EMNLP Findings2021
DIRECT: Direct and Indirect Responses in Conversational Text Corpus
Junya Takayama, Tomoyuki Kajiwara, Yuki Arase
Abstract
We create a large-scale dialogue corpus that provides pragmatic paraphrases to advance technology for understanding the underlying intentions of users. While neural conversation models acquire the ability to generate fluent responses through training on a dialogue corpus, previous corpora have mainly focused on the literal meanings of utterances. However, in reality, people do not always present their intentions directly. For example, if a person said to the operator of a reservation service 'I don't have enough budget.', they, in fact, mean 'please find a cheaper option for me.' Our corpus provides a total of 71, 498 indirect-direct utterance pairs accompanied by a multi-turn dialogue history extracted from the MultiWoZ dataset. In addition, we propose three tasks to benchmark the ability of models to recognize and generate indirect and direct utterances. We also investigated the performance of state-ofthe-art pre-trained models as baselines.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
3 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- A Simple Language Model for Task-Oriented Dialogue cites Paraphrase Augmented Task-Oriented Dialog Generation
- Entailed Between the Lines: Incorporating Implication into NLI cites Resolving Indirect Referring Expressions for Entity Selection
- MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems cites A Simple Language Model for Task-Oriented Dialogue
Cited by top-tier papers3
- VAGUE: Visual Contexts Clarify Ambiguous ExpressionsHeejeong Nam, Jinwoo Ahn, Keummin Ka, Jiwan Chung et al.ICCV 2025 · 1 citation
- Resolving Indirect Referring Expressions for Entity SelectionMohammad Javad Hosseini, Filip Radlinski, Silvia Pareti, Annie LouisACL 2023
- Entailed Between the Lines: Incorporating Implication into NLIShreya Havaldar, Hamidreza Alvari, John Palowitch, Mohammad Javad Hosseini et al.ACL 2025
Builds on6
- BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and ComprehensionMike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad et al.ACL 2020 · 1,224 citations
- A Simple Language Model for Task-Oriented DialogueEhsan Hosseini-Asl, Bryan McCann, Chien-Sheng Wu, Semih Yavuz et al.NeurIPS 2020 · 590 citations
- MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue SystemsZhaojiang Lin, Andrea Madotto, Genta Indra Winata, Pascale FungEMNLP 2020 · 138 citations
- Paraphrase Augmented Task-Oriented Dialog GenerationSilin Gao, Yichi Zhang, Zhijian Ou, Zhou YuACL 2020 · 78 citations
- Learning a Simple and Effective Model for Multi-turn Response Generation with Auxiliary TasksYufan Zhao, Can Xu, Wei WuEMNLP 2020 · 25 citations
Related papers
- "I'd rather just go to bed": Understanding Indirect AnswersAnnie Louis, Dan Roth, Filip RadlinskiEMNLP 2020
- GRICE: A Grammar-based Dataset for Recovering Implicature and Conversational rEasoningZilong Zheng, Shuwen Qiu, Lifeng Fan, Yixin Zhu et al.ACL Findings 2021 · 12 citations
- Multi-Domain Dialogue Acts and Response Co-GenerationKai Wang, Junfeng Tian, Rui Wang, Xiaojun Quan et al.ACL 2020 · 46 citations
- Let's Go Real Talk: Spoken Dialogue Model for Face-to-Face ConversationSe Jin Park, Chae Won Kim, Hyeongseop Rha, Minsu Kim et al.ACL 2024
- Disfluency Generation for More Robust Dialogue SystemsBenjamin MarieACL Findings 2023 · 2 citations
