A Deep Neural Network for Chinese Zero Pronoun Resolution

Abstract

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.

Transition-Based Disfluency Detection using LSTMs

“…Recently, deep learning methods have been widely used in many nature language processing tasks, such as name entity recognition (Lample et al, 2016), zero pronoun resolution (Yin et al, 2017) and word segmentation (Zhang et al, 2016). The effectiveness of neural features has also been studied for this framework Watanabe and Sumita, 2015;Andor et al, 2016).…”

Neural recovery machine for Chinese dropped pronoun

“…For integration, we first run our NRM on the OntoNotes 5.0 data, which is a standard and authoritative dataset for the zero pronoun resolution task. For each of the anaphoric zero pronoun, which is 20 predicted by the zero pronoun specific neural network (ZPSNN) [8], the NRM generates a pronoun, of which the representation is an embedding vector. The ZPSNN then extends its input with the recovered pronoun embedding and produces the zero pronoun resolution results.…”

“…In example (8), the antecedent of the dropped pronoun "她(She)" is absent on context. Other personal pronouns can also be placed in the position of the DP and are sensible both on syntactic and semantic.…”

Deep Reinforcement Learning for Chinese Zero Pronoun Resolution

“…Five recent zero pronoun resolution systems are employed as our baselines, namely, Zhao and Ng (2007), Chen and Ng (2015), Chen and Ng (2016), Yin et al (2017a) and Yin et al (2017b). The first of them is machine learning-based, the second is the unsupervised and the other ones are all deep learning models.…”