Neural Recovery Machine for Chinese Dropped Pronoun
This addresses a key challenge in natural language processing for Chinese and other pro-drop languages, offering a more efficient method for pronoun recovery, though it appears incremental as it builds on prior work in this domain.
The paper tackled the problem of recovering dropped pronouns in Chinese, a pro-drop language, by proposing a neural recovery machine (NRM) that avoids feature engineering, and it significantly outperformed state-of-the-art approaches on two datasets while also improving zero pronoun resolution performance.
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.