Abstract
Auto-regressive text generation models usually focus on local fluency, and may cause inconsistent semantic meaning in long text generation. Further, automatically generating words with similar semantics is challenging, and hand-crafted linguistic rules are difficult to apply. We consider a text planning scheme and present a model-based imitation-learning approach to alleviate the aforementioned issues. Specifically, we propose a novel guider network to focus on the generative process over a longer horizon, which can assist next-word prediction and provide intermediate rewards for generator optimization. Extensive experiments demonstrate that the proposed method leads to improved performance.
Original language | English |
---|---|
Title of host publication | 58TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2020) |
Publisher | ASSOC COMPUTATIONAL LINGUISTICS-ACL |
Pages | 2516-2531 |
Number of pages | 16 |
State | Published - 2020 |
Externally published | Yes |
Event | 58th Annual Meeting of the Association-for-Computational-Linguistics (ACL) - Duration: Jul 5 2020 → Jul 10 2020 |
Conference
Conference | 58th Annual Meeting of the Association-for-Computational-Linguistics (ACL) |
---|---|
Period | 07/5/20 → 07/10/20 |