scholarly journals Graph Convolutional Network for Word Sense Disambiguation

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Chun-Xiang Zhang ◽  
Rui Liu ◽  
Xue-Yao Gao ◽  
Bo Yu
Keyword(s):  
Language Processing ◽  
Word Sense Disambiguation ◽  
Ambiguous Word ◽  
Semantic Category ◽  
Word Sense ◽  
Convolutional Network ◽  
Part Of Speech ◽  
Average Accuracy ◽  
Test Corpus ◽  
Sense Disambiguation

Word sense disambiguation (WSD) is an important research topic in natural language processing, which is widely applied to text classification, machine translation, and information retrieval. In order to improve disambiguation accuracy, this paper proposes a WSD method based on the graph convolutional network (GCN). Word, part of speech, and semantic category are extracted from contexts of the ambiguous word as discriminative features. Discriminative features and sentence containing the ambiguous word are used as nodes to construct the WSD graph. Word2Vec tool, Doc2Vec tool, pointwise mutual information (PMI), and TF-IDF are applied to compute embeddings of nodes and edge weights. GCN is used to fuse features of a node and its neighbors, and the softmax function is applied to determine the semantic category of the ambiguous word. Training corpus of SemEval-2007: Task #5 is adopted to optimize the proposed WSD classifier. Test corpus of SemEval-2007: Task #5 is used to test the performance of WSD classifier. Experimental results show that average accuracy of the proposed method is improved.

scholarly journals A Novel Approach to Word Sense Disambiguation Based on Topical and Semantic Association

2013 ◽  
Vol 2013 ◽  
pp. 1-8 ◽  
Author(s):  
Xin Wang ◽  
Wanli Zuo ◽  
Ying Wang
Keyword(s):  
Language Processing ◽  
Fundamental Problem ◽  
Word Sense Disambiguation ◽  
Ambiguous Word ◽  
Semantic Features ◽  
Word Sense ◽  
Semantic Association ◽  
Data Set ◽  
Novel Approach ◽  
Sense Disambiguation

Word sense disambiguation (WSD) is a fundamental problem in nature language processing, the objective of which is to identify the most proper sense for an ambiguous word in a given context. Although WSD has been researched over the years, the performance of existing algorithms in terms of accuracy and recall is still unsatisfactory. In this paper, we propose a novel approach to word sense disambiguation based on topical and semantic association. For a given document, supposing that its topic category is accurately discriminated, the correct sense of the ambiguous term is identified through the corresponding topic and semantic contexts. We firstly extract topic discriminative terms from document and construct topical graph based on topic span intervals to implement topic identification. We then exploit syntactic features, topic span features, and semantic features to disambiguate nouns and verbs in the context of ambiguous word. Finally, we conduct experiments on the standard data set SemCor to evaluate the performance of the proposed method, and the results indicate that our approach achieves relatively better performance than existing approaches.

Word-Sense Disambiguation

2012 ◽  
Author(s):  
Mark Stevenson ◽  
Yorick Wilks
Keyword(s):  
Language Processing ◽  
Word Sense Disambiguation ◽  
Syntactic Analysis ◽  
Word Sense ◽  
Part Of Speech Tagging ◽  
Part Of Speech ◽  
Evaluation Strategies ◽  
Sense Disambiguation ◽  
Translation Systems ◽  
Speech Tagging

Word-sense disambiguation (WSD) is the process of identifying the meanings of words in context. This article begins with discussing the origins of the problem in the earliest machine translation systems. Early attempts to solve the WSD problem suffered from a lack of coverage. The main approaches to tackle the problem were dictionary-based, connectionist, and statistical strategies. This article concludes with a review of evaluation strategies for WSD and possible applications of the technology. WSD is an ‘intermediate’ task in language processing: like part-of-speech tagging or syntactic analysis, it is unlikely that anyone other than linguists would be interested in its results for their own sake. ‘Final’ tasks produce results of use to those without a specific interest in language and often make use of ‘intermediate’ tasks. WSD is a long-standing and important problem in the field of language processing.

scholarly journals Capsule Network Improved Multi-Head Attention for Word Sense Disambiguation

2021 ◽  
Vol 11 (6) ◽  
pp. 2488
Author(s):  
Jinfeng Cheng ◽  
Weiqin Tong ◽  
Weian Yan
Keyword(s):  
Neural Networks ◽  
Language Processing ◽  
Semantic Representation ◽  
Word Sense Disambiguation ◽  
Ambiguous Word ◽  
Word Sense ◽  
Great Contribution ◽  
Specific Context ◽  
The Core ◽  
Sense Disambiguation

Word sense disambiguation (WSD) is one of the core problems in natural language processing (NLP), which is to map an ambiguous word to its correct meaning in a specific context. There has been a lively interest in incorporating sense definition (gloss) into neural networks in recent studies, which makes great contribution to improving the performance of WSD. However, disambiguating polysemes of rare senses is still hard. In this paper, while taking gloss into consideration, we further improve the performance of the WSD system from the perspective of semantic representation. We encode the context and sense glosses of the target polysemy independently using encoders with the same structure. To obtain a better presentation in each encoder, we leverage the capsule network to capture different important information contained in multi-head attention. We finally choose the gloss representation closest to the context representation of the target word as its correct sense. We do experiments on English all-words WSD task. Experimental results show that our method achieves good performance, especially having an inspiring effect on disambiguating words of rare senses.

scholarly journals Query Expansion using Semantic Network for Information Retrieval in Telugu Language

2019 ◽  
Vol 8 (2) ◽  
pp. 874-877
Keyword(s):  
Information Retrieval ◽  
Language Processing ◽  
Query Expansion ◽  
Retrieval System ◽  
Semantic Network ◽  
Word Sense Disambiguation ◽  
Ambiguous Word ◽  
Information Retrieval System ◽  
Word Sense ◽  
Sense Disambiguation

Now-a-days digital documents are playing a major role in all the areas /web, as such all the information is digitalised. Queries are used by the search engines to retrieve the information. Query plays a major role in information retrieval system, as a result relevant and non relevant documents are retrieved. Query expansion techniques will better the performance of the information retrieval system. Our proposed query expansion technique is Word Sense Disambiguation. This is to find the correct sense of the ambiguous word in regional Telugu language. In Query expansion, if the added query term is an ambiguous word, accuracy of relevant documents will be very less. So to avoid this, proposed method Word Sense Disambiguation (WSD) is used, which is related to NLP Natural Language Processing and Artificial Intelligence AI. WSD improves the accuracy of information retrieval system.

Word Sense Disambiguation for Improving the Quality of Machine Translation

2014 ◽  
Vol 981 ◽  
pp. 153-156
Author(s):  
Chun Xiang Zhang ◽  
Long Deng ◽  
Xue Yao Gao ◽  
Li Li Guo
Keyword(s):  
Machine Translation ◽  
Language Processing ◽  
Word Sense Disambiguation ◽  
Ambiguous Word ◽  
Translation System ◽  
Word Sense ◽  
Ambiguous Words ◽  
Sense Disambiguation ◽  
Machine Translation System

Word sense disambiguation is key to many application problems in natural language processing. In this paper, a specific classifier of word sense disambiguation is introduced into machine translation system in order to improve the quality of the output translation. Firstly, translation of ambiguous word is deleted from machine translation of Chinese sentence. Secondly, ambiguous word is disambiguated and the classification labels are translations of ambiguous word. Thirdly, these two translations are combined. 50 Chinese sentences including ambiguous words are collected for test experiments. Experimental results show that the translation quality is improved after the proposed method is applied.

Research of Word Sense Disambiguation Based on Soft Pattern

2011 ◽  
Vol 460-461 ◽  
pp. 130-135
Author(s):  
Ke Liang Jia
Keyword(s):  
Language Processing ◽  
Word Sense Disambiguation ◽  
Ambiguous Word ◽  
Difficult Problem ◽  
Maximum Matching ◽  
Word Sense ◽  
Word Context ◽  
Nature Language Processing ◽  
Sense Disambiguation ◽  
Matching Degree

Word sense disambiguation (WSD) is always an important and difficult problem that requires to be solved in Nature Language Processing. This paper presents a new WSD method which is based on soft pattern matching. The method can learn the soft patterns from the sense of the ambiguous word and its context, to construct a soft pattern - based database. At last the sense of the ambiguous word is labeled by choosing the sense with the maximum matching degree between the ambiguous word context and the soft pattern. The experiment result shows that the method has high precision.

scholarly journals Numerical Simulation of Ambiguity Resolution in Multiple Information Streams Based on Network Machine Translation

Complexity ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-10
Author(s):  
Lei Wang ◽  
Qun Ai
Keyword(s):  
Mutual Information ◽  
Natural Language ◽  
Language Processing ◽  
Domain Knowledge ◽  
Word Sense Disambiguation ◽  
Word Segmentation ◽  
Word Sense ◽  
Test Corpus ◽  
Sense Disambiguation ◽  
Professional Fields

In natural language, the phenomenon of polysemy is widespread, which makes it very difficult for machines to process natural language. Word sense disambiguation is a key issue in the field of natural language processing. This paper introduces the more common statistical learning methods used in the field of word sense disambiguation. Using the naive Bayesian machine learning method and the feature vector set extracted and constructed by the Dice coefficient method, a semantic word disambiguation model based on semantics is realized. The results of comparative experiments show that the proposed method is better compared with known systems. This paper proposes a method for disambiguation of word segmentation in professional fields based on unsupervised learning. This method does not rely on professional domain knowledge and training corpus and only uses the frequency, mutual information, and boundary entropy information of the string in the test corpus to solve the problem of word segmentation ambiguity. The experimental results show that these three evaluation standards can solve the problem of word segmentation ambiguity in professional fields and improve the effect of word segmentation. Among them, the segmentation result using mutual information is the best, and the performance is stable.

IMPROVING WORD SENSE DISAMBIGUATION WITH AUTOMATICALLY RETRIEVED SEMANTIC KNOWLEDGE

2008 ◽  
Vol 02 (03) ◽  
pp. 365-380 ◽  
Author(s):  
DMITRIY DLIGACH ◽  
MARTHA PALMER
Keyword(s):  
Language Processing ◽  
Word Sense Disambiguation ◽  
Ambiguous Word ◽  
Semantic Knowledge ◽  
Word Sense ◽  
Novel Approach ◽  
Sense Disambiguation ◽  
Dependency Parser ◽  
Semantic Properties ◽  
Large Corpus

Word Sense Disambiguation (WSD) is an important problem in Natural Language Processing. Supervised WSD involves assigning a sense from some sense inventory to each occurrence of an ambiguous word. Verb sense distinctions often depend on the distinctions in the semantics of the target verb's arguments. Therefore, some method of capturing their semantics is crucial to the success of a VSD system. In this paper we propose a novel approach to encoding the semantics of the noun arguments of a verb. This approach involves extracting various semantic properties of that verb from a large text corpus. We contrast our approach with the traditional methods and show that it performs better while the only resources it requires are a large corpus and a dependency parser.

scholarly journals Attention Neural Network for Biomedical Word Sense Disambiguation

2022 ◽  
Vol 2022 ◽  
pp. 1-14
Author(s):  
Chun-Xiang Zhang ◽  
Shu-Yang Pang ◽  
Xue-Yao Gao ◽  
Jia-Qi Lu ◽  
Bo Yu
Keyword(s):  
Neural Network ◽  
Semantic Information ◽  
Short Term Memory ◽  
Word Sense Disambiguation ◽  
Semantic Category ◽  
Word Sense ◽  
Short Term ◽  
Part Of Speech ◽  
Sense Disambiguation ◽  
Long Short Term Memory

In order to improve the disambiguation accuracy of biomedical words, this paper proposes a disambiguation method based on the attention neural network. The biomedical word is viewed as the center. Morphology, part of speech, and semantic information from 4 adjacent lexical units are extracted as disambiguation features. The attention layer is used to generate a feature matrix. Average asymmetric convolutional neural networks (Av-ACNN) and bidirectional long short-term memory (Bi-LSTM) networks are utilized to extract features. The softmax function is applied to determine the semantic category of the biomedical word. At the same time, CNN, LSTM, and Bi-LSTM are applied to biomedical WSD. MSH corpus is adopted to optimize CNN, LSTM, Bi-LSTM, and the proposed method and testify their disambiguation performance. Experimental results show that the average disambiguation accuracy of the proposed method is improved compared with CNN, LSTM, and Bi-LSTM. The average disambiguation accuracy of the proposed method achieves 91.38%.

scholarly journals Supervised Word Sense Disambiguation with Recurrent Neural Network Model

2019 ◽  
Vol 9 (2) ◽  
pp. 1447-1453
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Natural Language ◽  
Language Processing ◽  
Word Processing ◽  
Word Sense Disambiguation ◽  
Ambiguous Word ◽  
Word Sense ◽  
Single Word ◽  
Sense Disambiguation

Disambiguating words is a branch of artificial intelligence that deals with natural language processing. The dissatisfaction of the motive of the word deals with the polysemy of the ambiguous word, processing a single word in natural language, having two or more meanings where the corresponding context discriminates the meaning. Humans are intelligent enough to derive the meaning of the word because they are a biological neural network. Computers can be trained in such a way that they should function similarly to biological neural networks. There are four different suggested approaches to clutter as the knowledge-dependent approach and the machine learning based models which are further classified as supervised, semi-supervised and unpublished learning models. The purpose of this research is to improve better communication between computers and humans. The discussed model used a supervised learning approach with recurrent neural networks.

Sign in / Sign up

Export Citation Format

Share Document