All-words Word Sense Disambiguation Using Concept Embeddings

All-words Word Sense Disambiguation Using Concept Embeddings Rui Suzuki, Kanako Komiya, Masayuki Asahara, Minoru Sasaki, Hiroyuki Shinnou Ibaraki University, 4-12-1 Nakanarusawa, Hitachi, Ibaraki JAPAN, National Institute for Japanese Language and Linguistics, 10-2 Midoricho, Tachikawa, Tokyo, JAPAN, {17nm709g@vc.ibaraki.ac.jp, kanako.komiya.nlp, minoru.sasaki.01, hiroyuki.shinnou.0828} @vc.ibaraki.ac.jp, masayu-a@ninjal.ac.jp Abstract All-words word sense disambiguation (all-words WSD) is the task of identifying the senses of all words in a document. Since the sense of a word depends on the context, such as the surrounding words, similar words are believed to have similar sets of surrounding words. We therefore predict the target word senses by calculating the distances between the surrounding word vectors of the target words and their synonyms using word embeddings. In addition, we introduce the new idea of concept embeddings, constructed from concept tag sequences created from the results of previous prediction steps. We predict the target word senses using the distances between surrounding word vectors constructed from word and concept embeddings, via a bootstrapped iterative process. Experimental results show that these concept embeddings were able to improve the performance of Japanese all-words WSD. Keywords: word sense disambiguation, all-words, unsupervised 1. Introduction Word sense disambiguation (WSD) involves identifying the senses of words in documents. In particular, the WSD task where the senses of all the words in a document are disam- biguated is referred to as all-words WSD. Much research has been carried out, not only on English WSD but also on Japanese WSD, for many years. However, there has been little research on Japanese all-words WSD, possibly because no tagged corpus has been available that was large enough for the task. Usually, the Japanese sense dataset Balanced Corpus of Contemporary Written Japanese (BC- CWJ) (Maekawa et al., 2014), tagged with sense IDs from Iwanami Kokugo Jiten (Nishio et al., 1994), is used for su- pervised WSD. However, unsupervised approaches to all- words WSD often require synonym information, which sense datasets cannot provide. This paper reports research on Japanese all-words WSD that uses a corpus that is in its infancy, namely BCCWJ annotated with concept tags or article numbers from the Word List by Semantic Prin- ciples (WLSP) (Kokuritsukokugokenkyusho, 1964), which is a Japanese thesaurus. In the WLSP, the article numbers indicate shared synonyms. In the WLSP thesaurus, words are classified and organized by their meanings1 and each WLSP record contains the fol- lowing fields: record ID number; lemma number; record type; class; division; section; article; article number; para- graph number; small paragraph number; word number; lemma (with explanatory note); lemma (without explana- tory note); reading; and reverse reading. Each record has an article number, which represents four fields: class; division; section; and article. For example, the word “犬”(inu, mean- ing spy or dog) has two records in the WLSP, and therefore has two article numbers, 1.2410 and 1.5501, indicating that the word is polysemous. In addition, there are 240 seman- tic breaks in the WLSP, which allow words to be classified in more detail than with the article numbers alone. Note that the article numbers …

Content truncated to 500 words