Deep Neural Architecture for Recovering Dropped Pronouns in Korean

다국어 초록 (Multilingual Abstract)

Pronouns are frequently dropped in Korean sentences, especially in text messages in the mobile phone environment. Restoring dropped pronouns can be a beneficial preprocessing task for machine translation, information extraction, spoken dialog systems, and many other applications. In this work, we address the problem of dropped pronoun recovery by resolving two simultaneous subtasks: detecting zero‐pronoun sentences and determining the type of dropped pronouns. The problems are statistically modeled by encoding the sentence and classifying types of dropped pronouns using a recurrent neural network (RNN) architecture. Various RNN‐based encoding architectures were investigated, and the stacked RNN was shown to be the best model for Korean zero‐pronoun recovery. The proposed method does not require any manual features to be implemented; nevertheless, it shows good performance.

참고문헌 (Reference)

1 P. Jing, "Zero-Anaphora Resolution in Chinese Using Maximum Entropy" 90 (90): 1092-1102, 2007

2 W. Yang, "Zero Pronoun Resolution in Chinese Using Machine Learning Plus Shallow Parsing" 905-910, 2008

3 A. Park, "Zero Object Resolution in Korean" 439-448, 2015

4 M. Hermans, "Training and Analyzing Deep Recurrent Neural Networks" 190-198, 2013

5 황민국, "Structural SVM을 이용한 백과사전 문서 내 생략 문장성분 복원" 한국지능정보시스템학회 21 (21): 131-150, 2015

6 S.J. Lee, "Restoring an Elided Title for Encyclopedia QA System" 32 (32): 541-543, 2005

7 Y. Yang, "Recovering Dropped Pronouns from Chinese Text Messages" 309-313, 2015

8 S.P. Converse, "Pronominal Anaphora Resolution in Chinese" Univ. Pennsylvania 2006

9 H. Sak, "Long Short-Term Memory Recurrent Neural Network Architectures for Large Scale Acoustic Modeling" 338-342, 2014

10 S. Hochreiter, "Long Short-Term Memory" 9 (9): 1735-1780, 1997

11 K. Cho, "Learning Phrase Representations Using RNN Encoder-Decoder for Statistical Machine Translation"

12 Y. Bengio, "Learning Deep Architectures for AI, Found. Trends(R)" 2 (2): 1-127, 2009

13 S. Cai, "Language- Independent Parsing with Empty Elements" 212-216, 2011

14 N.-R. Han, "Korean Zero Pronouns: Analysis and Resolution" Univ. Pennsylvania 2006

15 S. Zhao, "Identification and Resolution of Chinese Zero Pronouns: A Machine Learning Approach" 541-550, 2007

16 J. Chung, "Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling" 2014

17 T. Mikolov, "Efficient Estimation of Word Representations in Vector Space"

18 T. Chung, "Effects of Empty Categories on Machine Translation" 636-645, 2010

19 C. Giannella, "Dropped Pronoun Recovery in Chinese SMS, Technical Paper" 2015

20 L. Wang, "Dropped Pronoun Generation for Dialogue Machine Translation" 6110-6114, 2016

21 C. Chen, "Chinese Zero Pronoun Resolution with Deep Neural Networks" 778-788, 2016

22 Y. Yang, "Chasing the Ghost: Recovering Empty Categories in the Chinese Treebank" 1382-1390, 2010

23 F. Kong, "A Tree Kernel-Based Unified Framework for Chinese Zero Anaphora Resolution" 882-891, 2010