Semantics Of Sentences Research Articles

An English Teaching Ability Assessment Method Based on Fuzzy Mean-Shift Clustering

This paper presents an in-depth study and analysis of the assessment of English teaching ability using the algorithm of fuzzy mean-shift clustering. The paper proposes an automatic scoring model for Chinese-English sentence-level interpretation based on semantic scoring. The automatic scoring model calculates candidates’ Chinese-English sentence interpretation scores by fusing the feature parameters at both the phonological and content levels. Adaptive weights are introduced to fuse the current pixel and the neighborhood mean with adaptive weighting, and the weighted entropy constraint term is embedded in the clustering objective function to solve the selection problem of the weighting parameters. Finally, the graphical fuzzy division information of the neighboring pixels is used to construct the local spatial information constraint term of the current pixel, and the graphical fuzzy division term of the current pixel is adjusted to correct the clustering center obtained from the iteration. Fluency is selected as the feature scoring parameter at the speech level, and the automatic scoring model directly scores the fluency features of the candidates’ recordings; two feature scoring parameters, keywords, and sentence semantics are selected at the content level, and the content features are scored after converting the candidates’ recordings to text by manual conversion. The zero-energy product method is used to extract speech features to calculate fluency feature scores; the semantic scoring model introduced in this paper is used to calculate keyword and sentence semantic feature scores; finally, the random forest algorithm is used to fuse the above three feature scoring parameters to obtain the total quality score of Chinese-English interpretation. Considering the correlation of neighborhood pixel affiliation, the KL scatter and affiliation space information is used to supervise the current pixel affiliation, to further improve the segmentation accuracy of the algorithm; finally, segmentation tests are conducted on synthetic images, medical images, and remote sensing images. The results show that the proposed algorithm has a stronger noise suppression ability and can obtain more satisfactory segmentation results than other robust fuzzy clustering algorithms.

Emotion Analysis Model of Microblog Comment Text Based on CNN-BiLSTM.

Aiming at the problems of over reliance on labor and low generalization of traditional emotion analysis methods based on dictionary and machine learning, an emotion analysis model of microblog comment text based on deep learning is proposed. Firstly, text is obtained through microblog crawler program. After data preprocessing, including data cleaning, Chinese word segmentation, removal of stop words, and so on, the Skip-gram model is used for word vector training on a large-scale unmarked corpus, and then the trained word vector is used as the text input of CNN-BiLSTM model, which combines Bidirectional Long-Short Term Memory (BiLSTM) neural network and Convolution Neural Network (CNN). Considering the historical context information and the subsequent context information, BiLSTM can better use the temporal relationship of text to learn sentence semantics. CNN can extract hidden features from the text and combine them. Finally, after Adamax optimization training, the emotion type of microblog comment text is output. The proposed model combines the learning advantages of BiLSTM and CNN. The overall accuracy of text emotion analysis has been greatly improved, with an accuracy of 0.94 and an improvement of 8.51% compared with the single CNN model.

Multi-Label Classification in Patient-Doctor Dialogues With the RoBERTa-WWM-ext + CNN (Robustly Optimized Bidirectional Encoder Representations From Transformers Pretraining Approach With Whole Word Masking Extended Combining a Convolutional Neural Network) Model: Named Entity Study.

BackgroundWith the prevalence of online consultation, many patient-doctor dialogues have accumulated, which, in an authentic language environment, are of significant value to the research and development of intelligent question answering and automated triage in recent natural language processing studies.ObjectiveThe purpose of this study was to design a front-end task module for the network inquiry of intelligent medical services. Through the study of automatic labeling of real doctor-patient dialogue text on the internet, a method of identifying the negative and positive entities of dialogues with higher accuracy has been explored.MethodsThe data set used for this study was from the Spring Rain Doctor internet online consultation, which was downloaded from the official data set of Alibaba Tianchi Lab. We proposed a composite abutting joint model, which was able to automatically classify the types of clinical finding entities into the following 4 attributes: positive, negative, other, and empty. We adapted a downstream architecture in Chinese Robustly Optimized Bidirectional Encoder Representations from Transformers Pretraining Approach (RoBERTa) with whole word masking (WWM) extended (RoBERTa-WWM-ext) combining a text convolutional neural network (CNN). We used RoBERTa-WWM-ext to express sentence semantics as a text vector and then extracted the local features of the sentence through the CNN, which was our new fusion model. To verify its knowledge learning ability, we chose Enhanced Representation through Knowledge Integration (ERNIE), original Bidirectional Encoder Representations from Transformers (BERT), and Chinese BERT with WWM to perform the same task, and then compared the results. Precision, recall, and macro-F1 were used to evaluate the performance of the methods.ResultsWe found that the ERNIE model, which was trained with a large Chinese corpus, had a total score (macro-F1) of 65.78290014, while BERT and BERT-WWM had scores of 53.18247117 and 69.2795315, respectively. Our composite abutting joint model (RoBERTa-WWM-ext + CNN) had a macro-F1 value of 70.55936311, showing that our model outperformed the other models in the task.ConclusionsThe accuracy of the original model can be greatly improved by giving priority to WWM and replacing the word-based mask with unit to classify and label medical entities. Better results can be obtained by effectively optimizing the downstream tasks of the model and the integration of multiple models later on. The study findings contribute to the translation of online consultation information into machine-readable information.

Manifold biomedical text sentence embedding

Pretrained distributed sentence embeddings have been proven to be useful in various biomedical text tasks. However, the current research on biomedical text sentence embeddings is mainly based on Euclidean space. The geometric structure of sentences and the relations with the representations of sentence context contribute to more accurate representations of sentence semantics and still need further investigation. To address this issue, in this study, we propose a manifold biomedical text sentence embedding model. To learn biomedical text sentence embedding in the manifold space, we develop an efficient optimization algorithm with neighbourhood preserving embedding based on manifold optimization. We conducted experiments on two tasks of biomedical text classification and clustering, and the experimental results outperformed the state-of-the-art baseline models.

Attention-Based RU-BiLSTM Sentiment Analysis Model for Roman Urdu

Deep neural networks have emerged as a leading approach towards handling many natural language processing (NLP) tasks. Deep networks initially conquered the problems of computer vision. However, dealing with sequential data such as text and sound was a nightmare for such networks as traditional deep networks are not reliable in preserving contextual information. This may not harm the results in the case of image processing where we do not care about the sequence, but when we consider the data collected from text for processing, such networks may trigger disastrous results. Moreover, establishing sentence semantics in a colloquial text such as Roman Urdu is a challenge. Additionally, the sparsity and high dimensionality of data in such informal text have encountered a significant challenge for building sentence semantics. To overcome this problem, we propose a deep recurrent architecture RU-BiLSTM based on bidirectional LSTM (BiLSTM) coupled with word embedding and an attention mechanism for sentiment analysis of Roman Urdu. Our proposed model uses the bidirectional LSTM to preserve the context in both directions and the attention mechanism to concentrate on more important features. Eventually, the last dense softmax output layer is used to acquire the binary and ternary classification results. We empirically evaluated our model on two available datasets of Roman Urdu, i.e., RUECD and RUSA-19. Our proposed model outperformed the baseline models on many grounds, and a significant improvement of 6% to 8% is achieved over baseline models.

CK-Encoder: Enhanced Language Representation for Sentence Similarity

In recent years, neural networks have been widely used in natural language processing, especially in sentence similarity modeling. Most of the previous studies focused on the current sentence, ignoring the commonsense knowledge related to the current sentence in the task of sentence similarity modeling. Commonsense knowledge can be remarkably useful for understanding the semantics of sentences. CK-Encoder, which can effectively acquire commonsense knowledge to improve the performance of sentence similarity modeling, is proposed in this paper. Specifically, the model first generates a commonsense knowledge graph of the input sentence and calculates this graph by using the graph convolution network. In addition, CKER, a framework combining CK-Encoder and sentence encoder, is introduced. Experiments on two sentence similarity tasks have demonstrated that CK-Encoder can effectively acquire commonsense knowledge to improve the capability of a model to understand sentences.

Семантика безличных конструкций с дательным субъекта состояния в немецком и русском языках

The paper aims to compare the semantics of impersonal sentences with the subject of state in the dative case in the German and Russian languages. The scientific originality of the research lies in the fact that it reveals the similarities and differences in the semantics of impersonal constructions with the subject of state in the dative case in the German and Russian languages. As a result, it has been identified that certain differences can be seen in case of using nouns in the syntactic function of predicate, as well as transferring modal meanings: in the German language, the meaning of obligation cannot be delivered through impersonal constructions with the subject in the dative case.

A deep learning relation extraction approach to support a biomedical semi-automatic curation task: The case of the gluten bibliome

Discover relevant biomedical interactions in the literature is crucial for enhancing biology research. This curation process has an essential role in studying the different processes and interactions reported that affect the biological process (e.g., genome, metabolome, and transcriptome). In this sense, the objective of this work is twofold: reduce the manual effort required to curate and review the existing biochemical interactions reported in the gluten-related bibliome, while proposing a novel vector-space integrated into a deep learning model to assists manual curators in a real curation task by learning from their previous decisions. With this objective, the present work proposes a novel vector-space that combine (i) high-level lexical and syntactic inference features as Wordnets and Health-related domain ontologies, (ii) unsupervised semantic resources as word embedding, (iii) semantic and syntactic sentence knowledge, (iv) abbreviation resolution support, (v) several state-of-the-art Named-entity recognition methods, and, finally, (vi) different feature construction and optimization techniques to support a semi-automatic curation workflow. Therefore, the application of the proposed workflow over a classified set of 2,451 relevant gluten-related documents produces a total of 8,349 relevant and 471,813 irrelevant relations distributed in thirteen domain health-related categories. Experimental results showed that the proposed workflow is a valuable approach for a semi-automatic relation extraction task. It was able to obtain satisfactory results in the early stages of a real-world curation task and saved manual annotation efforts by learning from the decisions made by manual curators in iterative annotation rounds. The average F.score for the proposed relation categories was 0.731, being the lowest F.score at 0.47 and the highest F.score at 0.929. The different resources used in this work as well as the manually curated corpus are public available on our GitHub repository.

Semantic Role Labeling Integrated with Multilevel Linguistic Cues and Bi-LSTM-CRF

Chinese Semantic Role Labeling (SRL) is the core technology of semantic understanding. In the field of Chinese information processing, where statistical machine learning is still the mainstream, the traditional labeling methods rely heavily on the parsing degree of syntax and semantics of sentences. Therefore, the labeling precision is limited and cannot meet the current needs. This paper adopts the model based on a bidirectional long short-term memory network combined with the Conditional Random Field (Bi-LSTM-CRF). In the feature processing stage, pooling technology is combined with sampling and selecting multifeature vector groups to improve the performance of the sequence labeling model. Lexical, syntactic, and other multilevel linguistic features are integrated into the training to realize in-depth improvement of the original labeling model. Through several groups of experiments, the precision of model annotation in this paper has been significantly improved combined with linguistic-assisted analysis, which proves that it can optimize the annotation performance of the model by integrating relevant linguistic features into the model based on Bi-LSTM-CRF and sampling and extracting multifeature groups; the evaluation of F increases to 82.18 percent.

Dynamical Systems Implementation of Intrinsic Sentence Meaning

This paper proposes a model for implementation of intrinsic natural language sentence meaning in a physical language understanding system, where 'intrinsic' is understood as 'independent of meaning ascription by system-external observers'. The proposal is that intrinsic meaning can be implemented as a point attractor in the state space of a nonlinear dynamical system with feedback which is generated by temporally sequenced inputs. It is motivated by John Searle's well known (Behavioral and Brain Sciences, 3: 417–57, 1980) critique of the then-standard and currently still influential computational theory of mind (CTM), the essence of which was that CTM representations lack intrinsic meaning because that meaning is dependent on ascription by an observer. The proposed dynamical model comprises a collection of interacting artificial neural networks, and constitutes a radical simplification of the principle of compositional phrase structure which is at the heart of the current standard view of sentence semantics because it is computationally interpretable as a finite state machine.

Pluralities, counterparts, and groups.

I formulate a theory of groups based on pluralities and counterparts: roughly put, a group is a plurality of entities at a time. This theory comes with counterpart-theoretic semantics for modal and temporal sentences about groups. So this theory of groups is akin to the stage theory of material objects: both take the items they analyze to exist at a single time, and both use counterparts to satisfy certain conditions relating to the modal properties, temporal properties, and coincidence properties of those items.

SSIN: Sentence Semantic Interaction Network for Multi-Choice Reading Comprehension

Multiple-choice reading comprehension is a challenging task in natural language processing, which aims to select the correct answer from a set of candidate options when given passage and question. Previous approaches usually focus only on word vector interactions and ignore the importance of sentence semantics for reading when modeling the relationship between passage and question. However, reading is a process that includes complex interactions of various knowledge such as vocabulary, syntax and semantics. Interactions based on word vectors alone do not effectively capture the relationship between passage and question. In this work, we propose the Sentence Semantic Interaction Network (SSIN), which models the relationship among passage, question, and answer options based on sentence semantics. The experimental results show that superior results are achieved on both the RACE and MCTest datasets, confirming that the interaction based on sentence semantic vectors can effectively improve the performance of the model reading comprehension.

ГРАМАТИЧНІ ФОРМИ СУБ’ЄКТАВ СЕМАНТИКО-СИНТАКСИЧНІЙСТРУКТУРІ РЕЧЕННЯ

The article is devoted to the analysis of case forms that implement the subjective meaning in the semantic structure of a simple sentence. The attention is paid to the noun forms of the nominative, vocative, genitive, dative, accusative and instrumental cases of an agent in the Ukrainian sentence. The grammar functions of an agent in different cases are considered, i.e. of a subject in the nominative and vocative cases, of an object in the genitive, dative, accusative and instrumental cases. Background. The analysis of the sentence semantics involves the study of the interaction between its semantic and formal layout. The interrelation between sentence semantic and syntactic structures reveals formal models of predicative grammar constructions. Purpose. The analysed models with subject syntaxemes denoting an agent, an experiencer, an actor, quantity, quality, and a location enable linguists and language learners to determine the grammatical means of expressing substantive (subject) semantics. Methods. In the study of grammatical forms of subject syntaxemes, the structural method is used, in particular, the methods of sentence model transformation and component analysis. In a number of cases, these techniques helped to reveal that a substantive syntaxeme with subject semantics, expressed in the indirect (genitive, dative, accusative, instrumental) case, is regularly transformed into a subject syntaxeme in the nominative case in the grammatical position of the subject. Results. The grammar models considered in the article demonstrate that the semantic subject of the Ukrainian sentence can be expressed by all case forms without preposition. The variety of forms and means of subject expression allows the noun and its equivalents to realize their agent function in a semantic-syntactic combination with predicates of both verbal and its derivative forms (noun, numeral, adjective, adverbial) nature. Conclusion. The main grammar form of expressing subjectivity is the nominative case combined with a predicate of action, state, process, quantitative, qualitative or locative feature. The vocative case regularly denotes the subject of addressed speech, the other morphological forms of subjects (genitive, dative, accusative, instrumental) have a much narrower application in the Ukrainian sentence.

Weakly Supervised Temporal Adjacent Network for Language Grounding

Temporal language grounding (TLG) is a fundamental and challenging problem for vision and language understanding. Existing methods mainly focus on fully supervised setting with temporal boundary labels for training, which, however, suffers expensive cost of annotation. In this work, we are dedicated to weakly supervised TLG, where multiple description sentences are given to an untrimmed video without temporal boundary labels. In this task, it is critical to learn a strong cross-modal semantic alignment between sentence semantics and visual content. To this end, we introduce a novel weakly supervised temporal adjacent network (WSTAN) for temporal language grounding. Specifically, WSTAN learns cross-modal semantic alignment by exploiting temporal adjacent network in a multiple instance learning (MIL) paradigm, with a whole description paragraph as input. Moreover, we integrate a complementary branch into the framework, which explicitly refines the predictions with pseudo supervision from the MIL stage. An additional self-discriminating loss is devised on both the MIL branch and the complementary branch, aiming to enhance semantic discrimination by self-supervising. Extensive experiments are conducted on three widely used benchmark datasets, <i>i.e.</i>, ActivityNet-Captions, Charades-STA, and DiDeMo, and the results demonstrate the effectiveness of our approach.

Development and Analysis of a Sentence Semantics Representation Model

Development and Analysis of a Sentence Semantics Representation Model

Stable Contrastive Learning for Self-Supervised Sentence Embeddings With Pseudo-Siamese Mutual Learning

Learning semantic sentence embeddings is beneficial to a variety of natural language processing tasks. Recently, methods using the contrastive learning framework to fine-tune pre-trained language models have been proposed and have achieved significant performance on sentence embeddings. However, sentence embeddings are easy to “overfit” to the contrastive learning goal. With the training of contrastive learning, the gap between contrastive learning and test tasks leads to unstable even declining performance on test tasks. For this reason, existing methods rely on the labeled development set to frequently evaluate the performance on test tasks and get the best checkpoints. In such a way, models are limited when the labeled data is unavailable or extremely scarce. To address this problem, we propose <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">P</i> seudo- <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S</i> iamese network <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">M</i> utual <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">L</i> earning (PSML) for self-supervised sentence embeddings to reduce the gap between contrastive learning and test tasks. Consisting of the main encoder and the auxiliary encoder, PSML utilizes mutual learning as the basic framework. Between the two encoders, two mutual learning losses are constructed to share learning signals. The proposed model framework and losses of PSML help the model be optimized more stably and generalize better to test tasks, such as semantic textual similarity. Extensive experiments on seven public semantic textual similarity datasets show that PSML performs better than previous unsupervised contrastive methods for sentence embeddings. Besides, PSML also gives a stable performance curve on test tasks with training and is able to get the comparative performance without frequent evaluation on the labeled development set.

Metonymy and Croatian adverbial clauses

In this article I examine some metonymic aspects of the semantics of Croatian connectives introducing adverbial clauses of cause, condition, purpose, and concession. The analysis leans on the theory of conceptual metaphor and metonymy and, to a lesser extent, on cognitive grammar. It is also informed by grammaticalization scholarship within typological functionalism. I explore metonymic mappings between the categories of time and cause, manner and cause, cause and condition, purpose, cause and concession, condition and concession, time and condition, and metonymic mappings operating at the level of speech acts. The goal is to contribute to the growing, though still arguably small, body of cognitive linguistic research into the relevance of metonymy for the semantics of complex sentences, specifically the role it plays in subordination, and to expand this analysis to subordinate constructions in Croatian. Some attention is given to grammaticalization studies, where metaphor and metonymy are seen as two types of pragmatic inferencing facilitating interactions between the mentioned semantic categories in complex sentences.

A philosophically neutral semantics for perception sentences

AbstractJaakko Hintikka proposed treating objectual perception sentences, such as “Alice sees Bob,” as de re propositional perception sentences. Esa Saarinen extended Hintikka's idea to eventive perception sentences, such as “Alice sees Bob smile.” These approaches, elegant as they may be, are not philosophically neutral, for they presuppose, controversially, that the content of all perceptual experiences is propositional in nature. The aim of this paper is to propose a formal treatment of objectual and eventive perception sentences that builds on Hintikka's modal approach to propositional attitude ascriptions while avoiding controversial assumptions on the nature of perceptual experiences. Despite being simple and theoretically frugal, our approach is powerful enough to express a variety of interesting philosophical views about propositional, objectual, and eventive perception sentences, thus enabling the study of their inferential relationships.

Linguistic Creativity of the Indonesian for Foreign Speakers (BIPA) Students at the Morphological, Syntactic, and Semantic Levels

The research aimed to describe the forms of linguistic creativity of BIPA students at the morphological, syntactic, and semantic levels. The research method used was descriptive qualitative with content analysis techniques. The research data were 78 sentences written by BIPA students at Bina Nusantara University academic year 2020/2021. The results show that BIPA students’ sentences have linguistic creativity in the form of the morphological, syntactic, and semantic levels sentences. At the morphological level, the process of linguistic creativity in words is carried out by (1) inserting foreign terms into sentences, (2) using non-standard words, and (3) abbreviating words. While in phrases, linguistic creativity is done by (1) reversing the structure of the phrase, (2) forming nominal phrases with less common word pairs, and (3) forming nominal phrases by incorporating elements of student culture. At the syntactic level, linguistic creativity is carried out in the form of compiling compound sentences with the expansion of descriptions, expansion of objects, expansion of subjects, and expansion of predicates. At the semantic level, linguistic creativity is manifested in the form of the figure of speech: personification, simile, hyperbole, repetition, and metaphor.

Efficient Estimate of Low-Frequency Words’ Embeddings Based on the Dictionary: A Case Study on Chinese

Obtaining high-quality embeddings of out-of-vocabularies (OOVs) and low-frequency words is a challenge in natural language processing (NLP). To efficiently estimate the embeddings of OOVs and low-frequency words, we propose a new method that uses the dictionary to estimate the embeddings of OOVs and low-frequency words. More specifically, the explanatory note of an entry in dictionaries accurately describes the semantics of the corresponding word. Naturally, we adopt the sentence representation model to extract the semantics of the explanatory note and regard the semantics as the embedding of the corresponding word. We design a new sentence representation model to encode sentences to extract the semantics from the explanatory notes of entries more efficiently. Based on the assumption that the higher quality of word embeddings will lead to better performance, we design an extrinsic experiment to evaluate the quality of low-frequency words’ embeddings. The experimental results show that the embeddings of low-frequency words estimated by our proposed method have higher quality. In addition, both intrinsic and extrinsic experiments show that our proposed sentence representation model can represent the semantics of sentences well.