In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, Berlin, Germany. Ondřej Dušek and Filip Jurčíček (2016): Sequence-to-Sequence Generation for Spoken Dialogue via Deep Syntax Trees and Strings.If you use or refer to the seq2seq generation in TGen, please cite this paper: To get the version used in our ACL 2016 and SIGDIAL 2016 papers (seq2seq approach for generating sentence plans or strings, optionally using previous context), see this release.To get the version used in our ACL 2015 paper (A*-search only), see this release.If you do not require a specific version of TGen, we recommended to install the current master version, which has the latest bugfixes and all the functionality of the ACL2016/SIGDIAL2016 version.If you find a bug, feel free to contact me or open an issue. TGen is highly experimental and only tested on a few datasets, so bugs are inevitable.Please refer to USAGE.md for instructions on how to use TGen. For the old A*-search-based generation, see our ACL 2015 paper.For an improved version of the seq2seq generation that takes previous user utterance into account to generate a more contextually-appropriate response, see our SIGDIAL 2016 paper.For seq2seq generation, see our ACL 2016 paper.The seq2seq algorithm also supports direct string generation.įor more details on the algorithms, please refer to our papers: The newer seq2seq approach is preferrable: it yields higher performance in terms of both speed and quality.īoth algorithms support generating sentence plans (deep syntax trees), which are subsequently converted to text using the existing the surface realizer from Treex NLP toolkit. A sequence-to-sequence (seq2seq) recurrent neural network architecture based on the TensorFlow toolkitīoth algoritms can be trained from pairs of source meaning representations (dialogue acts) and target sentences.A statistical sentence planner based on A*-style search, with a candidate plan generator and a perceptron ranker.TGen is a statistical natural language generator, with two different algorithms supported: A statistical natural language generator for spoken dialogue systems
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |