Abstract
Recurrent neural network language models (RNNLMs) are the current standard-bearer for statistical language modeling. However, RNNLMs only estimate probabilities for complete sequences of text, whereas some applications require context-independent phrase probabilities instead. In this paper, we study how to compute an RNNLM’s em marginal probability: the probability that the model assigns to a short sequence of text when the preceding context is not known. We introduce a simple method of altering the RNNLM training to make the model more accurate at marginal estimation. Our experiments demonstrate that the technique is effective compared to baselines including the traditional RNNLM probability and an importance sampling approach. Finally, we show how we can use the marginal estimation to improve an RNNLM by training the marginals to match n-gram probabilities from a larger corpus.- Anthology ID:
- D18-1322
- Volume:
- Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
- Month:
- October-November
- Year:
- 2018
- Address:
- Brussels, Belgium
- Editors:
- Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2930–2935
- Language:
- URL:
- https://aclanthology.org/D18-1322
- DOI:
- 10.18653/v1/D18-1322
- Cite (ACL):
- Thanapon Noraset, Doug Downey, and Lidong Bing. 2018. Estimating Marginal Probabilities of n-grams for Recurrent Neural Language Models. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2930–2935, Brussels, Belgium. Association for Computational Linguistics.
- Cite (Informal):
- Estimating Marginal Probabilities of n-grams for Recurrent Neural Language Models (Noraset et al., EMNLP 2018)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-3/D18-1322.pdf
- Data
- WikiText-103, WikiText-2