Abstract
This paper introduces a novel training/decoding strategy for sequence labeling. Instead of greedily choosing a label at each time step, and using it for the next prediction, we retain the probability distribution over the current label, and pass this distribution to the next prediction. This approach allows us to avoid the effect of label bias and error propagation in sequence learning/decoding. Our experiments on dialogue act classification demonstrate the effectiveness of this approach. Even though our underlying neural network model is relatively simple, it outperforms more complex neural models, achieving state-of-the-art results on the MapTask and Switchboard corpora.- Anthology ID:
- D17-1229
- Volume:
- Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
- Month:
- September
- Year:
- 2017
- Address:
- Copenhagen, Denmark
- Editors:
- Martha Palmer, Rebecca Hwa, Sebastian Riedel
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2151–2156
- Language:
- URL:
- https://aclanthology.org/D17-1229
- DOI:
- 10.18653/v1/D17-1229
- Cite (ACL):
- Quan Hung Tran, Ingrid Zukerman, and Gholamreza Haffari. 2017. Preserving Distributional Information in Dialogue Act Classification. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2151–2156, Copenhagen, Denmark. Association for Computational Linguistics.
- Cite (Informal):
- Preserving Distributional Information in Dialogue Act Classification (Tran et al., EMNLP 2017)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/D17-1229.pdf