Abstract
Prior methods to text segmentation are mostly at token level. Despite the adequacy, this nature limits their full potential to capture the long-term dependencies among segments. In this work, we propose a novel framework that incrementally segments natural language sentences at segment level. For every step in segmentation, it recognizes the leftmost segment of the remaining sequence. Implementations involve LSTM-minus technique to construct the phrase representations and recurrent neural networks (RNN) to model the iterations of determining the leftmost segments. We have conducted extensive experiments on syntactic chunking and Chinese part-of-speech (POS) tagging across 3 datasets, demonstrating that our methods have significantly outperformed previous all baselines and achieved new state-of-the-art results. Moreover, qualitative analysis and the study on segmenting long-length sentences verify its effectiveness in modeling long-term dependencies.- Anthology ID:
- 2021.naacl-main.116
- 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:
- 1476–1486
- Language:
- URL:
- https://aclanthology.org/2021.naacl-main.116
- DOI:
- 10.18653/v1/2021.naacl-main.116
- Cite (ACL):
- Yangming Li, Lemao Liu, and Kaisheng Yao. 2021. Neural Sequence Segmentation as Determining the Leftmost Segments. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1476–1486, Online. Association for Computational Linguistics.
- Cite (Informal):
- Neural Sequence Segmentation as Determining the Leftmost Segments (Li et al., NAACL 2021)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2021.naacl-main.116.pdf
- Code
- LeePleased/LeftmostSeg
- Data
- Universal Dependencies