# A Joint Model for Dropped Pronoun Recovery and Conversational Discourse Parsing in Chinese Conversational Speech

arXiv: https://arxiv.org/abs/2106.03345 · HTML: https://mlsanity.com/paper/2106.03345/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 38 references that are in the map.
- First posted on arXiv 7 Jun 2021.

## Builds on (most cited first, 19 of 19)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Stanza: A Python Natural Language Processing Toolkit for Many Human Languages](https://mlsanity.com/paper/2003.07082/) (2020)
- [Composition-based Multi-Relational Graph Convolutional Networks](https://mlsanity.com/paper/1911.03082/) (2019)
- [Deep Biaffine Attention for Neural Dependency Parsing](https://mlsanity.com/paper/1611.01734/) (2016)
- [DialogueGCN: A Graph Convolutional Neural Network for Emotion Recognition in Conversation](https://mlsanity.com/paper/1908.11540/) (2019)
- [Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling](https://mlsanity.com/paper/1703.04826/) (2017)
- [Improving Multi-turn Dialogue Modelling with Utterance ReWriter](https://mlsanity.com/paper/1906.07004/) (2019)
- [Analogical Reasoning on Chinese Morphological and Semantic Relations](https://mlsanity.com/paper/1805.06504/) (2018)
- [A Deep Sequential Model for Discourse Parsing on Multi-Party Dialogues](https://mlsanity.com/paper/1812.00176/) (2018)
- [Translating Pro-Drop Languages with Reconstruction Models](https://mlsanity.com/paper/1801.03257/) (2018)
- [A Novel Approach to Dropped Pronoun Translation](https://mlsanity.com/paper/1604.06285/) (2016)
- [Dating Documents using Graph Convolution Networks](https://mlsanity.com/paper/1902.00175/) (2019)
- [A Graph-based Model for Joint Chinese Word Segmentation and Dependency Parsing](https://mlsanity.com/paper/1904.04697/) (2019)
- [Deep Reinforcement Learning for Chinese Zero pronoun Resolution](https://mlsanity.com/paper/1806.03711/) (2018)
- [Neural Recovery Machine for Chinese Dropped Pronoun](https://mlsanity.com/paper/1605.02134/) (2016)
- [Recovering Dropped Pronouns in Chinese Conversations via Modeling Their Referents](https://mlsanity.com/paper/1906.02128/) (2019)
- [Transformer-GCRF: Recovering Chinese Dropped Pronouns with General Conditional Random Fields](https://mlsanity.com/paper/2010.03224/) (2020)

## Built on by (most cited first, 2 of 2)

- [Uncovering the Potential of ChatGPT for Discourse Analysis in Dialogue: An Empirical Study](https://mlsanity.com/paper/2305.08391/) (2023)
- [Leveraging Discourse Structure for Extractive Meeting Summarization](https://mlsanity.com/paper/2405.11055/) (2024)

## Abstract (arXiv)

In this paper, we present a neural model for joint dropped pronoun recovery (DPR) and conversational discourse parsing (CDP) in Chinese conversational speech. We show that DPR and CDP are closely related, and a joint model benefits both tasks. We refer to our model as DiscProReco, and it first encodes the tokens in each utterance in a conversation with a directed Graph Convolutional Network (GCN). The token states for an utterance are then aggregated to produce a single state for each utterance. The utterance states are then fed into a biaffine classifier to construct a conversational discourse graph. A second (multi-relational) GCN is then applied to the utterance states to produce a discourse relation-augmented representation for the utterances, which are then fused together with token states in each utterance as input to a dropped pronoun recovery layer. The joint model is trained and evaluated on a new Structure Parsing-enhanced Dropped Pronoun Recovery (SPDPR) dataset that we annotated with both two types of information. Experimental results on the SPDPR dataset and other benchmarks show that DiscProReco significantly outperforms the state-of-the-art baselines of both tasks.