Can I Be of Further Assistance? Using Unstructured Knowledge Access to Improve Task-oriented Conversational Modeling

• URL: http://arxiv.org/abs/2106.09174v1
• Date: Wed, 16 Jun 2021 23:31:42 GMT
• Title: Can I Be of Further Assistance? Using Unstructured Knowledge Access to Improve Task-oriented Conversational Modeling
• Authors: Di Jin, Seokhwan Kim, Dilek Hakkani-Tur
• Abstract summary: This work focuses on responding to these beyond-API-coverage user turns by incorporating external, unstructured knowledge sources. We introduce novel data augmentation methods for the first two steps and demonstrate that the use of information extracted from dialogue context improves the knowledge selection and end-to-end performances.
• Score: 39.60614611655266
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Most prior work on task-oriented dialogue systems are restricted to limited coverage of domain APIs. However, users oftentimes have requests that are out of the scope of these APIs. This work focuses on responding to these beyond-API-coverage user turns by incorporating external, unstructured knowledge sources. Our approach works in a pipelined manner with knowledge-seeking turn detection, knowledge selection, and response generation in sequence. We introduce novel data augmentation methods for the first two steps and demonstrate that the use of information extracted from dialogue context improves the knowledge selection and end-to-end performances. Through experiments, we achieve state-of-the-art performance for both automatic and human evaluation metrics on the DSTC9 Track 1 benchmark dataset, validating the effectiveness of our contributions.

Related papers

• AVIS: Autonomous Visual Information Seeking with Large Language Model Agent [123.75169211547149]
  We propose an autonomous information seeking visual question answering framework, AVIS. Our method leverages a Large Language Model (LLM) to dynamically strategize the utilization of external tools. AVIS achieves state-of-the-art results on knowledge-intensive visual question answering benchmarks such as Infoseek and OK-VQA.
  arXiv  Detail & Related papers  (2023-06-13T20:50:22Z)
• Using Textual Interface to Align External Knowledge for End-to-End Task-Oriented Dialogue Systems [53.38517204698343]
  We propose a novel paradigm that uses a textual interface to align external knowledge and eliminate redundant processes. We demonstrate our paradigm in practice through MultiWOZ-Remake, including an interactive textual interface built for the MultiWOZ database.
  arXiv  Detail & Related papers  (2023-05-23T05:48:21Z)
• FCC: Fusing Conversation History and Candidate Provenance for Contextual Response Ranking in Dialogue Systems [53.89014188309486]
  We present a flexible neural framework that can integrate contextual information from multiple channels. We evaluate our model on the MSDialog dataset widely used for evaluating conversational response ranking tasks.
  arXiv  Detail & Related papers  (2023-03-31T23:58:28Z)
• SINC: Service Information Augmented Open-Domain Conversation [46.912064636311825]
  We propose a knowledge-driven dialogue system using dynamic service information. We release the first open domain Chinese service knowledge dialogue dataset DuSinc. Both automatic evaluation and human evaluation show that our proposed new method can significantly improve the effect of open-domain conversation.
  arXiv  Detail & Related papers  (2022-06-28T13:41:48Z)
• KETOD: Knowledge-Enriched Task-Oriented Dialogue [77.59814785157877]
  Existing studies in dialogue system research mostly treat task-oriented dialogue and chit-chat as separate domains. We investigate how task-oriented dialogue and knowledge-grounded chit-chat can be effectively integrated into a single model.
  arXiv  Detail & Related papers  (2022-05-11T16:01:03Z)
• Towards Zero and Few-shot Knowledge-seeking Turn Detection in Task-orientated Dialogue Systems [40.74708947185302]
  This work focuses on identifying user requests that are out of the scope of domain APIs. We propose a novel method, REDE, based on adaptive representation learning and density estimation. We demonstrate REDE's competitive performance on DSTC9 data and our newly collected test set.
  arXiv  Detail & Related papers  (2021-09-18T03:33:19Z)
• Learning to Select External Knowledge with Multi-Scale Negative Sampling [31.833572852656008]
  The Track-1 of DSTC9 aims to effectively answer user requests or questions during task-oriented dialogues. By leveraging external knowledge resources, relevant information can be retrieved and encoded into the response generation for these out-of-API-coverage queries.
  arXiv  Detail & Related papers  (2021-02-03T14:59:35Z)
• Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access Track in DSTC9 [21.181446816074704]
  This challenge track aims to expand the coverage of task-oriented dialogue systems by incorporating external unstructured knowledge sources. We define three tasks: knowledge-seeking turn detection, knowledge selection, and knowledge-grounded response generation.
  arXiv  Detail & Related papers  (2021-01-22T18:57:56Z)
• Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access [18.37585134613816]
  In this paper, we propose to expand coverage of task-oriented dialogue systems by incorporating external unstructured knowledge sources. We define three sub-tasks: knowledge-seeking turn detection, knowledge selection, and knowledge-grounded response generation. We introduce an augmented version of MultiWOZ 2.1, which includes new out-of-API-coverage turns and responses grounded on external knowledge sources.
  arXiv  Detail & Related papers  (2020-06-05T16:12:18Z)

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.