Efficient Incomplete Utterance Rewriting with Modern Convolutional Neural Networks

In recent years, the task of Incomplete Utterance Rewriting (IUR) has become an important research focus within the field of natural language processing. The goal is to restore incomplete utterances in a way that fits the surrounding context, thus enhancing overall understanding. In this paper, we propose a novel and efficient method. Unlike previous studies, we utilize a straightforward fully convolutional architecture to reveal the underlying semantic connections that exist among utterances and make corresponding edits to the original text to restore incomplete utterances. Compared to existing advanced methods, our approach provides a superior balance between efficiency and performance.

• Publication year

  2025

• Venue

  2025 4th International Conference on Artificial Intelligence, Human-Computer Interaction and Robotics (AIHCIR)

• Publication date

  2025-11-28

• Fields of study

  Not labeled

• Identifiers
  DOI 10.1109/AIHCIR67580.2025.11405269
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• LLMFormer: Large Language Model for Open-Vocabulary Semantic Segmentation

  2024cited by this paper
• Unified Open-Vocabulary Dense Visual Prediction

  2023cited by this paper
• Open-Vocabulary Object Detection via Scene Graph Discovery

  2023cited by this paper
• How Well Apply Simple MLP to Incomplete Utterance Rewriting?

  2023cited by this paper
• Transformer Scale Gate for Semantic Segmentation

  2022cited by this paper
• Self-Attention for Incomplete Utterance Rewriting

  2022cited by this paper
• ProposalCLIP: Unsupervised Open-Category Object Proposal Generation via Exploiting CLIP Cues

  2022cited by this paper
• RAST: Domain-Robust Dialogue Rewriting as Sequence Tagging

  2021cited by this paper
• SARG: A Novel Semi Autoregressive Generator for Multi-turn Incomplete Utterance Restoration

  2020cited by this paper
• Incomplete Utterance Rewriting as Semantic Segmentation

  2020cited by this paper
• Semantic Role Labeling Guided Multi-turn Dialogue ReWriter

  2020cited by this paper
• Improving Open-Domain Dialogue Systems via Multi-Turn Incomplete Utterance Restoration

  2019influential reference
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

  2019cited by this paper
• Improving Multi-turn Dialogue Modelling with Utterance ReWriter

  2019cited by this paper
• GECOR: An End-to-End Generative Ellipsis and Co-reference Resolution Model for Task-Oriented Dialogue

  2019cited by this paper
• Can You Unpack That? Learning to Rewrite Questions-in-Context

  2019cited by this paper
• Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer

  2019cited by this paper
• OpenNMT: Open-Source Toolkit for Neural Machine Translation

  2017cited by this paper
• Attention is All you Need

  2017cited by this paper
• Get To The Point: Summarization with Pointer-Generator Networks

  2017cited by this paper
• SQuAD: 100,000+ Questions for Machine Comprehension of Text

  2016cited by this paper
• Gaussian Error Linear Units (GELUs)

  2016cited by this paper
• Learning to Respond with Deep Neural Networks for Retrieval-Based Human-Computer Conversation System

  2016cited by this paper
• Layer Normalization

  2016cited by this paper
• Deep Residual Learning for Image Recognition

  2015cited by this paper
• Neural Responding Machine for Short-Text Conversation

  2015cited by this paper
• Neural Machine Translation by Jointly Learning to Align and Translate

  2014cited by this paper
• Adam: A Method for Stochastic Optimization

  2014cited by this paper
• ROUGE: A Package for Automatic Evaluation of Summaries

  2004cited by this paper
• Bleu: a Method for Automatic Evaluation of Machine Translation

  2002cited by this paper

• No citing papers are available for this paper.