Context-Aware Language Modeling for Goal-Oriented Dialogue Systems

• URL: http://arxiv.org/abs/2204.10198v1
• Date: Mon, 18 Apr 2022 17:23:11 GMT
• Title: Context-Aware Language Modeling for Goal-Oriented Dialogue Systems
• Authors: Charlie Snell, Sherry Yang, Justin Fu, Yi Su, Sergey Levine
• Abstract summary: We formulate goal-oriented dialogue as a partially observed Markov decision process. We derive a simple and effective method to finetune language models in a goal-aware way. We evaluate our method on a practical flight-booking task using AirDialogue.
• Score: 84.65707332816353
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Goal-oriented dialogue systems face a trade-off between fluent language generation and task-specific control. While supervised learning with large language models is capable of producing realistic text, how to steer such responses towards completing a specific task without sacrificing language quality remains an open question. In this work, we formulate goal-oriented dialogue as a partially observed Markov decision process, interpreting the language model as a representation of both the dynamics and the policy. This view allows us to extend techniques from learning-based control, such as task relabeling, to derive a simple and effective method to finetune language models in a goal-aware way, leading to significantly improved task performance. We additionally introduce a number of training strategies that serve to better focus the model on the task at hand. We evaluate our method, Context-Aware Language Models (CALM), on a practical flight-booking task using AirDialogue. Empirically, CALM outperforms the state-of-the-art method by 7% in terms of task success, matching human-level task performance.

Related papers

• Speech-Copilot: Leveraging Large Language Models for Speech Processing via Task Decomposition, Modularization, and Program Generation [42.55462692822432]
  Speech-Copilot is a modular framework for instruction-oriented speech-processing tasks. It builds speech processing-specific toolsets by analyzing pre-collected task instructions. It features a flexible agent based on large language models that performs tasks through program generation.
  arXiv  Detail & Related papers  (2024-07-13T13:26:43Z)
• Scalable Language Model with Generalized Continual Learning [58.700439919096155]
  The Joint Adaptive Re-ization (JARe) is integrated with Dynamic Task-related Knowledge Retrieval (DTKR) to enable adaptive adjustment of language models based on specific downstream tasks. Our method demonstrates state-of-the-art performance on diverse backbones and benchmarks, achieving effective continual learning in both full-set and few-shot scenarios with minimal forgetting.
  arXiv  Detail & Related papers  (2024-04-11T04:22:15Z)
• Integrating Self-supervised Speech Model with Pseudo Word-level Targets from Visually-grounded Speech Model [57.78191634042409]
  We propose Pseudo-Word HuBERT (PW-HuBERT), a framework that integrates pseudo word-level targets into the training process. Our experimental results on four spoken language understanding (SLU) benchmarks suggest the superiority of our model in capturing semantic information.
  arXiv  Detail & Related papers  (2024-02-08T16:55:21Z)
• Solving Dialogue Grounding Embodied Task in a Simulated Environment using Further Masked Language Modeling [0.0]
  Our proposed method employs language modeling to enhance task understanding through state-of-the-art (SOTA) methods using language models. Our experimental results provide compelling evidence of the superiority of our proposed method.
  arXiv  Detail & Related papers  (2023-06-21T17:17:09Z)
• Towards Generalized Models for Task-oriented Dialogue Modeling on Spoken Conversations [22.894541507068933]
  This paper presents our approach to build generalized models for the Knowledge-grounded Task-oriented Dialogue Modeling on Spoken Conversations Challenge of DSTC-10. We employ extensive data augmentation strategies on written data, including artificial error injection and round-trip text-speech transformation. Our approach ranks third on the objective evaluation and second on the final official human evaluation.
  arXiv  Detail & Related papers  (2022-03-08T12:26:57Z)
• Analyzing the Limits of Self-Supervision in Handling Bias in Language [52.26068057260399]
  We evaluate how well language models capture the semantics of four tasks for bias: diagnosis, identification, extraction and rephrasing. Our analyses indicate that language models are capable of performing these tasks to widely varying degrees across different bias dimensions, such as gender and political affiliation.
  arXiv  Detail & Related papers  (2021-12-16T05:36:08Z)
• Cross-lingual Spoken Language Understanding with Regularized Representation Alignment [71.53159402053392]
  We propose a regularization approach to align word-level and sentence-level representations across languages without any external resource. Experiments on the cross-lingual spoken language understanding task show that our model outperforms current state-of-the-art methods in both few-shot and zero-shot scenarios.
  arXiv  Detail & Related papers  (2020-09-30T08:56:53Z)
• DialoGLUE: A Natural Language Understanding Benchmark for Task-Oriented Dialogue [17.729711165119472]
  We introduce DialoGLUE (Dialogue Language Understanding Evaluation), a public benchmark consisting of 7 task-oriented dialogue datasets covering 4 distinct natural language understanding tasks. We release several strong baseline models, demonstrating performance improvements over a vanilla BERT architecture and state-of-the-art results on 5 out of 7 tasks. Through the DialoGLUE benchmark, the baseline methods, and our evaluation scripts, we hope to facilitate progress towards the goal of developing more general task-oriented dialogue models.
  arXiv  Detail & Related papers  (2020-09-28T18:36:23Z)
• TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialogue [113.45485470103762]
  In this work, we unify nine human-human and multi-turn task-oriented dialogue datasets for language modeling. To better model dialogue behavior during pre-training, we incorporate user and system tokens into the masked language modeling.
  arXiv  Detail & Related papers  (2020-04-15T04:09:05Z)

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.