Entailment Relation Aware Paraphrase Generation

2022-03-20 · Abhilasha Sancheti, Balaji Vasan Srinivasan, Rachel Rudinger

We introduce a new task of entailment relation aware paraphrase generation which aims at generating a paraphrase conforming to a given entailment relation (e.g. equivalent, forward entailing, or reverse entailing) with respect to a given input. We propose a reinforcement learning-based weakly-supervised paraphrasing system, ERAP, that can be trained using existing paraphrase and natural language inference (NLI) corpora without an explicit task-specific corpus. A combination of automated and human evaluations show that ERAP generates paraphrases conforming to the specified entailment relation and are of good quality as compared to the baselines and uncontrolled paraphrasing systems. Using ERAP for augmenting training data for downstream textual entailment task improves performance over an uncontrolled paraphrasing system, and introduces fewer training artifacts, indicating the benefit of explicit control during paraphrasing.

📄 PDF Abstract BibTeX arXiv:2203.10483

Code (0)

등록된 구현이 없습니다.

Tasks

Natural Language Inference Paraphrase Generation reinforcement-learning Reinforcement Learning (RL)Relation

Methods 이 논문이 사용한 방법론

AWARE We propose to theoretically and empirically examine the effect of incorporating weighting schemes into walk-aggregating GNNs. To this end, we propose a simple, interpretable, and…

Paraphrasing, textual entailment, and semantic similarity above word level

2022-08-10 · Venelin Kovatchev

This dissertation explores the linguistic and computational aspects of the meaning relations that can hold between two or more complex linguistic expressions (phrases, clauses, sentences, paragraphs). In particular, it f…

Natural Language Inference Paraphrase Identification Semantic Similarity Semantic Textual Similarity

Evaluating Factuality in Generation with Dependency-level Entailment

2020-10-12 · Findings of the Association for Computational Linguistics 2020 · Tanya Goyal, Greg Durrett

Despite significant progress in text generation models, a serious limitation is their tendency to produce text that is factually inconsistent with information in the input. Recent work has studied whether textual entailm…

ARC Natural Language Inference Question Generation Question-Generation+2

Neural Paraphrase Generation using Transfer Learning

2017-09-01 · WS 2017 9 · Florin Brad, Traian Rebedea

Progress in statistical paraphrase generation has been hindered for a long time by the lack of large monolingual parallel corpora. In this paper, we adapt the neural machine translation approach to paraphrase generation …

Machine Translation Natural Language Inference Paraphrase Generation Question Answering+3

PPDB 2.0: Better paraphrase ranking, fine-grained entailment relations, word embeddings, and style classification

2015-07-01 · IJCNLP 2015 7 · Ellie Pavlick, Pushpendre Rastogi, Juri Ganitkevitch, Benjamin Van Durme 외

General Classification Natural Language Inference Semantic Textual Similarity Text Generation+1

Construction of a Multilingual Corpus Annotated with Translation Relations

2018-08-01 · COLING 2018 8 · Yuming Zhai, Aur{\'e}lien Max, Anne Vilnat

Translation relations, which distinguish literal translation from other translation techniques, constitute an important subject of study for human translators (Chuquet and Paillard, 1989). However, automatic processing t…

Machine Translation Paraphrase Generation Translation