Two-stage Incomplete Utterance Rewriting on Editing Operation

• URL: http://arxiv.org/abs/2503.16063v1
• Date: Thu, 20 Mar 2025 11:56:14 GMT
• Title: Two-stage Incomplete Utterance Rewriting on Editing Operation
• Authors: Zhiyu Cao, Peifeng Li, Qiaoming Zhu, Yaxin Fan,
• Abstract summary: We propose a novel framework called TEO (emphTwo-stage approach on Editing Operation) for IUR.<n>The first stage generates editing operations and the second stage rewrites incomplete utterances utilizing the generated editing operations and the dialogue context.<n> Experimental results on three IUR datasets show that our TEO outperforms the SOTA models significantly.
• Score: 13.845201572755983
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Previous work on Incomplete Utterance Rewriting (IUR) has primarily focused on generating rewritten utterances based solely on dialogue context, ignoring the widespread phenomenon of coreference and ellipsis in dialogues. To address this issue, we propose a novel framework called TEO (\emph{Two-stage approach on Editing Operation}) for IUR, in which the first stage generates editing operations and the second stage rewrites incomplete utterances utilizing the generated editing operations and the dialogue context. Furthermore, an adversarial perturbation strategy is proposed to mitigate cascading errors and exposure bias caused by the inconsistency between training and inference in the second stage. Experimental results on three IUR datasets show that our TEO outperforms the SOTA models significantly.

Related papers

• Incomplete Utterance Rewriting with Editing Operation Guidance and Utterance Augmentation [13.845201572755983]
  We propose a multi-task learning framework EO-IUR (Editing Operation-guided Incomplete Utterance Rewriting) to generate coherent utterances.<n>We also propose a two-dimensional utterance augmentation strategy, namely editing operation-based incomplete utterance augmentation and LLM-based historical utterance augmentation.<n>The experimental results on three datasets demonstrate that our EO-IUR outperforms previous state-of-the-art (SOTA) baselines in both open-domain and task-oriented dialogue.
  arXiv  Detail & Related papers  (2025-03-20T11:26:46Z)
• Contextualized Diffusion Models for Text-Guided Image and Video Generation [67.69171154637172]
  Conditional diffusion models have exhibited superior performance in high-fidelity text-guided visual generation and editing. We propose a novel and general contextualized diffusion model (ContextDiff) by incorporating the cross-modal context encompassing interactions and alignments between text condition and visual sample. We generalize our model to both DDPMs and DDIMs with theoretical derivations, and demonstrate the effectiveness of our model in evaluations with two challenging tasks: text-to-image generation, and text-to-video editing.
  arXiv  Detail & Related papers  (2024-02-26T15:01:16Z)
• Causal Document-Grounded Dialogue Pre-training [81.16429056652483]
  We present a causally-complete dataset construction strategy for building million-level DocGD pre-training corpora. Experiments on three benchmark datasets demonstrate that our causal pre-training achieves considerable and consistent improvements under fully-supervised, low-resource, few-shot, and zero-shot settings.
  arXiv  Detail & Related papers  (2023-05-18T12:39:25Z)
• Towards End-to-End Open Conversational Machine Reading [57.18251784418258]
  In open-retrieval conversational machine reading (OR-CMR) task, machines are required to do multi-turn question answering given dialogue history and a textual knowledge base. We model OR-CMR as a unified text-to-text task in a fully end-to-end style. Experiments on the ShARC and OR-ShARC dataset show the effectiveness of our proposed end-to-end framework.
  arXiv  Detail & Related papers  (2022-10-13T15:50:44Z)
• An Imitation Learning Curriculum for Text Editing with Non-Autoregressive Models [22.996178360362734]
  We show that imitation learning algorithms for machine translation introduce mismatches between training and inference that lead to undertraining and poor generalization in editing scenarios. We show the efficacy of these strategies on two challenging English editing tasks: controllable text simplification and abstractive summarization.
  arXiv  Detail & Related papers  (2022-03-17T17:36:23Z)
• Structural Pre-training for Dialogue Comprehension [51.215629336320305]
  We present SPIDER, Structural Pre-traIned DialoguE Reader, to capture dialogue exclusive features. To simulate the dialogue-like features, we propose two training objectives in addition to the original LM objectives. Experimental results on widely used dialogue benchmarks verify the effectiveness of the newly introduced self-supervised tasks.
  arXiv  Detail & Related papers  (2021-05-23T15:16:54Z)
• Robust Dialogue Utterance Rewriting as Sequence Tagging [62.12912805378693]
  The task of dialogue rewriting aims to reconstruct the latest dialogue utterance by copying the missing content from the dialogue context. Until now, the existing models for this task suffer from the robustness issue, i.e., performances drop dramatically when testing on a different domain. We propose a novel sequence-tagging-based fluency model so that the search space is significantly reduced.
  arXiv  Detail & Related papers  (2020-12-29T00:05:35Z)
• Recurrent Inference in Text Editing [6.4689151804633775]
  We propose a new inference method, Recurrence, that iteratively performs editing actions, significantly narrowing the problem space. In each iteration, encoding the partially edited text, Recurrence decodes the latent representation, generates an action of short, fixed-length, and applies the action to complete a single edit. For a comprehensive comparison, we introduce three types of text editing tasks: Arithmetic Operators Restoration (AOR), Arithmetic Equation Simplification (AES), Arithmetic Equation Correction (AEC)
  arXiv  Detail & Related papers  (2020-09-26T17:06:29Z)
• SARG: A Novel Semi Autoregressive Generator for Multi-turn Incomplete Utterance Restoration [9.394277095571942]
  In this paper, we investigate the incomplete utterance restoration which has brought general improvement over multi-turn dialogue systems. We propose a novel semi autoregressive generator (SARG) with the high efficiency and flexibility.
  arXiv  Detail & Related papers  (2020-08-04T11:52:20Z)
• Detecting Ongoing Events Using Contextual Word and Sentence Embeddings [110.83289076967895]
  This paper introduces the Ongoing Event Detection (OED) task. The goal is to detect ongoing event mentions only, as opposed to historical, future, hypothetical, or other forms or events that are neither fresh nor current. Any application that needs to extract structured information about ongoing events from unstructured texts can take advantage of an OED system.
  arXiv  Detail & Related papers  (2020-07-02T20:44:05Z)
• Joint Contextual Modeling for ASR Correction and Language Understanding [60.230013453699975]
  We propose multi-task neural approaches to perform contextual language correction on ASR outputs jointly with language understanding (LU) We show that the error rates of off the shelf ASR and following LU systems can be reduced significantly by 14% relative with joint models trained using small amounts of in-domain data.
  arXiv  Detail & Related papers  (2020-01-28T22:09:25Z)

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.