A surprisingly effective out-of-the-box char2char model on the E2E NLG Challenge dataset

Shubham Agarwal, Marc Dymetman


Abstract
We train a char2char model on the E2E NLG Challenge data, by exploiting “out-of-the-box” the recently released tfseq2seq framework, using some of the standard options offered by this tool. With minimal effort, and in particular without delexicalization, tokenization or lowercasing, the obtained raw predictions, according to a small scale human evaluation, are excellent on the linguistic side and quite reasonable on the adequacy side, the primary downside being the possible omissions of semantic material. However, in a significant number of cases (more than 70%), a perfect solution can be found in the top-20 predictions, indicating promising directions for solving the remaining issues.
Anthology ID:
W17-5519
Volume:
Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue
Month:
August
Year:
2017
Address:
Saarbrücken, Germany
Editors:
Kristiina Jokinen, Manfred Stede, David DeVault, Annie Louis
Venue:
SIGDIAL
SIG:
SIGDIAL
Publisher:
Association for Computational Linguistics
Note:
Pages:
158–163
Language:
URL:
https://aclanthology.org/W17-5519
DOI:
10.18653/v1/W17-5519
Bibkey:
Cite (ACL):
Shubham Agarwal and Marc Dymetman. 2017. A surprisingly effective out-of-the-box char2char model on the E2E NLG Challenge dataset. In Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue, pages 158–163, Saarbrücken, Germany. Association for Computational Linguistics.
Cite (Informal):
A surprisingly effective out-of-the-box char2char model on the E2E NLG Challenge dataset (Agarwal & Dymetman, SIGDIAL 2017)
Copy Citation:
PDF:
https://aclanthology.org/W17-5519.pdf