PGTask: Introducing the Task of Profile Generation from Dialogues

• URL: http://arxiv.org/abs/2304.06634v2
• Date: Sat, 26 Aug 2023 05:55:48 GMT
• Title: PGTask: Introducing the Task of Profile Generation from Dialogues
• Authors: Rui Ribeiro, Joao P. Carvalho, Lu\'isa Coheur
• Abstract summary: Profile Generation Task (PGTask) is a new dataset for extracting profile information from dialogues. Using state-of-the-art methods, we provide a benchmark for profile generation on this novel dataset. Our experiments disclose the challenges of profile generation, and we hope that this introduces a new research direction.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent approaches have attempted to personalize dialogue systems by leveraging profile information into models. However, this knowledge is scarce and difficult to obtain, which makes the extraction/generation of profile information from dialogues a fundamental asset. To surpass this limitation, we introduce the Profile Generation Task (PGTask). We contribute with a new dataset for this problem, comprising profile sentences aligned with related utterances, extracted from a corpus of dialogues. Furthermore, using state-of-the-art methods, we provide a benchmark for profile generation on this novel dataset. Our experiments disclose the challenges of profile generation, and we hope that this introduces a new research direction.

Related papers

• Step-Back Profiling: Distilling User History for Personalized Scientific Writing [50.481041470669766]
  Large language models (LLM) excel at a variety of natural language processing tasks, yet they struggle to generate personalized content for individuals. We introduce STEP-BACK PROFILING to personalize LLMs by distilling user history into concise profiles. Our approach outperforms the baselines by up to 3.6 points on the general personalization benchmark.
  arXiv  Detail & Related papers  (2024-06-20T12:58:26Z)
• Recent Trends in Personalized Dialogue Generation: A Review of Datasets, Methodologies, and Evaluations [25.115319934091282]
  This paper seeks to survey the recent landscape of personalized dialogue generation. Covering 22 datasets, we highlight benchmark datasets and newer ones enriched with additional features. We analyze 17 seminal works from top conferences between 2021-2023 and identify five distinct types of problems.
  arXiv  Detail & Related papers  (2024-05-28T09:04:13Z)
• Learning from Emotions, Demographic Information and Implicit User Feedback in Task-Oriented Document-Grounded Dialogues [59.516187851808375]
  We introduce FEDI, the first English dialogue dataset for task-oriented document-grounded dialogues annotated with demographic information, user emotions and implicit feedback. Our experiments with FLAN-T5, GPT-2 and LLaMA-2 show that these data have the potential to improve task completion and the factual consistency of the generated responses and user acceptance.
  arXiv  Detail & Related papers  (2024-01-17T14:52:26Z)
• PRODIGy: a PROfile-based DIalogue Generation dataset [12.566555088877871]
  We propose a new resource where each dialogue is aligned with all possible speaker representations such as communication style, biographies, and personality. This framework allows to test several baselines built using generative language models with several profile configurations.
  arXiv  Detail & Related papers  (2023-11-09T08:19:34Z)
• 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)
• Unsupervised Neural Stylistic Text Generation using Transfer learning and Adapters [66.17039929803933]
  We propose a novel transfer learning framework which updates only $0.3%$ of model parameters to learn style specific attributes for response generation. We learn style specific attributes from the PERSONALITY-CAPTIONS dataset.
  arXiv  Detail & Related papers  (2022-10-07T00:09:22Z)
• Leveraging Natural Supervision for Language Representation Learning and Generation [8.083109555490475]
  We describe three lines of work that seek to improve the training and evaluation of neural models using naturally-occurring supervision. We first investigate self-supervised training losses to help enhance the performance of pretrained language models for various NLP tasks. We propose a framework that uses paraphrase pairs to disentangle semantics and syntax in sentence representations.
  arXiv  Detail & Related papers  (2022-07-21T17:26:03Z)
• Leveraging Pre-Trained Language Models to Streamline Natural Language Interaction for Self-Tracking [25.28975864365579]
  We propose a novel NLP task for self-tracking that extracts close- and open-ended information from a retrospective activity log. The framework augments the prompt using synthetic samples to transform the task into 10-shot learning, to address a cold-start problem in bootstrapping a new tracking topic.
  arXiv  Detail & Related papers  (2022-05-31T01:58:04Z)
• 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)
• 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.