paper-with-me

Papers

Open Domain Response Generation Guided by Retrieved Conversations

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Open domain response generation is the task of creating a response givena user query in any topics/domain. Limited by context and referenceinformation, responses generated by current systems are often "bland"or generic. In this paper, we combine a response generation model witha retrieval system that searches for relevant utterances and responses,and extracts keywords from the retrieved results to guide the responsegeneration. Our model uses a keyword extraction module to extract twotypes of keywords in an unsupervised fashion: (1) keywords in thequery not found in the retrieved utterances (DIFFKEY),and (2) overlapping keywords among the retrieved responses(SIMKEY). Given these keywords, we use a two-stage transformer thatfirst decides where to insert the keywords in the response, and thengenerates the full response given the location of the keywords. Thekeyword extraction module and the two-stage transformer are connected ina single network, and so our system is trained end-to-end.Experimental results on Cornell Movie-Dialog corpus, Douban and Weibodemonstrate that our model outperforms state-of-the-art systems in termsof ROUGE, relevance scores and human evaluation. Source code of ourmodel is available at: ANONYMISED.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Keyword ExtractionResponse GenerationRetrieval

Similar Papers 제목 키워드 기반

Understanding and Improving the Exemplar-based Generation for Open-domain Conversation

2021-12-13 · NLP4ConvAI (ACL) 2022 5 · Seungju Han, Beomsu Kim, Seokjun Seo, Enkhbayar Erdenee 외

Exemplar-based generative models for open-domain conversation produce responses based on the exemplars provided by the retriever, taking advantage of generative models and retrieval models. However, they often ignore the…

InformativenessRetrieval

PrLM: Learning Explicit Reasoning for Personalized RAG via Contrastive Reward Optimization

2025-08-10 · Kepu Zhang, Teng Shi, Weijie Yu, Jun Xu arxiv

Personalized retrieval-augmented generation (RAG) aims to produce user-tailored responses by incorporating retrieved user profiles alongside the input query. Existing methods primarily focus on improving retrieval and re…

Reinforcement LearningText Generation

Entity Resolution in Open-domain Conversations

2021-06-01 · NAACL 2021 4 · Mingyue Shang, Tong Wang, Mihail Eric, Jiangning Chen 외

In recent years, incorporating external knowledge for response generation in open-domain conversation systems has attracted great interest. To improve the relevancy of retrieved knowledge, we propose a neural entity link…

Entity LinkingEntity Resolutionnamed-entity-recognitionNamed Entity Recognition+3

Response Generation by Context-aware Prototype Editing

2018-06-19 · Yu Wu, Furu Wei, Shaohan Huang, Yunli Wang 외

Open domain response generation has achieved remarkable progress in recent years, but sometimes yields short and uninformative responses. We propose a new paradigm for response generation, that is response generation by …

DecoderDiversityInformativenessResponse Generation+1

Evaluating the Robustness of Retrieval-Augmented Generation to Adversarial Evidence in the Health Domain

2025-09-04 · Shakiba Amirshahi, Amin Bigdeli, Charles L. A. Clarke, Amira Ghenai arxiv

Retrieval augmented generation (RAG) systems provide a method for factually grounding the responses of a Large Language Model (LLM) by providing retrieved evidence, or context, as support. Guided by this context, RAG sys…