Transformer-GCRF: Recovering Chinese Dropped Pronouns with General Conditional Random Fields
This addresses a domain-specific issue in Chinese NLP, with incremental improvements by modeling dependencies between pronouns across utterances.
The paper tackles the problem of recovering dropped pronouns in Chinese conversations, which is important for NLP applications like Machine Translation, by proposing a Transformer-GCRF model that outperforms state-of-the-art methods on three datasets.
Pronouns are often dropped in Chinese conversations and recovering the dropped pronouns is important for NLP applications such as Machine Translation. Existing approaches usually formulate this as a sequence labeling task of predicting whether there is a dropped pronoun before each token and its type. Each utterance is considered to be a sequence and labeled independently. Although these approaches have shown promise, labeling each utterance independently ignores the dependencies between pronouns in neighboring utterances. Modeling these dependencies is critical to improving the performance of dropped pronoun recovery. In this paper, we present a novel framework that combines the strength of Transformer network with General Conditional Random Fields (GCRF) to model the dependencies between pronouns in neighboring utterances. Results on three Chinese conversation datasets show that the Transformer-GCRF model outperforms the state-of-the-art dropped pronoun recovery models. Exploratory analysis also demonstrates that the GCRF did help to capture the dependencies between pronouns in neighboring utterances, thus contributes to the performance improvements.