Well Begun is Half Done: Generator-agnostic Knowledge Pre-Selection for Knowledge-Grounded Dialogue

• URL: http://arxiv.org/abs/2310.07659v3
• Date: Fri, 20 Oct 2023 13:43:35 GMT
• Title: Well Begun is Half Done: Generator-agnostic Knowledge Pre-Selection for Knowledge-Grounded Dialogue
• Authors: Lang Qin, Yao Zhang, Hongru Liang, Jun Wang, Zhenglu Yang
• Abstract summary: We focus on the third under-explored category of study, which can not only select knowledge accurately in advance, but has the advantage to reduce the learning, adjustment, and interpretation burden. We propose GATE, a generator-agnostic knowledge selection method, to prepare knowledge for subsequent response generation models.
• Score: 24.395322923436026
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Accurate knowledge selection is critical in knowledge-grounded dialogue systems. Towards a closer look at it, we offer a novel perspective to organize existing literature, i.e., knowledge selection coupled with, after, and before generation. We focus on the third under-explored category of study, which can not only select knowledge accurately in advance, but has the advantage to reduce the learning, adjustment, and interpretation burden of subsequent response generation models, especially LLMs. We propose GATE, a generator-agnostic knowledge selection method, to prepare knowledge for subsequent response generation models by selecting context-related knowledge among different knowledge structures and variable knowledge requirements. Experimental results demonstrate the superiority of GATE, and indicate that knowledge selection before generation is a lightweight yet effective way to facilitate LLMs (e.g., ChatGPT) to generate more informative responses.

Related papers

• A Knowledge Plug-and-Play Test Bed for Open-domain Dialogue Generation [51.31429493814664]
  We present a benchmark named multi-source Wizard of Wikipedia for evaluating multi-source dialogue knowledge selection and response generation. We propose a new challenge, dialogue knowledge plug-and-play, which aims to test an already trained dialogue model on using new support knowledge from previously unseen sources.
  arXiv  Detail & Related papers  (2024-03-06T06:54:02Z)
• Beyond Factuality: A Comprehensive Evaluation of Large Language Models as Knowledge Generators [78.63553017938911]
  Large language models (LLMs) outperform information retrieval techniques for downstream knowledge-intensive tasks. However, community concerns abound regarding the factuality and potential implications of using this uncensored knowledge. We introduce CONNER, designed to evaluate generated knowledge from six important perspectives.
  arXiv  Detail & Related papers  (2023-10-11T08:22:37Z)
• Generative Knowledge Selection for Knowledge-Grounded Dialogues [40.47433331803577]
  We propose a simple yet effective generative approach for knowledge selection, called GenKS. GenKS learns to select snippets by generating their identifiers with a sequence-to-sequence model. We conduct experiments on three benchmark datasets, and verify GenKS achieves the best results on both knowledge selection and response generation.
  arXiv  Detail & Related papers  (2023-04-10T19:49:55Z)
• A Survey of Knowledge Enhanced Pre-trained Language Models [78.56931125512295]
  We present a comprehensive review of Knowledge Enhanced Pre-trained Language Models (KE-PLMs) For NLU, we divide the types of knowledge into four categories: linguistic knowledge, text knowledge, knowledge graph (KG) and rule knowledge. The KE-PLMs for NLG are categorized into KG-based and retrieval-based methods.
  arXiv  Detail & Related papers  (2022-11-11T04:29:02Z)
• Knowledge-Grounded Dialogue with Reward-Driven Knowledge Selection [1.1633929083694388]
  Knoformer is a dialogue response generation model based on reinforcement learning. It can automatically select one or more related knowledge from the knowledge pool and does not need knowledge labels during training.
  arXiv  Detail & Related papers  (2021-08-31T08:53:08Z)
• Retrieval-Free Knowledge-Grounded Dialogue Response Generation with Adapters [52.725200145600624]
  We propose KnowExpert to bypass the retrieval process by injecting prior knowledge into the pre-trained language models with lightweight adapters. Experimental results show that KnowExpert performs comparably with the retrieval-based baselines.
  arXiv  Detail & Related papers  (2021-05-13T12:33:23Z)
• Prediction, Selection, and Generation: Exploration of Knowledge-Driven Conversation System [24.537862151735006]
  In open-domain conversational systems, it is important but challenging to leverage background knowledge. We combine the knowledge bases and pre-training model to propose a knowledge-driven conversation system. We study the performance factors that maybe affect the generation of knowledge-driven dialogue.
  arXiv  Detail & Related papers  (2021-04-23T07:59:55Z)
• Difference-aware Knowledge Selection for Knowledge-grounded Conversation Generation [101.48602006200409]
  We propose a difference-aware knowledge selection method for multi-turn knowledge-grounded dialogs. It first computes the difference between the candidate knowledge sentences provided at the current turn and those chosen in the previous turns. Then, the differential information is fused with or disentangled from the contextual information to facilitate final knowledge selection.
  arXiv  Detail & Related papers  (2020-09-20T07:47:26Z)
• Knowledge-graph based Proactive Dialogue Generation with Improved Meta-Learning [0.0]
  We propose a knowledge graph based proactive dialogue generation model (KgDg) with three components. For knowledge triplets embedding and selection, we formulate it as a problem of sentence embedding to better capture semantic information. Our improved MAML algorithm is capable of learning general features from a limited number of knowledge graphs.
  arXiv  Detail & Related papers  (2020-04-19T08:41:12Z)
• Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue [51.513276162736844]
  We propose a sequential latent variable model as the first approach to this matter. The model named sequential knowledge transformer (SKT) can keep track of the prior and posterior distribution over knowledge.
  arXiv  Detail & Related papers  (2020-02-18T11:59:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.