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 1608.04147cs.CLcs.NE
收藏

基于数值的语义纠错语言模型

Numerically Grounded Language Models for Semantic Error Correction

University College London(伦敦大学学院)

Georgios P. Spithourakis, Isabelle Augenstein, Sebastian Riedel

摘要:

语义错误检测和纠正是诸如事实检查、语音到文本或语法错误纠正等应用的重要任务。目前的方法通常集中在相对较浅的语义,不考虑数字量。我们的方法使用基于文本中数字的语言模型。对于递归神经语言模型架构,这种基础很容易实现,其可以进一步以不完整的背景知识基础为条件。我们对临床报告的评估表明,与未接地的方法相比,数字接地可使困惑度提高33%,语义错误纠正的F1提高5分。以知识为基础的条件会产生进一步的改进。

英文摘要:

Semantic error detection and correction is an important task for applications such as fact checking, speech-to-text or grammatical error correction. Current approaches generally focus on relatively shallow semantics and do not account for numeric quantities. Our approach uses language models grounded in numbers within the text. Such groundings are easily achieved for recurrent neural language model architectures, which can be further conditioned on incomplete background knowledge bases. Our evaluation on clinical reports shows that numerical grounding improves perplexity by 33% and F1 for semantic error correction by 5 points when compared to ungrounded approaches. Conditioning on a knowledge base yields further improvements.

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。

↑