Intra-Sentential Subject Zero Anaphora Resolution using Multi-Column Convolutional Neural Network

Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 1244–1254, Austin, Texas, November 1-5, 2016. c⃝2016 Association for Computational Linguistics Intra-Sentential Subject Zero Anaphora Resolution using Multi-Column Convolutional Neural Network Ryu Iida Kentaro Torisawa Jong-Hoon Oh Canasai Kruengkrai Julien Kloetzer National Institute of Information and Communications Technology Kyoto 619-0289, Japan {ryu.iida,torisawa,rovellia,canasai,julien}@nict.go.jp Abstract This paper proposes a method for intra- sentential subject zero anaphora resolution in Japanese. Our proposed method utilizes a Multi-column Convolutional Neural Network (MCNN) for predicting zero anaphoric rela- tions. Motivated by Centering Theory and other previous works, we exploit as clues both the surface word sequence and the dependency tree of a target sentence in our MCNN. Even though the F-score of our method was lower than that of the state-of-the-art method, which achieved relatively high recall and low preci- sion, our method achieved much higher pre- cision (>0.8) in a wide range of recall lev- els. We believe such high precision is cru- cial for real-world NLP applications and thus our method is preferable to the state-of-the-art method. 1 Introduction In such pro-drop languages as Japanese, Chinese and Italian, pronouns are frequently omitted in text. For example, the subject of uketa (suffered) is unre- alized in the following Japanese example (1): (1) sono-houkokusho-wa seifui-ga the report-TOP governmenti-SUBJ jouyaku-o teiketsushi (ϕi-ga) keizaitekini treaty-OBJ make iti-SUBJ economically higai-o uke-ta koto-o shitekishi-ta damage-OBJ suffer-PAST COMP point out-PAST The report pointed out that the governmenti agreed to a treaty and (iti) suffered economically. The omitted argument is called a zero anaphor, which is represented using ϕ. In example (1), zero anaphor ϕi refers to its antecedent, seifui (govern- ment). Such a reference phenomenon is called zero anaphora. Identifying zero anaphoric relations is an essential task in developing such accurate NLP applications as information extraction and machine translation for pro-drop languages. For example, in Japanese, 60% of subjects in newspaper articles are unrealized as zero anaphors (Iida et al., 2007). This paper proposes a method for intra-sentential subject zero anaphora resolution, in which a zero anaphor and its antecedent appear in the same sen- tence and the zero anaphor must be a subject of a predicate, for Japanese. We target subject zero anaphors because they represent 85% of the intra- sentential zero anaphora in our data set (example (1) is such a case). Furthermore, this work focuses on intra-sentential zero anaphora because inter- sentential cases, in which a zero anaphor and its an- tecedent do not appear in the same sentence, are ex- tremely difficult. The accuracy of the state-of-the- art method for resolving inter-sentential anaphora is low (Sasano and Kurohashi, 2011), and we believe the current technologies are not mature enough to deal with inter-sentential cases. Our method locally predicts the likelihood of a zero anaphoric relation between every possible com- bination of potential zero anaphor and potential an- tecedent without considering the other (potential) zero anaphoric relations in the same sentence. The final determination of zero anaphoric relations for each zero anaphor in a given …

Content truncated to 500 words