Syntax-Guided Controlled Generation of Paraphrases

• Published in: Transactions of the Association for Computational Linguistics Vol. 8; pp. 330 - 345
• Main Authors: Kumar, Ashutosh, Ahuja, Kabir, Vadapalli, Raghuram, Talukdar, Partha
• Format: Journal Article
• Language: English
• Published: One Rogers Street, Cambridge, MA 02142-1209, USA MIT Press 01.01.2020; MIT Press Journals, The; The MIT Press
• Subjects: Constraints; Human performance; Paraphrase; Sentences; Source code; Syntactic complexity; Syntax
• ISSN: 2307-387X; 2307-387X
• DOI: 10.1162/tacl_a_00318

Given a sentence (e.g., “I like mangoes”) and a constraint (e.g., sentiment flip), the goal of controlled text generation is to produce a sentence that adapts the input sentence to meet the requirements of the constraint (e.g., “I hate mangoes”). Going beyond such simple constraints, recent work has started exploring the incorporation of complex syntactic-guidance as constraints in the task of controlled paraphrase generation. In these methods, syntactic-guidance is sourced from a separate exemplar sentence. However, these prior works have only utilized limited syntactic information available in the parse tree of the exemplar sentence. We address this limitation in the paper and propose Syntax Guided Controlled Paraphraser (SGCP), an end-to-end framework for syntactic paraphrase generation. We find that Sgcp can generate syntax-conforming sentences while not compromising on relevance. We perform extensive automated and human evaluations over multiple real-world English language datasets to demonstrate the efficacy of Sgcp over state-of-the-art baselines. To drive future research, we have made Sgcp’s source code available.