Publications
Authors:
Shubham Agarwal, Marc Dymetman
Citation:
SIGDIAL 2017 Special Session: Natural Language Generation for Dialogue Systems, Saarbruecken, Germany, 15 - 17 August 2017
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 of 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.
Year:
2017
Report number:
2017/227