arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.02176cs.CL
收藏

文本连贯性评价的Transformer模型

Transformer Models for Text Coherence Assessment

IIIT Hyderabad(海得拉巴国际信息技术研究所);Microsoft(微软)

Tushar Abhishek, Daksh Rawat, Manish Gupta, Vasudeva Varma

摘要:

连贯是文本质量的一个重要方面,对保证文本的可读性至关重要。这对于文本生成系统(如摘要,问答,机器翻译,问题生成,表到文本等)的输出是必不可少的。自动连贯性评分模型也有助于文章评分或提供写作反馈。以前的大量工作都利用了基于实体的方法,句法模式,话语关系,以及最近传统的深度学习架构来进行文本连贯性评估。以前的工作有缺点,如无法处理长距离依赖关系,词汇表外的单词,或模型序列信息。我们假设一致性评估是一个认知上复杂的任务,需要更深层次的模型,并可以从其他相关任务中受益。因此,在本文中,我们提出了四种不同的基于transformer的任务架构:香草Transformer,分层Transformer,多任务学习为基础的模型,并与基于事实的输入表示模型。我们在四个不同的一致性评估任务上使用多个领域的流行基准数据集进行的实验表明,我们的模型实现了最先进的结果,远远优于现有模型。

英文摘要:

Coherence is an important aspect of text quality and is crucial for ensuring its readability. It is essential desirable for outputs from text generation systems like summarization, question answering, machine translation, question generation, table-to-text, etc. An automated coherence scoring model is also helpful in essay scoring or providing writing feedback. A large body of previous work has leveraged entity-based methods, syntactic patterns, discourse relations, and more recently traditional deep learning architectures for text coherence assessment. Previous work suffers from drawbacks like the inability to handle long-range dependencies, out-of-vocabulary words, or model sequence information. We hypothesize that coherence assessment is a cognitively complex task that requires deeper models and can benefit from other related tasks. Accordingly, in this paper, we propose four different Transformer-based architectures for the task: vanilla Transformer, hierarchical Transformer, multi-task learning-based model, and a model with fact-based input representation. Our experiments with popular benchmark datasets across multiple domains on four different coherence assessment tasks demonstrate that our models achieve state-of-the-art results outperforming existing models by a good margin.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑