Academic literature on the topic 'Semantic pivot'

Cross-domain sentiment classification aims to leverage useful knowledge from a source domain to mitigate the supervision sparsity in a target domain. A series of approaches depend on the pivot features that behave similarly for polarity prediction in both domains. However, the engineering of such pivot features remains cumbersome and prevents us from learning the disentangled and transferable representations from rich semantic and syntactic information. Towards learning the pivots and representations simultaneously, we propose a new Transferable Pivot Transformer (TPT). Our model consists of two networks: a Pivot Selector that learns to detect transferable n-gram pivots from contexts, and a Transferable Transformer that learns to generate domain-invariant representations by modeling the correlation between pivot and non-pivot words. The Pivot Selector and Transferable Transformer are jointly optimized through end-to-end back-propagation. We experiment with real tasks of cross-domain sentiment classification over 20 domain pairs where our model outperforms prior arts.

We offer a new analysis of the semantics of the English it-cleft, building on recent work on exclusive particles such as "only." The analysis emphasizes the discourse function of clefts — which, we claim, is to terminate a line of inquiry by marking an answer as complete. It accounts for the semantic effects — not previously appreciated — of focus placement within the cleft pivot. It also provides a solution to a previously discussed problem with the projection of exhaustivity from embedded contexts.

A novel method for finding linear mappings among word embeddings for several languages, taking as pivot a shared, multilingual embedding space, is proposed in this paper. Previous approaches learned translation matrices between two specific languages, while this method learns translation matrices between a given language and a shared, multilingual space. The system was first trained on bilingual, and later on multilingual corpora as well. In the first case, two different training data were applied: Dinu’s English–Italian benchmark data, and English–Italian translation pairs extracted from the PanLex database. In the second case, only the PanLex database was used. The system performs on English–Italian languages with the best setting significantly better than the baseline system given by Mikolov, and it provides a comparable performance with more sophisticated systems. Exploiting the richness of the PanLex database, the proposed method makes it possible to learn linear mappings among an arbitrary number of languages.

Many studies have been carried out in order to increase thesearch efficiency of constraint satisfaction problems; among them,some make use of structural properties of the constraintnetwork; others take into account semantic properties of theconstraints, generally assuming that all the constraints possessthe given property. In this paper, we propose a new decompositionmethod benefiting from both semantic properties of functional constraints (not bijective constraints) and structuralproperties of the network; furthermore, not all the constraints needto be functional. We show that under some conditions, the existenceof solutions can be guaranteed. We first characterize a particularsubset of the variables, which we name a root set. We thenintroduce pivot consistency, a new local consistency which is aweak form of path consistency and can be achieved in O(n^2d^2)complexity (instead of O(n^3d^3) for path consistency), and wepresent associated properties; in particular, we show that anyconsistent instantiation of the root set can be linearly extended to a solution, which leads to the presentation of the aforementioned new method for solving by decomposing functional CSPs.

The center pivot irrigation system (CPIS) is a modern irrigation technique widely used in precision agriculture due to its high efficiency in water consumption and low labor compared to traditional irrigation methods. The CPIS is a leader in mechanized irrigation in Brazil, with growth forecast for the coming years. Therefore, the mapping of center pivot areas is a strategic factor for the estimation of agricultural production, ensuring food security, water resources management, and environmental conservation. In this regard, digital processing of satellite images is the primary tool allowing regional and continuous monitoring with low costs and agility. However, the automatic detection of CPIS using remote sensing images remains a challenge, and much research has adopted visual interpretation. Although CPIS presents a consistent circular shape in the landscape, these areas can have a high internal variation with different plantations that vary over time, which is difficult with just the spectral behavior. Deep learning using convolutional neural networks (CNNs) is an emerging approach that provokes a revolution in image segmentation, surpassing traditional methods, and achieving higher accuracy and efficiency. This research aimed to evaluate the use of deep semantic segmentation of CPIS from CNN-based algorithms using Landsat-8 surface reflectance images (seven bands). The developed methodology can be subdivided into the following steps: (a) Definition of three study areas with a high concentration of CPIS in Central Brazil; (b) acquisition of Landsat-8 images considering the seasonal variations of the rain and drought periods; (c) definition of CPIS datasets containing Landsat images and ground truth mask of 256×256 pixels; (d) training using three CNN architectures (U-net, Deep ResUnet, and SharpMask); (e) accuracy analysis; and (f) large image reconstruction using six stride values (8, 16, 32, 64, 128, and 256). The three methods achieved state-of-the-art results with a slight prevalence of U-net over Deep ResUnet and SharpMask (0.96, 0.95, and 0.92 Kappa coefficients, respectively). A novelty in this research was the overlapping pixel analysis in the large image reconstruction. Lower stride values had improvements quantified by the Receiver Operating Characteristic curve (ROC curve) and Kappa, and fewer errors in the frame edges were also perceptible. The overlapping images significantly improved the accuracy and reduced the error present in the edges of the classified frames. Additionally, we obtained greater accuracy results during the beginning of the dry season. The present study enabled the establishment of a database of center pivot images and an adequate methodology for mapping the center pivot in central Brazil.

Since the colloquial Arabic is now widespread it is required to describe the collection and classification of a multi-dialectal corpus of Arabic. Nowadays, colloquial multi-dialectal comes in almost country based forms such as Egyptian, Iraqi, Levantine, Tunisian, etc. This paper discusses a new method for analyzing the conversation of the educational chat room using Corpus for Palestinian Arabic and Stanford Tagger. This method represents the key words using semantic net-like representation to obtain the main subjects of the conversation. The main subject of the chat is obtained using the proposed method which shows a high accuracy. Using Arabic Corpus, Stanford Tagger and percentage of words will add more accuracy. The study also examines the effect of pivot distribution based on occurrences and <em>betweeness</em> values of the pivots over the text. This study examines some of the characteristics of the texts written in colloquial Arabic dialect and analyzes the free expressive Arabic statements. The results of the paper show that the core can be determined by combining both the occurrences and the distribution of the word over the conversation.

Since the colloquial Arabic is now widespread it is required to describe the collection and classification of a multi-dialectal corpus of Arabic. Nowadays, colloquial multi-dialectal comes in almost country based forms such as Egyptian, Iraqi, Levantine, Tunisian, etc. This paper discusses a new method for analyzing the conversation of the educational chat room using Corpus for Palestinian Arabic and Stanford Tagger. This method represents the key words using semantic net-like representation to obtain the main subjects of the conversation. The main subject of the chat is obtained using the proposed method which shows a high accuracy. Using Arabic Corpus, Stanford Tagger and percentage of words will add more accuracy. The study also examines the effect of pivot distribution based on occurrences and <em>betweeness</em> values of the pivots over the text. This study examines some of the characteristics of the texts written in colloquial Arabic dialect and analyzes the free expressive Arabic statements. The results of the paper show that the core can be determined by combining both the occurrences and the distribution of the word over the conversation.

Food safety comment classification represents a specialized task within the realm of text classification. The objective is to efficiently identify a large volume of food safety comments, aiding relevant authorities in timely food analysis and safety alerts. Traditional methods typically employ one-hot encoding for label processing. However, in real-world situations, classified labels often convey valuable semantic information and guidance. This paper introduces an innovative approach to enhance the classification performance of food safety comments by embedding label information. Initially, we extracted generic sentiment pivot words from various classification labels as label description information. Subsequently, we employ a joint embedding approach to integrate this label description information into the text. This process will pool the expressions of the pivot word into the corresponding sentiment labels in the known domains after averaging to get the embedded expression. This aims to acquire highly detailed self-semantic feature vectors and self-knowledge feature vectors that are integrated with labeled descriptive information. Then, feed the semantic representation of comments and the word-embedded representation of labeled description information into a time-step-based multilayer Bi-LSTM and a step-based multilayer CNN, respectively. Ultimately, we concatenate these two feature vectors to facilitate matching, thereby fusing the self-semantic and self-knowledge features of labeled description information to train a classification model for food safety comments. Experimental results on the food safety comment dataset showcase a noteworthy improvement of 1.74% and 1.27% in Macro_Precision and Macro_F1 metrics, respectively, compared to BERT, BERT-RNN, and BERT-CNN. Through extensive ablation experiments and additional studies, our method effectively embeds labeling information, demonstrating a clear advantage over traditional methods in the task of classifying food safety comments. Doi: 10.28991/HIJ-2024-05-01-013 Full Text: PDF

This study, in two parts, endeavors a novel analysis of existential constructions, based on a different theoretical setting of clause structure, where the predicate is taken as a necessary and sufficient constituent of the clause. Leaning on this perception, the analyses of existential constructions developed here tries to overcome the discrepancy between form and (semantic and informational) meaning in Hebrew existential constructions. The main part of the study deals with affirmative existential-presentative constructions, used to introduce referents into the discourse. Most of the constructions have been analyzed as consisting of an existential constituent, viewed as a modal marker, and a pivot, regarded as the core component of the predicate domain. This analysis is shown to be valid for both the existential marker jeʃ and for its suppletive verbal forms, derived from √hjj ‘be’. A distinction is made between verbal forms with non-referential and referential verb-bound person markers, where the latter, found with expected, known or given pivots, function as focus marking devices, coming in complementary distribution with prosodic marking of focus. Thus, presentative-existential sentences are formed as unipartite sentences, consisting of only a predicate domain. The last two sections of Part I deal with constructions where the existential constituent follows the pivot and with constructions where the pivot is definite. Part II deals with other existential constructions, including negative constructions; bipartite existential sentences; existential constituents as sole constituents in a sentence; existential constituents with clitic referential markers; and the use of existential markers as interjections or discourse markers.