arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2104.09777cs.CLcs.HC
收藏

基于覆盖深度学习语言模型的文本子句提取

Subsentence Extraction from Text Using Coverage-Based Deep Learning Language Models

University of Auckland(奥克兰大学);CSIRO Data61(澳大利亚联邦科学与工业研究组织数据61研究所)

JongYoon Lim, Inkyu Sa, Ho Seok Ahn, Norina Gasteiger, Sanghyub John Lee, Bruce MacDonald

摘要:

情感预测在心理学、神经科学和计算机科学等各个研究领域仍然是一个具有挑战性且尚未解决的任务。这源于其高度的主观性和有限的输入来源,可以有效地捕捉实际的情绪。如果只使用基于文本的输入,这可能更具挑战性。与此同时,深度学习的兴起和前所未有的大量数据为人工智能执行令人印象深刻的准确预测甚至人类水平的推理铺平了道路。从这一点得到启发,我们提出了一个基于覆盖率的情感和子句提取系统,估计输入文本的跨度,并递归地将此信息反馈给网络。预测子句由表达情感的辅助信息组成。这是实现生动和史诗般的情感交付(在本文的范围内)以及其他自然语言处理任务(如文本摘要和问答)的重要构建块。我们的方法在子句预测方面大大优于最先进的方法(即,平均Jaccard评分为0.72至0.89)。为了评估,我们设计了由24个消融研究组成的严格实验。最后,我们通过共享软件包和一个公共数据集将我们学到的经验教训反馈给社区,该数据集可以重现本文中提出的结果。

英文摘要:

Sentiment prediction remains a challenging and unresolved task in various research fields, including psychology, neuroscience, and computer science. This stems from its high degree of subjectivity and limited input sources that can effectively capture the actual sentiment. This can be even more challenging with only text-based input. Meanwhile, the rise of deep learning and an unprecedented large volume of data have paved the way for artificial intelligence to perform impressively accurate predictions or even human-level reasoning. Drawing inspiration from this, we propose a coverage-based sentiment and subsentence extraction system that estimates a span of input text and recursively feeds this information back to the networks. The predicted subsentence consists of auxiliary information expressing a sentiment. This is an important building block for enabling vivid and epic sentiment delivery (within the scope of this paper) and for other natural language processing tasks such as text summarisation and Q&A. Our approach outperforms the state-of-the-art approaches by a large margin in subsentence prediction (i.e., Average Jaccard scores from 0.72 to 0.89). For the evaluation, we designed rigorous experiments consisting of 24 ablation studies. Finally, our learned lessons are returned to the community by sharing software packages and a public dataset that can reproduce the results presented in this paper.

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。

↑