arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1504.00548cs.CL
收藏

通过嵌入词典学习理解短语

Learning to Understand Phrases by Embedding the Dictionary

University of Cambridge(剑桥大学);Courant Institute of Mathematical Sciences(库朗数学科学研究所);New York University(纽约大学);Université de Montréal(蒙特利尔大学)

Felix Hill, Kyunghyun Cho, Anna Korhonen, Yoshua Bengio

摘要:

学习丰富语义词表示的分布模型是最近NLP研究的成功案例。然而,事实证明,开发学习短语和句子的有用表示的模型要困难得多。我们建议使用日常词典中的定义作为弥合词汇和短语语义之间差距的一种手段。神经语言嵌入模型可以被有效地训练,以将字典定义(短语)映射到由这些定义定义的单词的(词汇)表示。我们提出了这些架构的两个应用程序:“反向字典”,返回一个概念的名称给出了定义或描述和一般知识的填字游戏问题的答案。在这两项任务中,神经语言嵌入模型在少数免费可用的词汇资源的定义上进行训练,其表现与依赖于重要任务特定工程的现有商业系统一样好或更好。结果突出了神经嵌入架构和基于定义的训练对于开发理解短语和句子的模型的有效性。

英文摘要:

Distributional models that learn rich semantic word representations are a success story of recent NLP research. However, developing models that learn useful representations of phrases and sentences has proved far harder. We propose using the definitions found in everyday dictionaries as a means of bridging this gap between lexical and phrasal semantics. Neural language embedding models can be effectively trained to map dictionary definitions (phrases) to (lexical) representations of the words defined by those definitions. We present two applications of these architectures: "reverse dictionaries" that return the name of a concept given a definition or description and general-knowledge crossword question answerers. On both tasks, neural language embedding models trained on definitions from a handful of freely-available lexical resources perform as well or better than existing commercial systems that rely on significant task-specific engineering. The results highlight the effectiveness of both neural embedding architectures and definition-based training for developing models that understand phrases and sentences.

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。

↑