mlsanityData to 14 Oct 2026

CARE: A Clue-guided Assistant for CSRs to Read User Manuals

arXiv 2408.03633 ↗First posted 7 Aug 2024cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

It is time-saving to build a reading assistant for customer service representations (CSRs) when reading user manuals, especially information-rich ones. Current solutions don't fit the online custom service scenarios well due to the lack of attention to user questions and possible responses. Hence, we propose to develop a time-saving and careful reading assistant for CSRs, named CARE. It can help the CSRs quickly find proper responses from the user manuals via explicit clue chains. Specifically, each of the clue chains is formed by inferring over the user manuals, starting from the question clue aligned with the user question and ending at a possible response. To overcome the shortage of supervised data, we adopt the self-supervised strategy for model learning. The offline experiment shows that CARE is efficient in automatically inferring accurate responses from the user manual. The online experiment further demonstrates the superiority of CARE to reduce CSRs' reading burden and keep high service quality, in particular with >35% decrease in time spent and keeping a >0.75 ICC score.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 39 references that are in the map. First posted on arXiv 7 Aug 2024.

Builds on

19 of 39 references.

References · 19

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  3. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  4. 2019Heterogeneous Graph Attention Networkcited by 734
  5. 2018The Web as a Knowledge-base for Answering Complex Questionscited by 410
  6. 2021QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answeringcited by 388
  7. 2021Self-supervised Heterogeneous Graph Neural Network with Co-contrastive Learningcited by 130
  8. 2020A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sourcescited by 126
  9. 2021A Survey on Complex Knowledge Base Question Answering: Methods, Challenges and Solutionscited by 78
  10. 2020SPARQA: Skeleton-based Semantic Parsing for Complex Questions over Knowledge Basescited by 47
  11. 2019R4C: A Benchmark for Evaluating RC Systems to Get the Right Answer for the Right Reasoncited by 36
  12. 2020A Survey on Explainability in Machine Reading Comprehensioncited by 33
7 more
  1. 2022Scim: Intelligent Skimming Support for Scientific Paperscited by 27
  2. 2022PERT: Pre-training BERT with Permuted Language Modelcited by 23
  3. 2022Uni-Parser: Unified Semantic Parser for Question Answering on Knowledge Base and Databasecited by 16
  4. 2023HOP, UNION, GENERATE: Explainable Multi-hop Reasoning without Rationale Supervisioncited by 5
  5. 2022Dynamic Relevance Graph Network for Knowledge-Aware Question Answeringcited by 4
  6. 2021Fact-Tree Reasoning for N-ary Question Answering over Knowledge Graphscited by 2
  7. 2022ChartText: Linking Text with Charts in Documentscited by 1

Built on by

Not cited yet.