arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.01004cs.CLcs.LGstat.ML
收藏

FAT ALBERT:基于BERT的语义相似注意层在大文本中寻找答案

FAT ALBERT: Finding Answers in Large Texts using Semantic Similarity Attention Layer based on BERT

Simon Fraser University(西蒙弗雷泽大学)

Omar Mossad, Amgad Ahmed, Anandharaju Raju, Hari Karthikeyan, Zayed Ahmed

摘要:

基于机器的文本理解一直是自然语言处理的一个重要研究领域。一旦完全理解文本上下文和语义,就可以训练深度学习模型来解决大量任务子集,例如文本摘要、分类和问答。在本文中,我们专注于问答问题,特别是多项选择类型的问题。我们开发了一个模型的基础上BERT,一个国家的最先进的Transformer网络。此外,我们减轻了BERT的能力,以支持大型文本语料库提取的影响力最高的句子,通过一个语义相似度模型。对我们提出的模型的评估表明,它在MovieQA挑战中优于领先的模型,我们目前在排行榜上排名第一,测试准确率为87.79%。最后,我们讨论了模型的缺点,并提出了可能的改进,以克服这些限制。

英文摘要:

Machine based text comprehension has always been a significant research field in natural language processing. Once a full understanding of the text context and semantics is achieved, a deep learning model can be trained to solve a large subset of tasks, e.g. text summarization, classification and question answering. In this paper we focus on the question answering problem, specifically the multiple choice type of questions. We develop a model based on BERT, a state-of-the-art transformer network. Moreover, we alleviate the ability of BERT to support large text corpus by extracting the highest influence sentences through a semantic similarity model. Evaluations of our proposed model demonstrate that it outperforms the leading models in the MovieQA challenge and we are currently ranked first in the leader board with test accuracy of 87.79%. Finally, we discuss the model shortcomings and suggest possible improvements to overcome these limitations.

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。

↑