Memory Attentive Fusion: External Language Model Integration for Transformer-based Sequence-to-Sequence Model
Mana Ihori, Ryo Masumura, Naoki Makishima, Tomohiro Tanaka, Akihiko Takashima, Shota Orihashi
Abstract
This paper presents a novel fusion method for integrating an external language model (LM) into the Transformer based sequence-to-sequence (seq2seq) model. While paired data are basically required to train the seq2seq model, the external LM can be trained with only unpaired data. Thus, it is important to leverage memorized knowledge in the external LM for building the seq2seq model, since it is hard to prepare a large amount of paired data. However, the existing fusion methods assume that the LM is integrated with recurrent neural network-based seq2seq models instead of the Transformer. Therefore, this paper proposes a fusion method that can explicitly utilize network structures in the Transformer. The proposed method, called memory attentive fusion, leverages the Transformer-style attention mechanism that repeats source-target attention in a multi-hop manner for reading the memorized knowledge in the LM. Our experiments on two text-style conversion tasks demonstrate that the proposed method performs better than conventional fusion methods.- Anthology ID:
- 2020.inlg-1.1
- Volume:
- Proceedings of the 13th International Conference on Natural Language Generation
- Month:
- December
- Year:
- 2020
- Address:
- Dublin, Ireland
- Editors:
- Brian Davis, Yvette Graham, John Kelleher, Yaji Sripada
- Venue:
- INLG
- SIG:
- SIGGEN
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1–6
- Language:
- URL:
- https://aclanthology.org/2020.inlg-1.1
- DOI:
- 10.18653/v1/2020.inlg-1.1
- Cite (ACL):
- Mana Ihori, Ryo Masumura, Naoki Makishima, Tomohiro Tanaka, Akihiko Takashima, and Shota Orihashi. 2020. Memory Attentive Fusion: External Language Model Integration for Transformer-based Sequence-to-Sequence Model. In Proceedings of the 13th International Conference on Natural Language Generation, pages 1–6, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- Memory Attentive Fusion: External Language Model Integration for Transformer-based Sequence-to-Sequence Model (Ihori et al., INLG 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-3/2020.inlg-1.1.pdf