Zero-anaphora resolution by learning rich syntactic pattern features

et al. 2019

Front. Comput. Sci.

Dropped pronouns (DPs) are ubiquitous in pro-drop languages like Chinese, Japanese etc. Previous work mainly focused on painstakingly exploring the empirical features for DPs recovery. In this paper, we propose a neural recovery machine (NRM) to model and recover DPs in Chinese, so that to avoid the non-trivial feature engineering process. The experimental results show that the proposed NRM significantly outperforms the state-of-the-art approaches on both two heterogeneous datasets. Further experiment results of Chinese zero pronoun (ZP) resolution show that the performance of ZP resolution can also be improved by recovering the ZPs to DPs.

Section: Zero Pronoun Resolutionmentioning

confidence: 99%

Neural recovery machine for Chinese dropped pronoun

Zhang

et al. 2019

Front. Comput. Sci.

“…Ferrández and Peral (2000) proposed a set of hand-crafted rules for Spanish ZP resolution. Recently, supervised approaches have been exploited for ZP resolution in Korean (Han, 2006) and Japanese (Isozaki and Hirao, 2003;Iida et al, 2006Iida et al, , 2007Sasano and Kurohashi, 2011). Iida and Poesio (2011) developed a cross-lingual approach for Japanese and Italian ZPs where an ILPbased model was employed to zero anaphora detection and resolution.…”

Section: Zero Pronoun Resolutionmentioning

confidence: 99%

“…Previous works on zero pronoun (ZP) resolution mainly focused on the supervised learning approaches (Han, 2006;Zhao and Ng, 2007;Iida et al, 2007;Kong and Zhou, 2010;Iida and Poesio, 2011;Chen and Ng, 2013). However, a major obstacle for training the supervised learning models for ZP resolution is the lack of annotated data.…”

Section: Introductionmentioning

confidence: 99%

Generating and Exploiting Large-scale Pseudo Training Data for Zero Pronoun Resolution

Cui

Proceedings of the 55th Annual Meeting of the Association For Computational Linguistics (Volume 1: Long Papers)

et al. 2017

Most existing approaches for zero pronoun resolution are heavily relying on annotated data, which is often released by shared task organizers. Therefore, the lack of annotated data becomes a major obstacle in the progress of zero pronoun resolution task. Also, it is expensive to spend manpower on labeling the data for better performance. To alleviate the problem above, in this paper, we propose a simple but novel approach to automatically generate large-scale pseudo training data for zero pronoun resolution. Furthermore, we successfully transfer the cloze-style reading comprehension neural network model into zero pronoun resolution task and propose a two-step training mechanism to overcome the gap between the pseudo training data and the real one. Experimental results show that the proposed approach significantly outperforms the state-of-the-art systems with an absolute improvements of 3.1% F-score on OntoNotes 5.0 data.

“…Ferrández and Peral [2000] propose a set of hand-crafted rules for Spanish ZP resolution. Recently, supervised approaches have been exploited for ZP resolution in Korean [Han, 2006] and Japanese [Isozaki and Hirao, 2003;Iida et al, 2006;Iida et al, 2007;Imamura et al, 2009;Sasano and Kurohashi, 2011;Iida and Poesio, 2011]. Iida et al [2015] propose a novel approach of recognizing subject sharing relations, where an ILP-based zero anaphora resolution method is combined to improve the performance of intra-sentential zero anaphora resolution in Japanese.…”

Section: Zero Pronoun Resolution For Other Languagesmentioning

confidence: 99%

A Deep Neural Network for Chinese Zero Pronoun Resolution

Zhang

Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence

2017

Existing approaches for Chinese zero pronoun resolution overlook semantic information. This is because zero pronouns have no descriptive information, which results in difficulty in explicitly capturing their semantic similarities with antecedents. Moreover, when dealing with candidate antecedents, traditional systems simply take advantage of the local information of a single candidate antecedent while failing to consider the underlying information provided by the other candidates from a global perspective. To address these weaknesses, we propose a novel zero pronoun-specific neural network, which is capable of representing zero pronouns by utilizing the contextual information at the semantic level. In addition, when dealing with candidate antecedents, a two-level candidate encoder is employed to explicitly capture both the local and global information of candidate antecedents. We conduct experiments on the Chinese portion of the OntoNotes 5.0 corpus. Experimental results show that our approach substantially outperforms the state-of-the-art method in various experimental settings.