Abstract
Negative sampling is an important component in word2vec for distributed word representation learning. We hypothesize that taking into account global, corpus-level information and generating a different noise distribution for each target word better satisfies the requirements of negative examples for each training word than the original frequency-based distribution. In this purpose we pre-compute word co-occurrence statistics from the corpus and apply to it network algorithms such as random walk. We test this hypothesis through a set of experiments whose results show that our approach boosts the word analogy task by about 5% and improves the performance on word similarity tasks by about 1% compared to the skip-gram negative sampling baseline.- Anthology ID:
- P18-2090
- Volume:
- Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
- Month:
- July
- Year:
- 2018
- Address:
- Melbourne, Australia
- Editors:
- Iryna Gurevych, Yusuke Miyao
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 566–571
- Language:
- URL:
- https://aclanthology.org/P18-2090
- DOI:
- 10.18653/v1/P18-2090
- Cite (ACL):
- Zheng Zhang and Pierre Zweigenbaum. 2018. GNEG: Graph-Based Negative Sampling for word2vec. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 566–571, Melbourne, Australia. Association for Computational Linguistics.
- Cite (Informal):
- GNEG: Graph-Based Negative Sampling for word2vec (Zhang & Zweigenbaum, ACL 2018)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/P18-2090.pdf