What You See is What You Get: Visual Pronoun Coreference Resolution in Dialogues
Xintong Yu, Hongming Zhang, Yangqiu Song, Yan Song, Changshui Zhang
Abstract
Grounding a pronoun to a visual object it refers to requires complex reasoning from various information sources, especially in conversational scenarios. For example, when people in a conversation talk about something all speakers can see, they often directly use pronouns (e.g., it) to refer to it without previous introduction. This fact brings a huge challenge for modern natural language understanding systems, particularly conventional context-based pronoun coreference models. To tackle this challenge, in this paper, we formally define the task of visual-aware pronoun coreference resolution (PCR) and introduce VisPro, a large-scale dialogue PCR dataset, to investigate whether and how the visual information can help resolve pronouns in dialogues. We then propose a novel visual-aware PCR model, VisCoref, for this task and conduct comprehensive experiments and case studies on our dataset. Results demonstrate the importance of the visual information in this PCR case and show the effectiveness of the proposed model.- Anthology ID:
- D19-1516
- Volume:
- Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
- Month:
- November
- Year:
- 2019
- Address:
- Hong Kong, China
- Editors:
- Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
- Venues:
- EMNLP | IJCNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 5123–5132
- Language:
- URL:
- https://aclanthology.org/D19-1516
- DOI:
- 10.18653/v1/D19-1516
- Cite (ACL):
- Xintong Yu, Hongming Zhang, Yangqiu Song, Yan Song, and Changshui Zhang. 2019. What You See is What You Get: Visual Pronoun Coreference Resolution in Dialogues. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 5123–5132, Hong Kong, China. Association for Computational Linguistics.
- Cite (Informal):
- What You See is What You Get: Visual Pronoun Coreference Resolution in Dialogues (Yu et al., EMNLP-IJCNLP 2019)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/D19-1516.pdf
- Code
- HKUST-KnowComp/Visual_PCR
- Data
- VisPro, VisDial