QA-Driven Zero-shot Slot Filling with Weak Supervision Pretraining

Xinya Du, Luheng He, Qi Li, Dian Yu, Panupong Pasupat, Yuan Zhang


Abstract
Slot-filling is an essential component for building task-oriented dialog systems. In this work, we focus on the zero-shot slot-filling problem, where the model needs to predict slots and their values, given utterances from new domains without training on the target domain. Prior methods directly encode slot descriptions to generalize to unseen slot types. However, raw slot descriptions are often ambiguous and do not encode enough semantic information, limiting the models’ zero-shot capability. To address this problem, we introduce QA-driven slot filling (QASF), which extracts slot-filler spans from utterances with a span-based QA model. We use a linguistically motivated questioning strategy to turn descriptions into questions, allowing the model to generalize to unseen slot types. Moreover, our QASF model can benefit from weak supervision signals from QA pairs synthetically generated from unlabeled conversations. Our full system substantially outperforms baselines by over 5% on the SNIPS benchmark.
Anthology ID:
2021.acl-short.83
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
654–664
Language:
URL:
https://aclanthology.org/2021.acl-short.83
DOI:
10.18653/v1/2021.acl-short.83
Bibkey:
Cite (ACL):
Xinya Du, Luheng He, Qi Li, Dian Yu, Panupong Pasupat, and Yuan Zhang. 2021. QA-Driven Zero-shot Slot Filling with Weak Supervision Pretraining. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 654–664, Online. Association for Computational Linguistics.
Cite (Informal):
QA-Driven Zero-shot Slot Filling with Weak Supervision Pretraining (Du et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2021.acl-short.83.pdf
Video:
 https://preview.aclanthology.org/nschneid-patch-4/2021.acl-short.83.mp4
Data
SNIPS