# Transformers to Learn Hierarchical Contexts in Multiparty Dialogue for Span-based Question Answering

arXiv: https://arxiv.org/abs/2004.03561 · HTML: https://mlsanity.com/paper/2004.03561/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Apr 2020.

## Built on by (most cited first, 13 of 13)

- [Quality Controlled Paraphrase Generation](https://mlsanity.com/paper/2203.10940/) (2022)
- [Autonomous Agents for Collaborative Task under Information Asymmetry](https://mlsanity.com/paper/2406.14928/) (2024)
- [Automatically Select Emotion for Response via Personality-affected Emotion Transition](https://mlsanity.com/paper/2106.15846/) (2021)
- [Self- and Pseudo-self-supervised Prediction of Speaker and Key-utterance for Multi-party Dialogue Reading Comprehension](https://mlsanity.com/paper/2109.03772/) (2021)
- [Enhanced Speaker-aware Multi-party Multi-turn Dialogue Comprehension](https://mlsanity.com/paper/2109.04066/) (2021)
- [Advances in Multi-turn Dialogue Comprehension: A Survey](https://mlsanity.com/paper/2103.03125/) (2021)
- [Back to the Future: Bidirectional Information Decoupling Network for Multi-turn Dialogue Modeling](https://mlsanity.com/paper/2204.08152/) (2022)
- [Span-based Named Entity Recognition by Generating and Compressing Information](https://mlsanity.com/paper/2302.05392/) (2023)
- [Personality-affected Emotion Generation in Dialog Systems](https://mlsanity.com/paper/2404.07229/) (2024)
- [Revisiting Conversation Discourse for Dialogue Disentanglement](https://mlsanity.com/paper/2306.03975/) (2023)
- [Advances in Multi-turn Dialogue Comprehension: A Survey](https://mlsanity.com/paper/2110.04984/) (2021)
- [Question-Interlocutor Scope Realized Graph Modeling over Key Utterances for Dialogue Reading Comprehension](https://mlsanity.com/paper/2210.14456/) (2022)
- [Coreference-aware Double-channel Attention Network for Multi-party Dialogue Reading Comprehension](https://mlsanity.com/paper/2305.08348/) (2023)

## Abstract (arXiv)

We introduce a novel approach to transformers that learns hierarchical representations in multiparty dialogue. First, three language modeling tasks are used to pre-train the transformers, token- and utterance-level language modeling and utterance order prediction, that learn both token and utterance embeddings for better understanding in dialogue contexts. Then, multi-task learning between the utterance prediction and the token span prediction is applied to fine-tune for span-based question answering (QA). Our approach is evaluated on the FriendsQA dataset and shows improvements of 3.8% and 1.4% over the two state-of-the-art transformer models, BERT and RoBERTa, respectively.