Constrained Decoding for Neural NLG from Compositional Representations in Task-Oriented Dialogue. Balakrishnan, A., Rao, J., Upasani, K., White, M., & Subba, R. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 831–844, Florence, Italy, July, 2019. Association for Computational Linguistics. ![Constrained Decoding for Neural NLG from Compositional Representations in Task-Oriented Dialogue [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper abstract bibtex 1 download Generating fluent natural language responses from structured semantic representations is a critical step in task-oriented conversational systems. Avenues like the E2E NLG Challenge have encouraged the development of neural approaches, particularly sequence-to-sequence (Seq2Seq) models for this problem. The semantic representations used, however, are often underspecified, which places a higher burden on the generation model for sentence planning, and also limits the extent to which generated responses can be controlled in a live system. In this paper, we (1) propose using tree-structured semantic representations, like those used in traditional rule-based NLG systems, for better discourse-level structuring and sentence-level planning; (2) introduce a challenging dataset using this representation for the weather domain; (3) introduce a constrained decoding approach for Seq2Seq models that leverages this representation to improve semantic correctness; and (4) demonstrate promising results on our dataset and the E2E dataset.
@inproceedings{balakrishnan-etal-2019-constrained,
title = "Constrained Decoding for Neural {NLG} from Compositional Representations in Task-Oriented Dialogue",
author = "Balakrishnan, Anusha and
Rao, Jinfeng and
Upasani, Kartikeya and
White, Michael and
Subba, Rajen",
booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/P19-1080",
pages = "831--844",
abstract = "Generating fluent natural language responses from structured semantic representations is a critical step in task-oriented conversational systems. Avenues like the E2E NLG Challenge have encouraged the development of neural approaches, particularly sequence-to-sequence (Seq2Seq) models for this problem. The semantic representations used, however, are often underspecified, which places a higher burden on the generation model for sentence planning, and also limits the extent to which generated responses can be controlled in a live system. In this paper, we (1) propose using tree-structured semantic representations, like those used in traditional rule-based NLG systems, for better discourse-level structuring and sentence-level planning; (2) introduce a challenging dataset using this representation for the weather domain; (3) introduce a constrained decoding approach for Seq2Seq models that leverages this representation to improve semantic correctness; and (4) demonstrate promising results on our dataset and the E2E dataset.",
}
Downloads: 1
{"_id":"fdmejGDGKwFfYb4mq","bibbaseid":"balakrishnan-rao-upasani-white-subba-constraineddecodingforneuralnlgfromcompositionalrepresentationsintaskorienteddialogue-2019","authorIDs":[],"author_short":["Balakrishnan, A.","Rao, J.","Upasani, K.","White, M.","Subba, R."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Constrained Decoding for Neural NLG from Compositional Representations in Task-Oriented Dialogue","author":[{"propositions":[],"lastnames":["Balakrishnan"],"firstnames":["Anusha"],"suffixes":[]},{"propositions":[],"lastnames":["Rao"],"firstnames":["Jinfeng"],"suffixes":[]},{"propositions":[],"lastnames":["Upasani"],"firstnames":["Kartikeya"],"suffixes":[]},{"propositions":[],"lastnames":["White"],"firstnames":["Michael"],"suffixes":[]},{"propositions":[],"lastnames":["Subba"],"firstnames":["Rajen"],"suffixes":[]}],"booktitle":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","month":"July","year":"2019","address":"Florence, Italy","publisher":"Association for Computational Linguistics","url":"https://www.aclweb.org/anthology/P19-1080","pages":"831–844","abstract":"Generating fluent natural language responses from structured semantic representations is a critical step in task-oriented conversational systems. Avenues like the E2E NLG Challenge have encouraged the development of neural approaches, particularly sequence-to-sequence (Seq2Seq) models for this problem. The semantic representations used, however, are often underspecified, which places a higher burden on the generation model for sentence planning, and also limits the extent to which generated responses can be controlled in a live system. In this paper, we (1) propose using tree-structured semantic representations, like those used in traditional rule-based NLG systems, for better discourse-level structuring and sentence-level planning; (2) introduce a challenging dataset using this representation for the weather domain; (3) introduce a constrained decoding approach for Seq2Seq models that leverages this representation to improve semantic correctness; and (4) demonstrate promising results on our dataset and the E2E dataset.","bibtex":"@inproceedings{balakrishnan-etal-2019-constrained,\n title = \"Constrained Decoding for Neural {NLG} from Compositional Representations in Task-Oriented Dialogue\",\n author = \"Balakrishnan, Anusha and\n Rao, Jinfeng and\n Upasani, Kartikeya and\n White, Michael and\n Subba, Rajen\",\n booktitle = \"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics\",\n month = jul,\n year = \"2019\",\n address = \"Florence, Italy\",\n publisher = \"Association for Computational Linguistics\",\n url = \"https://www.aclweb.org/anthology/P19-1080\",\n pages = \"831--844\",\n abstract = \"Generating fluent natural language responses from structured semantic representations is a critical step in task-oriented conversational systems. Avenues like the E2E NLG Challenge have encouraged the development of neural approaches, particularly sequence-to-sequence (Seq2Seq) models for this problem. The semantic representations used, however, are often underspecified, which places a higher burden on the generation model for sentence planning, and also limits the extent to which generated responses can be controlled in a live system. In this paper, we (1) propose using tree-structured semantic representations, like those used in traditional rule-based NLG systems, for better discourse-level structuring and sentence-level planning; (2) introduce a challenging dataset using this representation for the weather domain; (3) introduce a constrained decoding approach for Seq2Seq models that leverages this representation to improve semantic correctness; and (4) demonstrate promising results on our dataset and the E2E dataset.\",\n}\n\n","author_short":["Balakrishnan, A.","Rao, J.","Upasani, K.","White, M.","Subba, R."],"key":"balakrishnan-etal-2019-constrained","id":"balakrishnan-etal-2019-constrained","bibbaseid":"balakrishnan-rao-upasani-white-subba-constraineddecodingforneuralnlgfromcompositionalrepresentationsintaskorienteddialogue-2019","role":"author","urls":{"Paper":"https://www.aclweb.org/anthology/P19-1080"},"metadata":{"authorlinks":{}},"downloads":1},"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/OSU-CLLT/pubs/main/cllt.bib","creationDate":"2019-08-27T13:29:28.740Z","downloads":1,"keywords":[],"search_terms":["constrained","decoding","neural","nlg","compositional","representations","task","oriented","dialogue","balakrishnan","rao","upasani","white","subba"],"title":"Constrained Decoding for Neural NLG from Compositional Representations in Task-Oriented Dialogue","year":2019,"dataSources":["3fzDnLmhTDHQArsQA","j9kmFyT7sM9z3JACo","9PwrYxnvYQhcYnPdY"]}