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 1808.09419cs.CL
收藏

识别格式良好的自然语言问题

Identifying Well-formed Natural Language Questions

Google AI Language(谷歌AI语言部门)

Manaal Faruqui, Dipanjan Das

摘要:

理解搜索查询是一个很难的问题,因为它涉及到处理用户普遍发出的“单词沙拉”文本。然而,如果查询类似于格式良好的问题,则自然语言处理流水线能够执行更准确的解释,从而减少下游复合错误。因此,识别查询是否格式良好可以增强查询理解。在这里,我们介绍了一个新的任务,确定一个良好的形式自然语言的问题。我们构建并发布了一个包含25,100个公开可用问题的数据集,这些问题分为格式良好和非格式良好的类别,并报告了测试集的准确率为70.7%。我们还表明,我们的分类器可用于提高神经序列到序列模型的性能,以生成阅读理解问题。

英文摘要:

Understanding search queries is a hard problem as it involves dealing with "word salad" text ubiquitously issued by users. However, if a query resembles a well-formed question, a natural language processing pipeline is able to perform more accurate interpretation, thus reducing downstream compounding errors. Hence, identifying whether or not a query is well formed can enhance query understanding. Here, we introduce a new task of identifying a well-formed natural language question. We construct and release a dataset of 25,100 publicly available questions classified into well-formed and non-wellformed categories and report an accuracy of 70.7% on the test set. We also show that our classifier can be used to improve the performance of neural sequence-to-sequence models for generating questions for reading comprehension.

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。

↑