Abstract
We propose a new type of representation learning method that models words, phrases and sentences seamlessly. Our method does not depend on word segmentation and any human-annotated resources (e.g., word dictionaries), yet it is very effective for noisy corpora written in unsegmented languages such as Chinese and Japanese. The main idea of our method is to ignore word boundaries completely (i.e., segmentation-free), and construct representations for all character n-grams in a raw corpus with embeddings of compositional sub-n-grams. Although the idea is simple, our experiments on various benchmarks and real-world datasets show the efficacy of our proposal.- Anthology ID:
- N19-1324
- Volume:
- Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
- Month:
- June
- Year:
- 2019
- Address:
- Minneapolis, Minnesota
- Editors:
- Jill Burstein, Christy Doran, Thamar Solorio
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3207–3215
- Language:
- URL:
- https://aclanthology.org/N19-1324
- DOI:
- 10.18653/v1/N19-1324
- Cite (ACL):
- Geewook Kim, Kazuki Fukui, and Hidetoshi Shimodaira. 2019. Segmentation-free compositional n-gram embedding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 3207–3215, Minneapolis, Minnesota. Association for Computational Linguistics.
- Cite (Informal):
- Segmentation-free compositional n-gram embedding (Kim et al., NAACL 2019)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/N19-1324.pdf
- Code
- kdrl/SCNE + additional community code