Determining the intended sense of words in text – word sense disambiguation (WSD) – is a long-standing problem in natural language processing. Recently, researchers have shown promising results using word vectors extracted from a neural network language model as features in WSD algorithms. However, a simple average or concatenation of word vectors for each word in a text loses the sequential and syntactic information of the text. In this paper, we study WSD with a sequence learning neural net, LSTM, to better capture the sequential and syntactic patterns of the text. To alleviate the lack of training data in all-words WSD, we employ the same LSTM in a semi-supervised label propagation classifier. We demonstrate state-of-the-art results, especially on verbs.
Dayu Yuan, Julian Richardson, Ryan Doherty, Colin Evans, and Eric Altendorf. 2016.Semi-supervised Word Sense Disambiguation with Neural Models. InProceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 1374–1385, Osaka, Japan. The COLING 2016 Organizing Committee.
@inproceedings{yuan-etal-2016-semi, title = "Semi-supervised Word Sense Disambiguation with Neural Models", author = "Yuan, Dayu and Richardson, Julian and Doherty, Ryan and Evans, Colin and Altendorf, Eric", editor = "Matsumoto, Yuji and Prasad, Rashmi", booktitle = "Proceedings of {COLING} 2016, the 26th International Conference on Computational Linguistics: Technical Papers", month = dec, year = "2016", address = "Osaka, Japan", publisher = "The COLING 2016 Organizing Committee", url = "https://aclanthology.org/C16-1130/", pages = "1374--1385", abstract = "Determining the intended sense of words in text {--} word sense disambiguation (WSD) {--} is a long-standing problem in natural language processing. Recently, researchers have shown promising results using word vectors extracted from a neural network language model as features in WSD algorithms. However, a simple average or concatenation of word vectors for each word in a text loses the sequential and syntactic information of the text. In this paper, we study WSD with a sequence learning neural net, LSTM, to better capture the sequential and syntactic patterns of the text. To alleviate the lack of training data in all-words WSD, we employ the same LSTM in a semi-supervised label propagation classifier. We demonstrate state-of-the-art results, especially on verbs."}
<?xml version="1.0" encoding="UTF-8"?><modsCollection xmlns="http://www.loc.gov/mods/v3"><mods ID="yuan-etal-2016-semi"> <titleInfo> <title>Semi-supervised Word Sense Disambiguation with Neural Models</title> </titleInfo> <name type="personal"> <namePart type="given">Dayu</namePart> <namePart type="family">Yuan</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Julian</namePart> <namePart type="family">Richardson</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Ryan</namePart> <namePart type="family">Doherty</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Colin</namePart> <namePart type="family">Evans</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Eric</namePart> <namePart type="family">Altendorf</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <originInfo> <dateIssued>2016-12</dateIssued> </originInfo> <typeOfResource>text</typeOfResource> <relatedItem type="host"> <titleInfo> <title>Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers</title> </titleInfo> <name type="personal"> <namePart type="given">Yuji</namePart> <namePart type="family">Matsumoto</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Rashmi</namePart> <namePart type="family">Prasad</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <originInfo> <publisher>The COLING 2016 Organizing Committee</publisher> <place> <placeTerm type="text">Osaka, Japan</placeTerm> </place> </originInfo> <genre authority="marcgt">conference publication</genre> </relatedItem> <abstract>Determining the intended sense of words in text – word sense disambiguation (WSD) – is a long-standing problem in natural language processing. Recently, researchers have shown promising results using word vectors extracted from a neural network language model as features in WSD algorithms. However, a simple average or concatenation of word vectors for each word in a text loses the sequential and syntactic information of the text. In this paper, we study WSD with a sequence learning neural net, LSTM, to better capture the sequential and syntactic patterns of the text. To alleviate the lack of training data in all-words WSD, we employ the same LSTM in a semi-supervised label propagation classifier. We demonstrate state-of-the-art results, especially on verbs.</abstract> <identifier type="citekey">yuan-etal-2016-semi</identifier> <location> <url>https://aclanthology.org/C16-1130/</url> </location> <part> <date>2016-12</date> <extent unit="page"> <start>1374</start> <end>1385</end> </extent> </part></mods></modsCollection>
%0 Conference Proceedings%T Semi-supervised Word Sense Disambiguation with Neural Models%A Yuan, Dayu%A Richardson, Julian%A Doherty, Ryan%A Evans, Colin%A Altendorf, Eric%Y Matsumoto, Yuji%Y Prasad, Rashmi%S Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers%D 2016%8 December%I The COLING 2016 Organizing Committee%C Osaka, Japan%F yuan-etal-2016-semi%X Determining the intended sense of words in text – word sense disambiguation (WSD) – is a long-standing problem in natural language processing. Recently, researchers have shown promising results using word vectors extracted from a neural network language model as features in WSD algorithms. However, a simple average or concatenation of word vectors for each word in a text loses the sequential and syntactic information of the text. In this paper, we study WSD with a sequence learning neural net, LSTM, to better capture the sequential and syntactic patterns of the text. To alleviate the lack of training data in all-words WSD, we employ the same LSTM in a semi-supervised label propagation classifier. We demonstrate state-of-the-art results, especially on verbs.%U https://aclanthology.org/C16-1130/%P 1374-1385
Dayu Yuan, Julian Richardson, Ryan Doherty, Colin Evans, and Eric Altendorf. 2016.Semi-supervised Word Sense Disambiguation with Neural Models. InProceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 1374–1385, Osaka, Japan. The COLING 2016 Organizing Committee.