Skip to Main content Skip to Navigation
Conference papers

Neural-Driven Multi-criteria Tree Search for Paraphrase Generation

Abstract : A good paraphrase is semantically similar to the original sentence but it must be also well formed, and syntactically different to ensure diversity. To deal with this tradeoff, we propose to cast the paraphrase generation task as a multi-objectives search problem on the lattice of text transformations. We use BERT and GPT2 to measure respectively the semantic distance and the correctness of the candidates. We study two search algorithms: Monte-Carlo Tree Search For Paraphrase Generation (MCPG) and Pareto Tree Search (PTS) that we use to explore the huge sets of candidates generated by applying the PPDB-2.0 edition rules. We evaluate this approach on 5 datasets and show that it performs reasonably well and that it outperforms a state-of-the-art edition-based text generation method.
Complete list of metadata

https://hal.inria.fr/hal-03127865
Contributor : Damien Lolive Connect in order to contact the contributor
Submitted on : Monday, February 1, 2021 - 5:29:30 PM
Last modification on : Wednesday, November 3, 2021 - 8:14:50 AM
Long-term archiving on: : Sunday, May 2, 2021 - 7:50:33 PM

File

neural_driven_multi_criteria_t...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03127865, version 1

Citation

Betty Fabre, Tanguy Urvoy, Jonathan Chevelu, Damien Lolive. Neural-Driven Multi-criteria Tree Search for Paraphrase Generation. Learning Meets Combinatorial Algorithms (LMCA) Workshop at NeurIPS 2020, Dec 2020, online, France. ⟨hal-03127865⟩

Share

Metrics

Les métriques sont temporairement indisponibles