Coarse-to-Fine Knowledge Selection for Document Grounded Dialogs
- URL: http://arxiv.org/abs/2302.11849v1
- Date: Thu, 23 Feb 2023 08:28:29 GMT
- Title: Coarse-to-Fine Knowledge Selection for Document Grounded Dialogs
- Authors: Yeqin Zhang, Haomin Fu, Cheng Fu, Haiyang Yu, Yongbin Li, Cam-Tu
Nguyen
- Abstract summary: Multi-document grounded dialogue systems (DGDS) answer users' requests by finding supporting knowledge from a collection of documents.
This paper proposes Re3G, which aims to optimize both coarse-grained knowledge retrieval and fine-grained knowledge extraction in a unified framework.
- Score: 11.63334863772068
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Multi-document grounded dialogue systems (DGDS) belong to a class of
conversational agents that answer users' requests by finding supporting
knowledge from a collection of documents. Most previous studies aim to improve
the knowledge retrieval model or propose more effective ways to incorporate
external knowledge into a parametric generation model. These methods, however,
focus on retrieving knowledge from mono-granularity language units (e.g.
passages, sentences, or spans in documents), which is not enough to effectively
and efficiently capture precise knowledge in long documents. This paper
proposes Re3G, which aims to optimize both coarse-grained knowledge retrieval
and fine-grained knowledge extraction in a unified framework. Specifically, the
former efficiently finds relevant passages in a retrieval-and-reranking
process, whereas the latter effectively extracts finer-grain spans within those
passages to incorporate into a parametric answer generation model (BART, T5).
Experiments on DialDoc Shared Task demonstrate the effectiveness of our method.
Related papers
- Learning More Effective Representations for Dense Retrieval through Deliberate Thinking Before Search [65.53881294642451]
Deliberate Thinking based Dense Retriever (DEBATER)
DEBATER enhances recent dense retrievers by enabling them to learn more effective document representations through a step-by-step thinking process.
Experimental results show that DEBATER significantly outperforms existing methods across several retrieval benchmarks.
arXiv Detail & Related papers (2025-02-18T15:56:34Z) - Conversational Text Extraction with Large Language Models Using Retrieval-Augmented Systems [0.20971479389679337]
This study introduces a system leveraging Large Language Models (LLMs) to extract text from PDF documents via a conversational interface.
The system provides informative responses to user inquiries while highlighting relevant passages within the PDF.
The proposed system gives competitive ROUGE values as compared to existing state-of-the-art techniques for text extraction and summarization.
arXiv Detail & Related papers (2025-01-16T19:12:25Z) - Retrieval-Generation Synergy Augmented Large Language Models [30.53260173572783]
We propose an iterative retrieval-generation collaborative framework.
We conduct experiments on four question answering datasets, including single-hop QA and multi-hop QA tasks.
arXiv Detail & Related papers (2023-10-08T12:50:57Z) - Retrieval Augmentation for Commonsense Reasoning: A Unified Approach [64.63071051375289]
We propose a unified framework of retrieval-augmented commonsense reasoning (called RACo)
Our proposed RACo can significantly outperform other knowledge-enhanced method counterparts.
arXiv Detail & Related papers (2022-10-23T23:49:08Z) - Generate rather than Retrieve: Large Language Models are Strong Context
Generators [74.87021992611672]
We present a novel perspective for solving knowledge-intensive tasks by replacing document retrievers with large language model generators.
We call our method generate-then-read (GenRead), which first prompts a large language model to generate contextutal documents based on a given question, and then reads the generated documents to produce the final answer.
arXiv Detail & Related papers (2022-09-21T01:30:59Z) - Layout-Aware Information Extraction for Document-Grounded Dialogue:
Dataset, Method and Demonstration [75.47708732473586]
We propose a layout-aware document-level Information Extraction dataset, LIE, to facilitate the study of extracting both structural and semantic knowledge from visually rich documents.
LIE contains 62k annotations of three extraction tasks from 4,061 pages in product and official documents.
Empirical results show that layout is critical for VRD-based extraction, and system demonstration also verifies that the extracted knowledge can help locate the answers that users care about.
arXiv Detail & Related papers (2022-07-14T07:59:45Z) - Enhanced Knowledge Selection for Grounded Dialogues via Document
Semantic Graphs [123.50636090341236]
We propose to automatically convert background knowledge documents into document semantic graphs.
Our document semantic graphs preserve sentence-level information through the use of sentence nodes and provide concept connections between sentences.
Our experiments show that our semantic graph-based knowledge selection improves over sentence selection baselines for both the knowledge selection task and the end-to-end response generation task on HollE.
arXiv Detail & Related papers (2022-06-15T04:51:32Z) - Variational Learning for Unsupervised Knowledge Grounded Dialogs [6.761874595503588]
Recent methods for knowledge grounded dialogs generate responses by incorporating information from an external textual document.
We develop a variational approach to the above technique wherein, we instead maximize the Evidence Lower bound (ELBO)
To the best of our knowledge we are the first to apply variational training for open-scale unsupervised knowledge grounded dialog systems.
arXiv Detail & Related papers (2021-11-23T13:41:03Z) - DIALKI: Knowledge Identification in Conversational Systems through
Dialogue-Document Contextualization [41.21012318918167]
We introduce a knowledge identification model that leverages the document structure to provide dialogue-contextualized passage encodings.
We demonstrate the effectiveness of our model on two document-grounded conversational datasets.
arXiv Detail & Related papers (2021-09-10T05:40:37Z) - 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)
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.