通过对比学习建模会话依赖的短语检索用于开放域会话问答
Phrase Retrieval for Open-Domain Conversational Question Answering with Conversational Dependency Modeling via Contrastive Learning
AI总结：
本文提出基于短语检索的 ODConvQA 单阶段答案预测方法，并通过对比学习建模多轮会话依赖，在两个数据集上显著优于检索器-阅读器基线。
摘要：
开放域会话问答（ODConvQA）旨在基于“检索器-阅读器”流水线，通过多轮会话回答问题：该流水线先检索段落，再利用这些段落预测答案。然而，这种流水线方法不仅使阅读器容易受到从检索器传播而来的错误影响，还需要额外投入来同时开发检索器和阅读器；由于二者无法并行运行，还会进一步降低速度。在本研究中，我们提出一种利用面向词序列的短语检索机制直接预测答案的方法，将传统上两个不同的子任务简化为单一子任务。此外，我们首次研究了其在 ODConvQA 任务上的能力。然而，由于会话中前一轮与当前轮之间存在依赖关系，简单采用该方法会产生很大问题。为解决这一问题，我们进一步引入一种新颖的对比学习策略，通过最大化同一会话中连续轮次的表示相似性，同时最小化无关会话上下文的表示相似性，确保在为当前上下文检索短语时反映前几轮信息。我们在两个 ODConvQA 数据集上验证了所提模型，实验结果表明，该模型显著优于采用检索器-阅读器的相关基线。代码可在 https://github.com/starsuzi/PRO-ConvQA 获取。
英文摘要：
Open-Domain Conversational Question Answering (ODConvQA) aims at answering questions through a multi-turn conversation based on a retriever-reader pipeline, which retrieves passages and then predicts answers with them. However, such a pipeline approach not only makes the reader vulnerable to the errors propagated from the retriever, but also demands additional effort to develop both the retriever and the reader, which further makes it slower since they are not runnable in parallel. In this work, we propose a method to directly predict answers with a phrase retrieval scheme for a sequence of words, reducing the conventional two distinct subtasks into a single one. Also, for the first time, we study its capability for ODConvQA tasks. However, simply adopting it is largely problematic, due to the dependencies between previous and current turns in a conversation. To address this problem, we further introduce a novel contrastive learning strategy, making sure to reflect previous turns when retrieving the phrase for the current context, by maximizing representational similarities of consecutive turns in a conversation while minimizing irrelevant conversational contexts. We validate our model on two ODConvQA datasets, whose experimental results show that it substantially outperforms the relevant baselines with the retriever-reader. Code is available at: https://github.com/starsuzi/PRO-ConvQA.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
