# Transformer-GCRF: Recovering Chinese Dropped Pronouns with General Conditional Random Fields Source: [Transformer-GCRF: Recovering Chinese Dropped Pronouns with General Conditional Random Fields]() Collection index: [llms.txt]() Data updated: 2025-10-25T22:38:00.142Z Authors: Jingxuan Yang, Kerui Xu, Jun Xu, Si Li, Sheng Gao, Jun Guo, Ji-Rong Wen, Nianwen Xue Published: 2020-10-07T07:06:09.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Dropped Pronoun Recovery on OntoNotes TC 5.0 (CoNLL 2012 Shared Task) (test)](): Dropped Pronoun Recovery; OntoNotes TC 5.0 (CoNLL 2012 Shared Task) (test); Precision: 0.4048. - [Dropped Pronoun Recovery on BaiduZhidao (test)](): Dropped Pronoun Recovery; BaiduZhidao (test); Precision: 43.3. - [Dropped Pronoun Recovery on SPDPR (test)](): Dropped Pronoun Recovery; SPDPR (test); Precision: 52.51. ## Original sources and implementation [Original paper]() [PDF]()