parsers. We claim that adversarial learning approaches can improve the generalization capacities of models. We test this hypothesis on different semantic representation schemes, languages and corpora, providing experimental results to support our hypothesis

APA, Harvard, Vancouver, ISO und andere Zitierweisen

Tang, Anfu. „Leveraging linguistic and semantic information for relation extraction from domain-specific texts“. Electronic Thesis or Diss., université Paris-Saclay, 2023. http://www.theses.fr/2023UPASG081.

Der volle Inhalt der Quelle

Annotation:

Cette thèse a pour objet l'extraction d'informations relationnelles à partir de documents scientifiques biomédicaux, c'est-à-dire la transformation de texte non structuré en information structurée exploitable par une machine. En tant que tâche dans le domaine du traitement automatique des langues (TAL), l'extraction de relations sémantiques spécialisées entre entités textuelles rend explicite et formalise les structures sous-jacentes. Les méthodes actuelles à l'état de l'art s'appuient sur de l'apprentissage supervisé, plus spécifiquement l'ajustement de modèles de langue pré-entraînés comme BERT. L'apprentissage supervisé a besoin de beaucoup d'exemples d'apprentissages qui sont coûteux à produire, d'autant plus dans les domaines spécialisés comme le domaine biomédical. Les variants de BERT, comme par exemple PubMedBERT, ont obtenu du succès sur les tâches de TAL dans des textes biomédicaux. Nous faisons l'hypothèse que l'injection d'informations externes telles que l'information syntaxique ou la connaissance factuelle dans ces variants de BERT peut pallier le nombre réduit de données d'entraînement annotées. Dans ce but, cette thèse concevra plusieurs architectures neuronales basés sur PubMedBERT qui exploitent des informations linguistiques obtenues par analyse syntaxique ou des connaissances du domaine issues de bases de connaissance
This thesis aims to extract relations from scientific documents in the biomedical domain, i.e. transform unstructured texts into structured data that is machine-readable. As a task in the domain of Natural Language Processing (NLP), the extraction of semantic relations between textual entities makes explicit and formalizes the underlying structures. Current state-of-the-art methods rely on supervised learning, more specifically the fine-tuning of pre-trained language models such as BERT. Supervised learning requires a large amount of examples that are expensive to produce, especially in specific domains such as the biomedical domain. BERT variants such as PubMedBERT have been successful on NLP tasks involving biomedical texts. We hypothesize that injecting external information such as syntactic information or factual knowledge into such BERT variants can compensate for the reduced number of annotated training data. To this end, this thesis consists of proposing several neural architectures based on PubMedBERT that exploit linguistic information obtained by syntactic parsers or domain knowledge from knowledge bases

APA, Harvard, Vancouver, ISO und andere Zitierweisen

Ribeyre, Corentin. „Méthodes d’analyse supervisée pour l’interface syntaxe-sémantique : de la réécriture de graphes à l’analyse par transitions“. Sorbonne Paris Cité, 2016. http://www.theses.fr/2016USPCC119.

Der volle Inhalt der Quelle

Annotation:

Aujourd'hui, le volume de données textuelles disponibles est colossal. Ces données représentent des informations inestimables impossibles à traiter manuellement. De fait, il est essentiel d'utiliser des techniques de Traitement Automatique des Langues pour extraire les informations saillantes et comprendre le sens sous-jacent. Cette thèse s'inscrit dans cette perspective et proposent des ressources, des modèles et des méthodes pour permettre : (i) l'annotation automatique de corpus à l'interface entre la syntaxe et la sémantique afin d'en extraire la structure argumentale (ii) l'exploitation des ressources par des méthodes efficaces. Nous proposons d’abord un système de réécriture de graphes et un ensemble de règles de réécriture manuellement écrites permettant l'annotation automatique de la syntaxe profonde du français. Grâce à cette approche, deux corpus ont vu le jour : le DeepSequoia, version profonde du corpus Séquoia et le DeepFTB, version profonde du French Treebank en dépendances. Ensuite, nous proposons deux extensions d'analyseurs par transitions et les adaptons à l'analyse de graphes. Nous développons aussi un ensemble de traits riches issus d'analyses syntaxiques. L'idée est d'apporter des informations topologiquement variées donnant à nos analyseurs les indices nécessaires pour une prédiction performante de la structure argumentale. Couplé à un analyseur par factorisation d'arcs, cet ensemble de traits permet d'établir l'état de l'art sur le français et de dépasser celui établi pour les corpus DM et PAS sur l'anglais. Enfin, nous explorons succinctement une méthode d'induction pour le passage d'un arbre vers un graphe
Nowadays, the amount of textual data has become so gigantic, that it is not possible to deal with it manually. In fact, it is now necessary to use Natural Language Processing techniques to extract useful information from these data and understand their underlying meaning. In this thesis, we offer resources, models and methods to allow: (i) the automatic annotation of deep syntactic corpora to extract argument structure that links (verbal) predicates to their arguments (ii) the use of these resources with the help of efficient methods. First, we develop a graph rewriting system and a set of manually-designed rewriting rules to automatically annotate deep syntax in French. Thanks to this approach, two corpora were created: the DeepSequoia, a deep syntactic version of the Séquoia corpus and the DeepFTB, a deep syntactic version of the dependency version of the French Treebank. Next, we extend two transition-based parsers and adapt them to be able to deal with graph structures. We also develop a set of rich linguistic features extracted from various syntactic trees. We think they are useful to bring different kind of topological information to accurately predict predicat-argument structures. Used in an arc-factored second-order parsing model, this set of features gives the first state-of-the-art results on French and outperforms the one established on the DM and PAS corpora for English. Finally, we briefly explore a method to automatically induce the transformation between a tree and a graph. This completes our set of coherent resources and models to automatically analyze the syntax-semantics interface on French and English

APA, Harvard, Vancouver, ISO und andere Zitierweisen

Bücher zum Thema "Deep semantic parsing"

Reckman, Hilletje Gezina Bouwke. Flat but not shallow: Towards flatter representations in deep semantic parsing for precise and feasible inferencing : proefschrift. Utrecht: LOT, 2009.

Den vollen Inhalt der Quelle finden

APA, Harvard, Vancouver, ISO und andere Zitierweisen

Buchteile zum Thema "Deep semantic parsing"

Gołuchowski, Konrad, und Adam Przepiórkowski. „Semantic Role Labelling without Deep Syntactic Parsing“. In Advances in Natural Language Processing, 192–97. Berlin, Heidelberg: Springer Berlin Heidelberg, 2012. http://dx.doi.org/10.1007/978-3-642-33983-7_19.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

Jayasinghe, Ishadi, und Surangika Ranathunga. „Two-Step Memory Networks for Deep Semantic Parsing of Geometry Word Problems“. In SOFSEM 2020: Theory and Practice of Computer Science, 676–85. Cham: Springer International Publishing, 2020. http://dx.doi.org/10.1007/978-3-030-38919-2_57.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

Ravikiran, Pichika, und Midhun Chakkaravarthy. „Improved Efficiency of Semantic Segmentation using Pyramid Scene Parsing Deep Learning Network Method“. In Intelligent Systems and Sustainable Computing, 175–81. Singapore: Springer Nature Singapore, 2022. http://dx.doi.org/10.1007/978-981-19-0011-2_16.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

Konferenzberichte zum Thema "Deep semantic parsing"

Grefenstette, Edward, Phil Blunsom, Nando de Freitas und Karl Moritz Hermann. „A Deep Architecture for Semantic Parsing“. In Proceedings of the ACL 2014 Workshop on Semantic Parsing. Stroudsburg, PA, USA: Association for Computational Linguistics, 2014. http://dx.doi.org/10.3115/v1/w14-2405.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

Duong, Long, Hadi Afshar, Dominique Estival, Glen Pink, Philip Cohen und Mark Johnson. „Active learning for deep semantic parsing“. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). Stroudsburg, PA, USA: Association for Computational Linguistics, 2018. http://dx.doi.org/10.18653/v1/p18-2008.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

Sharma, Abhishek, Oncel Tuzel und David W. Jacobs. „Deep hierarchical parsing for semantic segmentation“. In 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2015. http://dx.doi.org/10.1109/cvpr.2015.7298651.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

Peng, Hao, Sam Thomson und Noah A. Smith. „Deep Multitask Learning for Semantic Dependency Parsing“. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Stroudsburg, PA, USA: Association for Computational Linguistics, 2017. http://dx.doi.org/10.18653/v1/p17-1186.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

Liu, Ziwei, Xiaoxiao Li, Ping Luo, Chen-Change Loy und Xiaoou Tang. „Semantic Image Segmentation via Deep Parsing Network“. In 2015 IEEE International Conference on Computer Vision (ICCV). IEEE, 2015. http://dx.doi.org/10.1109/iccv.2015.162.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

Xiao, Chunyang, Christoph Teichmann und Konstantine Arkoudas. „Grammatical Sequence Prediction for Real-Time Neural Semantic Parsing“. In Proceedings of the Workshop on Deep Learning and Formal Languages: Building Bridges. Stroudsburg, PA, USA: Association for Computational Linguistics, 2019. http://dx.doi.org/10.18653/v1/w19-3902.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

Liu, Hantang, Jialiang Zhang, Jianke Zhu und Steven C. H. Hoi. „DeepFacade: A Deep Learning Approach to Facade Parsing“. In Twenty-Sixth International Joint Conference on Artificial Intelligence. California: International Joint Conferences on Artificial Intelligence Organization, 2017. http://dx.doi.org/10.24963/ijcai.2017/320.

Der volle Inhalt der Quelle

Annotation:

The parsing of building facades is a key component to the problem of 3D street scenes reconstruction, which is long desired in computer vision. In this paper, we propose a deep learning based method for segmenting a facade into semantic categories. Man-made structures often present the characteristic of symmetry. Based on this observation, we propose a symmetric regularizer for training the neural network. Our proposed method can make use of both the power of deep neural networks and the structure of man-made architectures. We also propose a method to refine the segmentation results using bounding boxes generated by the Region Proposal Network. We test our method by training a FCN-8s network with the novel loss function. Experimental results show that our method has outperformed previous state-of-the-art methods significantly on both the ECP dataset and the eTRIMS dataset. As far as we know, we are the first to employ end-to-end deep convolutional neural network on full image scale in the task of building facades parsing.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

Packard, Woodley, Emily M. Bender, Jonathon Read, Stephan Oepen und Rebecca Dridan. „Simple Negation Scope Resolution through Deep Parsing: A Semantic Solution to a Semantic Problem“. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Stroudsburg, PA, USA: Association for Computational Linguistics, 2014. http://dx.doi.org/10.3115/v1/p14-1007.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

Jain, Shubham, Amy de Buitleir und Enda Fallon. „A Framework for Adaptive Deep Reinforcement Semantic Parsing of Unstructured Data“. In 2021 International Conference on Information and Communication Technology Convergence (ICTC). IEEE, 2021. http://dx.doi.org/10.1109/ictc52510.2021.9620904.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

Liao, Zhihua, und Yan Xie. „A Statistical Machine Translation Model with Forest-to-Tree Algorithm for Semantic Parsing“. In RANLP 2017 - Recent Advances in Natural Language Processing Meet Deep Learning. Incoma Ltd. Shoumen, Bulgaria, 2017. http://dx.doi.org/10.26615/978-954-452-049-6_059.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

Wir bieten Rabatte auf alle Premium-Pläne für Autoren, deren Werke in thematische Literatursammlungen aufgenommen wurden. Kontaktieren Sie uns, um einen einzigartigen Promo-Code zu erhalten!