Word Sense Disambiguation Performance Research Articles

Effect of Supervised Sense Disambiguation Model Using Machine Learning Technique and Word Embedding in Word Sense Disambiguation

Natural language processing includes a subfield called word sense disambiguation, which focuses mostly on words that might have several meanings. Polysemous terms are also referred to as confusing phrases in some circles. The performance of word sense disambiguation depends on how effectively the ambiguous word is recognized by the machine. The discussed word embedding model for the ambiguous words represents the words from the document space to vector space with no data loss. The most identified challenge of ambiguous word representation is the features. The selection and representation of ambiguous words with respect to the features is the tedious task of word embedding. The discussed word embedding model uses countable features of available context for disambiguation. The proposed model is implemented for ambiguous words with context information. The available context of ambiguous/polysemous words is used for disambiguation. The unavailability of the context is the challenge in this model. The Recurrent Neural Network with Large Small Term Memory is used for the classification. The output of the RNN-LSTM is the sense values which are further mapped with the freely available lexical resource WordNet for retrieving the correct sense(meaning).

Wiki sense bag creation using multilingual word sense disambiguation

Performance of word sense disambiguation (WSD) is one of the challenging tasks in the area of natural language processing (NLP). Generation of sense annotated corpus for multilingual word sense disambiguation is out of reach for most languages even if resources are available. In this paper we propose an unsupervised method using word and sense embedding or improving the performance of these systems using untagged. Corpora and create two bags namely ontological bag and wiki sense bag to generate the senses with highest similarity. Wiki sense bag provides external knowledge to the system required to boost the disambiguation accuracy. We explore Word2Vec model to generate the sense bag and observe significant performance gain for our dataset.

Deep analysis of word sense disambiguation via semi-supervised learning and neural word representations

• Ambiguity is a challenging task in text mining addressed for word-sense disambiguation algorithms. • The lack of labeled dataset is a barrier and semi-supervised learning (SSL) addresses this problem. • Our method explored SSL and word-embeddings CBOW, SKIP-GRAM, FASTTEXT, GLOVE, BERT and ELECTRA . • The F1-score increases in several datasets like Senseval-2, Senseval-3, Semeval-2007 and Semcor. Word Sense Disambiguation (WSD) aims to determine the meaning of a word in context. Different approaches have been proposed in supervised and unsupervised domains. In most cases, supervised learning provides superior WSD performance. Since sense-annotated corpora can be difficult or time-consuming to obtain, which must be repeated for new domains, languages, and sense inventories, semi-supervised learning (SSL) methods, that combine a small amount of sense-annotated data, start to be pre-eminent. In SSL, graph-based methods are common, because they capture the relationships between terms using an undirected graph. This paper aims to investigate semi-supervised WSD by considering different graph-based SSL algorithms with features generated by word embeddings from Word2Vec, FastText, GloVe, BERT and ELECTRA models combined with parts-of-speech tags and word context. We test several combinations of word-embedding models, similarity measures for graph construction and SSL classification algorithms to disambiguate classical lexical sample WSD datasets. The results indicate our SSL algorithms achieved competitive results compared to supervised ones and the ELECTRA models performed better than other embeddings for SSL.

Capsule Network Improved Multi-Head Attention for Word 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.

Word sense disambiguation based on context selection using knowledge-based word similarity

In this paper, we introduce a novel knowledge-based word-sense disambiguation (WSD) system. In particular, the main goal of our research is to find an effective way to filter out unnecessary information by using word similarity. For this, we adopt two methods in our WSD system. First, we propose a novel encoding method for word vector representation by considering the graphical semantic relationships from the lexical knowledge bases, and the word vector representation is utilized to determine the word similarity in our WSD system. Second, we present an effective method for extracting the contextual words from a text for analyzing an ambiguous word based on word similarity. The results demonstrate that the suggested methods significantly enhance the baseline WSD performance in all corpora. In particular, the performance on nouns is similar to those of the state-of-the-art knowledge-based WSD models, and the performance on verbs surpasses that of the existing knowledge-based WSD models.

Multilingual Approach to Word Sense Disambiguation Using word2vec and Sense Embedding With Semantic Cloud

Word Sense Disambiguation(WSD) is an open problem in the area of Natural language processing. Many WSD systems uses knowledge based unsupervised approach as it bares us from using tagged corpus. But this approach depends extensively on knowledge. Enhancing the knowledge for ambiguity resolution is one of the important issues in WSD. Although Multilingual lexical resource is an asset for knowledge based systems(KBS), many KBS have not yield satisfactory results due to lack of sufficient information required for disambiguation. Multilingual information can help boost the performance of WSD in various languages. Combining lexical semantic information from different languages helps improve WSD task. We make use of Babel Net, a huge multilingual resource provider to attain the task and design a semantic word cloud to provide high performance disambiguation by imposing additional knowledge.

Two Knowledge-based Methods for High-Performance Sense Distribution Learning

Knowing the correct distribution of senses within a corpus can potentially boost the performance of Word Sense Disambiguation (WSD) systems by many points. We present two fully automatic and language-independent methods for computing the distribution of senses given a raw corpus of sentences. Intrinsic and extrinsic evaluations show that our methods outperform the current state of the art in sense distribution learning and the strongest baselines for the most frequent sense in multiple languages and on domain-specific test sets. Our sense distributions are available at http://trainomatic.org.

Word Sense Disambiguation Based on Perceptron Model

Word sense disambiguation (WSD) is an important research topic in natural language processing field, which is very useful for machine translation and information retrieval. In this paper, a linear combination model based on multiple discriminative features is proposed to determine correct sense of an ambiguous word, in which morphology and part of speech in left and right words around ambiguous word are used as features. Then, perceptron algorithm is applied to optimize the WSD model. Experiments show that the WSD performance is improved after the proposed method is applied.

Semi-supervised Learning with Induced Word Senses for State of the Art Word Sense Disambiguation

Word Sense Disambiguation (WSD) aims to determine the meaning of a word in context, and successful approaches are known to benefit many applications in Natural Language Processing. Although supervised learning has been shown to provide superior WSD performance, current sense-annotated corpora do not contain a sufficient number of instances per word type to train supervised systems for all words. While unsupervised techniques have been proposed to overcome this data sparsity problem, such techniques have not outperformed supervised methods. In this paper, we propose a new approach to building semi-supervised WSD systems that combines a small amount of sense-annotated data with information from Word Sense Induction, a fully-unsupervised technique that automatically learns the different senses of a word based on how it is used. In three experiments, we show how sense induction models may be effectively combined to ultimately produce high-performance semi-supervised WSD systems that exceed the performance of state-of-the-art supervised WSD techniques trained on the same sense-annotated data. We anticipate that our results and released software will also benefit evaluation practices for sense induction systems and those working in low-resource languages by demonstrating how to quickly produce accurate WSD systems with minimal annotation effort.

Chinese Word Sense Disambiguation Based on Beam Search

Research on word sense disambiguation (WSD) is of great importance in natural language processing. In this paper, a new method based on beam search algorithm for Chinese WSD is proposed. By mining potential knowledge between phrase and semantic category in a sentence, this approach can construct its semantic network. It searches an optimal semantic category sequence from a Chinese sentence's semantic network with beam search algorithm, so that correct meanings of ambiguous words can be found from the optimal sequence. Experiments show that a better WSD performance is gotten.

Effectiveness Comparison of Feature Words for Word Sense Disambiguation

The context of ambiguous words is the most important clue for word sense disambiguation (WSD). The selection and weight assignment of feature words affect the performance of WSD directly. The existing method usually selects the words in a certain length of window as feature words, which is easy to induce noise words in a short distance and neglect feature words in a long distance. Syntax parsing can analyze syntactic relations among words and output phrase structure tree or dependency tree of the sentence, which could be utilized to select feature words. The paper proposes the methods to select feature words based on phrase structure tree and dependency tree, and compares their effectiveness in detail. The results of experiments show that the method to select feature words and assign their weights with dependency tree is a preferred strategy for WSD.

종속격 정보를 적용한 동사 의미 중의성 해소

동형이의어는 여러 가지 의미를 가진 단어를 의미한다. 문장의 의미를 이해하기 위해서는 필수적으로 문장에 포함된 동형이의어의 의미를 결정해야 한다. 기존의 단어 의미 중의성 연구들은 공기 빈도를 기반으로 해결하였다. 하지만, 동사의 경우에는 정확도 향상을 위해서 격 정보가 중요하다. 왜냐하면, 동사 동형이의어의 의미는 행위의 주체나 객체에 따라 결정되어서 종속격(목적격, 부사격, 보격) 정보가 필요하며, 동사동형이의어 의미마다 서로 다른 격 정보가 필요하기 때문이다. 본 논문에서는 한국어 격 정보를 적용한 동사 의미 중의성 해소를 제안한다. 격정보는 표준국어대사전에 명시된 조사 정보를 이용하였다. 실험은 고빈도 동형이의어 12개를 대상으로 하였으며, 실험결과 정확도가 기존의 97.3%에서 98.7%로 1.34% 향상되었다. 이는 원래의 오류율을 2.7%에서 1.3%으로 절반정도 줄였다. Homographs can have multiple senses. In order to understand the meaning of a sentence, it is necessary to identify which sense isused for each word in the sentence. Previous researches on this problem heavily relied on the word co-occurrence information. However, we noticed that in case of verbs, information about subordinating cases of verbs can be utilized to further improve the performance of word sense disambiguation. Different senses require different sets of subordinating cases. In this paper, we propose the verb sense disambiguation using subordinating case information. The case information acquire postposition features in Standard Korean Dictionary. Our experiment on 12 high-frequency verb homographs shows that adding case information can improve the performance of word sense disambiguation by 1.34%, from 97.3% to 98.7%. The amount of improvement may seem marginal, we think it is meaningful because the error ratio reduced to less than a half, from 2.7% to 1.3%.

Studying the correlation between different word sense disambiguation methods and summarization effectiveness in biomedical texts

BackgroundWord sense disambiguation (WSD) attempts to solve lexical ambiguities by identifying the correct meaning of a word based on its context. WSD has been demonstrated to be an important step in knowledge-based approaches to automatic summarization. However, the correlation between the accuracy of the WSD methods and the summarization performance has never been studied.ResultsWe present three existing knowledge-based WSD approaches and a graph-based summarizer. Both the WSD approaches and the summarizer employ the Unified Medical Language System (UMLS) Metathesaurus as the knowledge source. We first evaluate WSD directly, by comparing the prediction of the WSD methods to two reference sets: the NLM WSD dataset and the MSH WSD collection. We next apply the different WSD methods as part of the summarizer, to map documents onto concepts in the UMLS Metathesaurus, and evaluate the summaries that are generated. The results obtained by the different methods in both evaluations are studied and compared.ConclusionsIt has been found that the use of WSD techniques has a positive impact on the results of our graph-based summarizer, and that, when both the WSD and summarization tasks are assessed over large and homogeneous evaluation collections, there exists a correlation between the overall results of the WSD and summarization tasks. Furthermore, the best WSD algorithm in the first task tends to be also the best one in the second. However, we also found that the improvement achieved by the summarizer is not directly correlated with the WSD performance. The most likely reason is that the errors in disambiguation are not equally important but depend on the relative salience of the different concepts in the document to be summarized.

Disambiguation of ambiguous biomedical terms using examples generated from the UMLS Metathesaurus

Researchers have access to a vast amount of information stored in textual documents and there is a pressing need for the development of automated methods to enable and improve access to this resource. Lexical ambiguity, the phenomena in which a word or phrase has more than one possible meaning, presents a significant obstacle to automated text processing. Word Sense Disambiguation (WSD) is a technology that resolves these ambiguities automatically and is an important stage in text understanding. The most accurate approaches to WSD rely on manually labeled examples but this is usually not available and is prohibitively expensive to create. This paper offers a solution to that problem by using information in the UMLS Metathesaurus to automatically generate labeled examples. Two approaches are presented. The first is an extension of existing work (Liu et al., 2002 [1]) and the second a novel approach that exploits information in the UMLS that has not been used for this purpose. The automatically generated examples are evaluated by comparing them against the manually labeled ones in the NLM-WSD data set and are found to outperform the baseline. The examples generated using the novel approach produce an improvement in WSD performance when combined with manually labeled examples.

An Experimental Study of Graph Connectivity for Unsupervised Word Sense Disambiguation

Word sense disambiguation (WSD), the task of identifying the intended meanings (senses) of words in context, has been a long-standing research objective for natural language processing. In this paper, we are concerned with graph-based algorithms for large-scale WSD. Under this framework, finding the right sense for a given word amounts to identifying the most "important" node among the set of graph nodes representing its senses. We introduce a graph-based WSD algorithm which has few parameters and does not require sense-annotated data for training. Using this algorithm, we investigate several measures of graph connectivity with the aim of identifying those best suited for WSD. We also examine how the chosen lexicon and its connectivity influences WSD performance. We report results on standard data sets and show that our graph-based approach performs comparably to the state of the art.

Word Sense Disambiguation by Learning Decision Trees from Unlabeled Data

In this paper we describe a machine learning approach to word sense disambiguation that uses unlabeled data. Our method is based on selective sampling with committees of decision trees. The committee members are trained on a small set of labeled examples which are then augmented by a large number of unlabeled examples. Using unlabeled examples is important because obtaining labeled data is expensive and time-consuming while it is easy and inexpensive to collect a large number of unlabeled examples. The idea behind this approach is that the labels of unlabeled examples can be estimated by using committees. Using additional unlabeled examples, therefore, improves the performance of word sense disambiguation and minimizes the cost of manual labeling. Effectiveness of this approach was examined on a raw corpus of one million words. Using unlabeled data, we achieved an accuracy improvement up to 20.2%.