Empty Category Detection using Path Features and Distributed Case Frames

Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 1335–1340, Lisbon, Portugal, 17-21 September 2015. c⃝2015 Association for Computational Linguistics. Empty Category Detection using Path Features and Distributed Case Frames Shunsuke Takeno†, Masaaki Nagata‡, Kazuhide Yamamoto† †Nagaoka University of Technology, 1603-1 Kamitomioka, Nagaoka, Niigata, 940-2188 Japan {takeno, yamamoto}@jnlp.org ‡NTT Communication Science Laboratories, NTT Corporation, 2-4 Hikaridai, Seika-cho, Soraku-gun, Kyoto, 619-0237 Japan nagata.masaaki@labs.ntt.co.jp Abstract We describe an approach for machine learning-based empty category detection that is based on the phrase structure analy- sis of Japanese. The problem is formal- ized as tree node classification, and we find that the path feature, the sequence of node labels from the current node to the root, is highly effective. We also find that the set of dot products between the word embeddings for a verb and those for case particles can be used as a substitution for case frames. Experiments show that the proposed method outperforms the previ- ous state-of the art method by 68.6% to 73.2% in terms of F-measure. 1 Introduction Empty categories are phonetically null elements that are used for representing dropped pro- nouns (“pro” or “small pro”), controlled elements (“PRO” or “big pro”) and traces of movement (“T” or “trace”), such as WH-questions and rela- tive clauses. They are important for pro-drop lan- guages such as Japanese, in particular, for the ma- chine translation from pro-drop languages to non- pro-drop languages such as English. Chung and Gildea (2010) reported their recover of empty cat- egories improved the accuracy of machine trans- lation both in Korean and in Chinese. Kudo et al. (2014) showed that generating zero subjects in Japanese improved the accuracy of preordering- based translation. State-of-the-art statistical syntactic parsers had typically ignored empty categories. Although Penn Treebank (Marcus et al., 1993) has annota- tions on PRO and trace, they provide only labeled bracketing. Johnson (2002) proposed a statistical pattern-matching algorithm for post-processing the results of syntactic parsing based on minimal unlexicalized tree fragments from empty node to its antecedent. Dienes and Dubey (2003) proposed a machine learning-based “trace tagger” as a pre- process of parsing. Campbell (2004) proposed a rule-based post-processing method based on lin- guistically motivated rules. Gabbard et al. (2006) replaced the rules with machine learning-based classifiers. Schmid (2006) and Cai et al. (2011) integrated empty category detection with the syn- tactic parsing. Empty category detection for pro (dropped pro- nouns or zero pronoun) has begun to receive at- tention as the Chinese Penn Treebank (Xue et al., 2005) has annotations for pro as well as PRO and trace. Xue and Yang (2013) formalized the problem as classifying each pair of the location of empty category and its head word in the de- pendency structure. Wang et al. (2015) pro- posed a joint embedding of empty categories and their contexts on dependency structure. Xiang et al. (2013) formalized the problem as classifying each IP node (roughly corresponds to S and SBAR in Penn Treebank) in the phrase structure. In this paper, we propose …

Content truncated to 500 words