Natural Language Deduction with Incomplete Information
Natural Language Deduction with Incomplete Information
复制标题
DOI：
10.48550/arxiv.2211.00614
复制
发表时间：
2022-11
期刊：
影响因子：
--
通讯作者：
Zayne Sprague;Kaj Bostrom;Swarat Chaudhuri;Greg Durrett
中科院分区：
文献类型：
--
作者：
Zayne Sprague;Kaj Bostrom;Swarat Chaudhuri;Greg Durrett
越来越多的工作研究如何通过生成自然语言“证明“来回答一个问题或验证一个主张：基于一组前提得出答案的演绎推理链。然而，这些方法只有在遵循所提供的证据时才能做出合理的推论。我们提出了一个新的系统，可以处理未充分指定的设置，不是所有的前提是在一开始就说明，也就是说，额外的假设需要具体化，以证明索赔。通过使用自然语言生成模型来溯因推断给定另一个前提和结论的前提，我们可以估算结论为真所需的缺失证据。我们的系统搜索两个条纹在一个双向的方式，交错演绎（正向链接）和溯因（反向链接）生成步骤。我们为每个步骤采样多个可能的输出，以实现搜索空间的覆盖，同时通过使用往返验证过程过滤低质量的生成来确保正确性。结果在一个修改版本的EntailmentBank数据集和一个新的数据集称为日常规范：为什么不？证明带验证的溯因生成可以跨域内和域外设置恢复前提。
A growing body of work studies how to answer a question or verify a claim by generating a natural language “proof:” a chain of deductive inferences yielding the answer based on a set of premises. However, these methods can only make sound deductions when they follow from evidence that is given. We propose a new system that can handle the underspecified setting where not all premises are stated at the outset; that is, additional assumptions need to be materialized to prove a claim. By using a natural language generation model to abductively infer a premise given another premise and a conclusion, we can impute missing pieces of evidence needed for the conclusion to be true. Our system searches over two fringes in a bidirectional fashion, interleaving deductive (forward-chaining) and abductive (backward-chaining) generation steps. We sample multiple possible outputs for each step to achieve coverage of the search space, at the same time ensuring correctness by filtering low-quality generations with a round-trip validation procedure. Results on a modified version of the EntailmentBank dataset and a new dataset called Everyday Norms: Why Not? Show that abductive generation with validation can recover premises across in- and out-of-domain settings.