Abstract
Recently slot filling has witnessed great development thanks to deep learning and the availability of large-scale annotated data. However, it poses a critical challenge to handle a novel domain whose samples are never seen during training. The recognition performance might be greatly degraded due to severe domain shifts. Most prior works deal with this problem in a two-pass pipeline manner based on metric learning. In practice, these dominant pipeline models may be limited in computational efficiency and generalization capacity because of non-parallel inference and context-free discrete label embeddings. To this end, we re-examine the typical metric-based methods, and propose a new adaptive end-to-end metric learning scheme for the challenging zero-shot slot filling. Considering simplicity, efficiency and generalizability, we present a cascade-style joint learning framework coupled with context-aware soft label representations and slot-level contrastive representation learning to mitigate the data and label shift problems effectively. Extensive experiments on public benchmarks demonstrate the superiority of the proposed approach over a series of competitive baselines.- Anthology ID:
- 2023.emnlp-main.387
- Volume:
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6291–6301
- Language:
- URL:
- https://aclanthology.org/2023.emnlp-main.387
- DOI:
- 10.18653/v1/2023.emnlp-main.387
- Cite (ACL):
- Yuanjun Shi, Linzhi Wu, and Minglai Shao. 2023. Adaptive End-to-End Metric Learning for Zero-Shot Cross-Domain Slot Filling. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 6291–6301, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Adaptive End-to-End Metric Learning for Zero-Shot Cross-Domain Slot Filling (Shi et al., EMNLP 2023)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/2023.emnlp-main.387.pdf