论文标题
构成关系意识到释义的产生
Entailment Relation Aware Paraphrase Generation
论文作者
论文摘要
我们介绍了一项新的构成关系的任务意识到的释义生成，该任务旨在生成符合给定输入的给定的关系关系（例如等效，前向需要或反向需要）的解释。我们提出了一个基于强化学习的弱监督措施系统ERAP，可以使用现有的释义和自然语言推断（NLI）语料库进行培训，而无需明确的特定任务特定的语料库。自动化和人类评估的结合表明，与基准和不受控制的释义系统相比，ERAP产生符合指定的元素关系的释义，并且具有良好的质量。使用ERAP来增强培训数据以进行下游文本需要任务，可以改善不受控制的释义系统的性能，并引入更少的培训文物，这表明在释义过程中明确控制的好处。
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.
