Video-aided Unsupervised Grammar Induction
Songyang Zhang, Linfeng Song, Lifeng Jin, Kun Xu, Dong Yu, Jiebo Luo
Abstract
We investigate video-aided grammar induction, which learns a constituency parser from both unlabeled text and its corresponding video. Existing methods of multi-modal grammar induction focus on grammar induction from text-image pairs, with promising results showing that the information from static images is useful in induction. However, videos provide even richer information, including not only static objects but also actions and state changes useful for inducing verb phrases. In this paper, we explore rich features (e.g. action, object, scene, audio, face, OCR and speech) from videos, taking the recent Compound PCFG model as the baseline. We further propose a Multi-Modal Compound PCFG model (MMC-PCFG) to effectively aggregate these rich features from different modalities. Our proposed MMC-PCFG is trained end-to-end and outperforms each individual modality and previous state-of-the-art systems on three benchmarks, i.e. DiDeMo, YouCook2 and MSRVTT, confirming the effectiveness of leveraging video information for unsupervised grammar induction.- Anthology ID:
- 2021.naacl-main.119
- Volume:
- Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
- Month:
- June
- Year:
- 2021
- Address:
- Online
- Editors:
- Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani-Tur, Iz Beltagy, Steven Bethard, Ryan Cotterell, Tanmoy Chakraborty, Yichao Zhou
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1513–1524
- Language:
- URL:
- https://aclanthology.org/2021.naacl-main.119
- DOI:
- 10.18653/v1/2021.naacl-main.119
- Award:
- Best Long Paper
- Cite (ACL):
- Songyang Zhang, Linfeng Song, Lifeng Jin, Kun Xu, Dong Yu, and Jiebo Luo. 2021. Video-aided Unsupervised Grammar Induction. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1513–1524, Online. Association for Computational Linguistics.
- Cite (Informal):
- Video-aided Unsupervised Grammar Induction (Zhang et al., NAACL 2021)
- PDF:
- https://preview.aclanthology.org/naacl-24-ws-corrections/2021.naacl-main.119.pdf
- Code
- Sy-Zhang/MMC-PCFG
- Data
- DiDeMo, Places, YouCook2