תקציר
Opinionated natural language generation (ONLG) is a new, challenging, NLG task in which we aim to automatically generate human-like, subjective, responses to opinionated articles online. We present a data-driven architecture for ONLG that generates subjective responses triggered by users' agendas, based on automatically acquired wide-coverage generative grammars. We compare three types of grammatical representations that we design for ONLG. The grammars interleave different layers of linguistic information, and are induced from a new, enriched dataset we developed. Our evaluation shows that generation with Relational-Realizational (Tsarfaty and Sima'an, 2008) inspired grammar gets better language model scores than lexicalized grammars à la Collins (2003), and that the latter gets better human-evaluation scores. We also show that conditioning the generation on topic models makes generated responses more relevant to the document content.
שפה מקורית | אנגלית |
---|---|
כותר פרסום המארח | ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers) |
מוציא לאור | Association for Computational Linguistics (ACL) |
עמודים | 1331-1341 |
מספר עמודים | 11 |
מסת"ב (אלקטרוני) | 9781945626753 |
מזהי עצם דיגיטלי (DOIs) | |
סטטוס פרסום | פורסם - 2017 |
אירוע | 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017 - Vancouver, קנדה משך הזמן: 30 יולי 2017 → 4 אוג׳ 2017 |
סדרות פרסומים
שם | ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers) |
---|---|
כרך | 1 |
כנס
כנס | 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017 |
---|---|
מדינה/אזור | קנדה |
עיר | Vancouver |
תקופה | 30/07/17 → 4/08/17 |
הערה ביבליוגרפית
Publisher Copyright:© 2017 Association for Computational Linguistics.