Syntax-Guided Controlled Generation of Paraphrases
Authors:
Open Access
- 1 December 2020
- journal article
- research article
- Published by MIT Press in Transactions of the Association for Computational Linguistics
- Vol. 8, 330-345
Abstract
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. 1Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- Towards String-To-Tree Neural Machine Translation2017
- Syntactically Guided Neural Machine Translation2016
- Generating Sentences from a Continuous Space2016
- Neural Machine Translation of Rare Words with Subword Units2016
- A survey of research on text simplificationITL - International Journal of Applied Linguistics, 2014
- Generating Phrasal and Sentential Paraphrases: A Survey of Data-Driven MethodsComputational Linguistics, 2010
- The Roots of Coherence in DiscourseHuman Development, 2003
- Long Short-Term MemoryNeural Computation, 1997
- Simple Fast Algorithms for the Editing Distance between Trees and Related ProblemsSIAM Journal on Computing, 1989
- Semantic Distinctions and Memory for Complex SentencesQuarterly Journal of Experimental Psychology, 1968