Intra-sentential Zero Anaphora Resolution using Subject Sharing Recognition
34315Authors
nan
Abstract
In this work, we improve the performance of intra-sentential zero anaphora resolu- tion in Japanese using a novel method of recognizing subject sharing relations. In Japanese, a large portion of intra- sentential zero anaphora can be regarded as subject sharing relations between pred- icates, that is, the subject of some predi- cate is also the unrealized subject of other predicates. We develop an accurate rec- ognizer of subject sharing relations for pairs of predicates in a single sentence, and then construct a subject shared pred- icate network, which is a set of predi- cates that are linked by the subject shar- ing relations recognized by our recognizer. We finally combine our zero anaphora resolution method exploiting the subject shared predicate network and a state-of- the-art ILP-based zero anaphora resolution method. Our combined method achieved a significant improvement over the the ILP- based method alone on intra-sentential zero anaphora resolution in Japanese. To the best of our knowledge, this is the first work to explicitly use an independent sub- ject sharing recognizer in zero anaphora resolution. 1
Keywords
Full Content
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 2179–2189, Lisbon, Portugal, 17-21 September 2015. c⃝2015 Association for Computational Linguistics. Intra-sentential Zero Anaphora Resolution using Subject Sharing Recognition Ryu Iida Kentaro Torisawa Chikara Hashimoto Jong-Hoon Oh Julien Kloetzer National Institute of Information and Communications Technology Kyoto 619-0289, Japan {ryu.iida,torisawa,ch,rovellia,julien}@nict.go.jp Abstract In this work, we improve the performance of intra-sentential zero anaphora resolu- tion in Japanese using a novel method of recognizing subject sharing relations. In Japanese, a large portion of intra- sentential zero anaphora can be regarded as subject sharing relations between pred- icates, that is, the subject of some predi- cate is also the unrealized subject of other predicates. We develop an accurate rec- ognizer of subject sharing relations for pairs of predicates in a single sentence, and then construct a subject shared pred- icate network, which is a set of predi- cates that are linked by the subject shar- ing relations recognized by our recognizer. We finally combine our zero anaphora resolution method exploiting the subject shared predicate network and a state-of- the-art ILP-based zero anaphora resolution method. Our combined method achieved a significant improvement over the the ILP- based method alone on intra-sentential zero anaphora resolution in Japanese. To the best of our knowledge, this is the first work to explicitly use an independent sub- ject sharing recognizer in zero anaphora resolution. 1 Introduction In ‘pro-dropped’ languages such as Japanese, Chi- nese and Italian, pronouns are often unrealized in text. For example, the subject of nomu (take) is omitted in example (1). (1) Tomi-wa infuruenza-ni natta-node , Tom-TOP flu-IOBJ had-since punc (ϕi-ga) kusuri-o non-da . hei-SUBJ medicine-OBJ took period Since Tomi had the flu, (hei) took medicine. Such unrealized pronouns are regarded as zero anaphors, which are indicated using ϕ in liter- ature, like ϕi-ga in example (1). refers to its antecedent somewhere.Zero anaphor This phe- nomenon of the reference is called zero anaphora. In Japanese, about 60% of subjects appear as zero anaphors in newspaper articles (Iida et al., 2007b), and thus zero anaphora resolution is an essential task for developing highly accurate machine trans- lation and information extraction systems. In this paper, we propose a novel method of re- solving intra-sentential zero anaphora, in which a subject zero anaphor refers to its antecedent in- side a single sentence. This work does not ad- dress inter-sentential zero anaphora, in which a zero anaphor in a sentence refers to its antecedent in another sentence. The novelty of our method is in the use of subject sharing relations, which are relations between two predicates that share a subject by (zero) anaphora or coreference. For ex- ample, in example (2), there are two subject shar- ing relations for predicate pairs, advance-plan and plan-dispatch, as illustrated in Figure 1. (2) seifui-wa (ϕi-ga) hisaichi-ni governmenti-TOP iti-SUBJ disaster site-IOBJ 50 nin-o hakensuru koto-o (ϕi-ga) 50 people-OBJ dispatch COMP-OBJ iti-SUBJ keikakusi junbisagyo-o susumeru . plan preparation-OBJ advance period The governmenti plans that (iti) will dispatch 50 people to the …
Content truncated to 500 words
Labeled Text
In this work, we improve the performance of intra-sentential zero anaphora resolution in Japanese using a novel method of recognizing subject sharing relations. In Japanese, a large portion of intrasentential zero anaphora can be regarded as subject sharing relations between predicates, that is, the subject of some predicate is also the unrealized subject of other predicates. We develop an accurate recognizer of subject sharing relations for pairs of predicates in a single sentence, and then construct a subject shared predicate network, which is a set of predicates that are linked by the subject sharing relations recognized by our recognizer. We finally combine our zero anaphora resolution method exploiting the subject shared predicate network and a state-ofthe-art ILP-based zero anaphora resolution method. Our combined method achieved a significant improvement over the the ILPbased method alone on intra-sentential zero anaphora resolution in Japanese. To the best of our knowledge, this is the first work to explicitly use an independent subject sharing recognizer in zero anaphora resolution. 1
Publication Details
- Paper ID:
- 34315
- Year:
- 2015
- Publication:
- TIPSTER
- Publication Type:
- conf
- DOI:
- nan