arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2311.08511cs.CL
收藏

CoRE-CoG:使用约束生成进行实体会话推荐

CoRE-CoG: Conversational Recommendation of Entities using Constrained Generation

IIT Delhi(印度理工学院德里分校);IIT Bombay(印度理工学院孟买分校)

Harshvardhan Srivastava, Kanav Pruthi, Soumen Chakrabarti, Mausam

AI总结:

CoRE-CoG通过推荐触发器、类型剪枝和约束生成模块,提升端到端会话推荐系统的推荐准确性与响应流畅性,在基准测试中F1和Recall@1分别提升近10和4个百分点。

摘要:

端到端会话推荐系统(CRS)通过利用对话历史记录和知识库(KB)来生成响应。CRS主要面临三个关键挑战:(1)在每一轮对话中,它必须决定推荐知识库实体是否合适;如果合适,则必须识别最相关的知识库实体进行推荐;最后,它必须以与对话历史一致的流畅语句推荐该实体。最近的CRS对这些期望目标关注不足,常常生成不流畅的响应或未在正确的轮次推荐(相关)实体。我们引入了一个新的CRS,称为CoRE-CoG。CoRE-CoG通过实现(1)一个推荐触发器,决定系统话语是否应包含实体,(2)一个类型剪枝模块,提高推荐实体的相关性,以及(3)一个新颖的约束响应生成器,在保持流畅性的同时进行推荐,来解决先前系统的局限性。这些模块共同确保同时做出准确的推荐决策和生成流畅的系统话语。使用最近基准的实验表明,特别是在条件生成子任务上,其性能优于基线,F1分数和Recall@1分别提高了近10个百分点和4个百分点。

英文摘要:

End-to-end conversational recommendation systems (CRS) generate responses by leveraging both dialog history and a knowledge base (KB). A CRS mainly faces three key challenges: (1) at each turn, it must decide if recommending a KB entity is appropriate; if so, it must identify the most relevant KB entity to recommend; and finally, it must recommend the entity in a fluent utterance that is consistent with the conversation history. Recent CRSs do not pay sufficient attention to these desiderata, often generating unfluent responses or not recommending (relevant) entities at the right turn. We introduce a new CRS we call CoRE-CoG. CoRE-CoG addresses the limitations in prior systems by implementing (1) a recommendation trigger that decides if the system utterance should include an entity, (2) a type pruning module that improves the relevance of recommended entities, and (3) a novel constrained response generator to make recommendations while maintaining fluency. Together, these modules ensure simultaneous accurate recommendation decisions and fluent system utterances. Experiments with recent benchmarks show the superiority particularly on conditional generation sub-tasks with close to 10 F1 and 4 Recall@1 percent points gain over baselines.

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。

↑