Abstract
This paper explores an incremental training strategy for the skip-gram model with negative sampling (SGNS) from both empirical and theoretical perspectives. Existing methods of neural word embeddings, including SGNS, are multi-pass algorithms and thus cannot perform incremental model update. To address this problem, we present a simple incremental extension of SGNS and provide a thorough theoretical analysis to demonstrate its validity. Empirical experiments demonstrated the correctness of the theoretical analysis as well as the practical usefulness of the incremental algorithm.- Anthology ID:
- D17-1037
- 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:
- 363–371
- Language:
- URL:
- https://aclanthology.org/D17-1037
- DOI:
- 10.18653/v1/D17-1037
- Cite (ACL):
- Nobuhiro Kaji and Hayato Kobayashi. 2017. Incremental Skip-gram Model with Negative Sampling. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 363–371, Copenhagen, Denmark. Association for Computational Linguistics.
- Cite (Informal):
- Incremental Skip-gram Model with Negative Sampling (Kaji & Kobayashi, EMNLP 2017)
- PDF:
- https://preview.aclanthology.org/ml4al-ingestion/D17-1037.pdf