Incomplete utterance rewriting (IUR) has recently become an essential task in NLP, aiming to complement the incomplete utterance with sufficient context information for comprehension. In this paper, we propose a novel method by directly extracting the coreference and omission relationship from the self-attention weight matrix of the transformer instead of word embeddings and edit the original text accordingly to generate the complete utterance. Benefiting from the rich information in the self-attention weight matrix, our method achieved competitive results on public IUR datasets.
Multi-Granularity Information Interaction Framework for Incomplete Utterance Rewriting
Wangxuan Institute of Computer Technology, Peking University(北京大学王选计算机研究所);Institute for Artificial Intelligence, Peking University(北京大学人工智能研究院);Ant Group(蚂蚁集团)
Improving Multi-turn Dialogue Modelling with Utterance ReWriter
Tencent Inc(腾讯公司);MPI Informatics(马克斯·普朗克信息学研究所);Saarland Informatics Campus(萨尔大学信息学院);Institute of Software, University of Chinese Academy of Science(中国科学院大学软件研究所);Alibaba Group(阿里巴巴集团);IBM Research(IBM研究院)
RSMLP: A light Sampled MLP Structure for Incomplete Utterance Rewrite
Hunan University(湖南大学);College of Electrical and Information Engineering, Hunan University(湖南大学电气与信息工程学院);Greater Bay Area Institute for Innovation, Hunan University(湖南大学粤港澳大湾区创新研究院)
SDR-GNN: Spectral Domain Reconstruction Graph Neural Network for Incomplete Multimodal Learning in Conversational Emotion Recognition
College of Computer and Mathematics, Central South University of Forestry and Technology(中南林业科技大学计算机与数学学院);Department of Computer Science, State University of New York(纽约州立大学计算机科学系)
Enhance Incomplete Utterance Restoration by Joint Learning Token Extraction and Text Generation
Cinnamon AI(Cinnamon人工智能公司);Hung Yen University of Technology and Education(兴安技术教育大学)
本文介绍了一种用于不完整话语恢复的模型JET(\textbf{J}),它是一个基于学习标记\textbf{E}提取和\textbf{T}下一代的模型。与以往的研究只工作在提取或抽象数据集不同,我们设计了一个简单而有效的模型,适用于两种情况下的IUR。我们的设计模拟IUR的性质,从上下文中省略的令牌有助于恢复。由此,我们构造一个识别省略的标记的选择器。为了支持选择器,我们设计了两种标签创建方法(软标签和硬标签),它们可以在省略的标记没有注释数据的情况下工作。恢复是通过使用发电机与联合学习的帮助下,选择。在四个基准数据集上的提取和抽象场景中的令人满意的结果表明,我们的模型在丰富和有限的训练数据设置中都优于预训练的T5和非生成语言模型方法。\footnote{The code is available at \url{https://github.com/shumpei19/JET}}
GSDNet: Revisiting Incomplete Multimodal-Diffusion from Graph Spectrum Perspective for Conversation Emotion Recognition
College of Computer and Mathematics, Central South University of Forestry and Technology(计算机与数学学院,中央南大学林业科技学院);Department of Computer Science, Anhui Normal University(计算机科学系,安徽师范大学);Future Technology Institute, South China University of Technology(未来技术研究院,华南理工大学);Department of Computer Science, State University of New York(计算机科学系,纽约州立大学)