Word Sense Disambiguation by Combining Labeled Data Expansion and Semi-Supervised Learning Method

Fujita, Shinya; Fujino, Akinori

doi:10.1145/2461316.2461319

Cited by 8 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Distant supervision is a learning paradigm similar to semi-supervised learning. Unlike semi-supervised methods which typically employ a supervised classifier and a small number of seed instances to do bootstrap learning (Yarowsky, 1995;Mihalcea, 2004;Fujita and Fujino, 2011), in distant supervision training data are created in a single run from scratch by aligning corpus instances with entries in a knowledge base. Distant supervision methods that have used LLRs as knowledge bases have been previously applied in relation extraction, e.g.…”

Section: Related Work and Discussionmentioning

confidence: 99%

Automated Verb Sense Labelling Based on Linked Lexical Resources

Cholakov

Eckle‐Kohler

Gurevych

2014

Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics

View full text Add to dashboard Cite

We present a novel approach for creating sense annotated corpora automatically. Our approach employs shallow syntacticosemantic patterns derived from linked lexical resources to automatically identify instances of word senses in text corpora. We evaluate our labelling method intrinsically on SemCor and extrinsically by using automatically labelled corpus text to train a classifier for verb sense disambiguation. Testing this classifier on verbs from the English MASC corpus and on verbs from the Senseval-3 all-words disambiguation task shows that it matches the performance of a classifier which has been trained on manually annotated data.

show abstract

Section: Related Work and Discussionmentioning

confidence: 99%

Automated Verb Sense Labelling Based on Linked Lexical Resources

Cholakov

Eckle‐Kohler

Gurevych

2014

Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics

View full text Add to dashboard Cite

show abstract

“…(Taghipour and Ng, 2015) and (Yuan et al, 2016) proposed a semi-supervised WSD method to use word embeddings of surrounding words of the target word and showed that the performance of WSD could be increased by taking advantage of word embeddings. (Fujita et al 2011) proposed a semi-supervised WSD method that automatically obtains reliable sense labelled examples using example sentences from the Iwanami Japanese dictionary to expand the labelled training data. Then, this method employs a maximum entropy model to construct a WSD classifier for each target word using common morphological features (surrounding words and POS tags) and topic features.…”

Section: Related Workmentioning

confidence: 99%

Semi-supervised Word Sense Disambiguation Using Example Similarity Graph

Yatabe¹,

Sasaki²

2020

Proceedings of the Graph-Based Methods for Natural Language Processing (TextGraphs)

View full text Add to dashboard Cite

Word Sense Disambiguation (WSD) is a well-known problem in the natural language processing. In recent years, there has been increasing interest in applying neural networks and machine learning techniques to solve WSD problems. However, these previous supervised approaches often suffer from the lack of manually sense-tagged examples. In this paper, to solve these problems, we propose a semi-supervised WSD method using graph embeddings based learning method in order to make effective use of labeled and unlabeled examples. The results of the experiments show that the proposed method performs better than the previous semi-supervised WSD method. Moreover, the graph structure between examples is effective for WSD and it is effective to utilize a graph structure obtained by fine-tuning BERT in the proposed method.

show abstract

“…Fujita and Fujino [11] proposed a method that provides reliable training data using example sentences from an external dictionary.…”

Section: Data Expansion Techniquementioning

confidence: 99%

Dual Sentiment Analysis: Considering Two Sides of One Review

Xia

Zong

et al. 2015

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

Bag-of-words (BOW) is now the most popular way to model text in statistical machine learning approaches in sentiment analysis. However, the performance of BOW sometimes remains limited due to some fundamental deficiencies in handling the polarity shift problem. We propose a model called dual sentiment analysis (DSA), to address this problem for sentiment classification. We first propose a novel data expansion technique by creating a sentiment-reversed review for each training and test review. On this basis, we propose a dual training algorithm to make use of original and reversed training reviews in pairs for learning a sentiment classifier, and a dual prediction algorithm to classify the test reviews by considering two sides of one review. We also extend the DSA framework from polarity (positive-negative) classification to 3-class (positivenegative-neutral) classification, by taking the neutral reviews into consideration. Finally, we develop a corpus-based method to construct a pseudo-antonym dictionary, which removes DSA's dependency on an external antonym dictionary for review reversion. We conduct a wide range of experiments including two tasks, nine datasets, two antonym dictionaries, three classification algorithms and two types of features. The results demonstrate the effectiveness of DSA in addressing polarity shift in sentiment classification.

show abstract

Word Sense Disambiguation by Combining Labeled Data Expansion and Semi-Supervised Learning Method

Cited by 8 publications

References 11 publications

Automated Verb Sense Labelling Based on Linked Lexical Resources

Automated Verb Sense Labelling Based on Linked Lexical Resources

Semi-supervised Word Sense Disambiguation Using Example Similarity Graph

Dual Sentiment Analysis: Considering Two Sides of One Review

Contact Info

Product

Resources

About