Joint Learning of Words and Meaning Representations for Open-Text Semantic Parsing
Joint Learning of Words and Meaning Representations for Open-Text Semantic Parsing
复制标题
DOI：
--
复制
发表时间：
2012-03
期刊：
影响因子：
--
通讯作者：
Antoine Bordes;Xavier Glorot;J. Weston;Yoshua Bengio
中科院分区：
文献类型：
--
作者：
Antoine Bordes;Xavier Glorot;J. Weston;Yoshua Bengio
开放文本语义解析器旨在通过推理相应的意义表示(MR-其意义的正式表示)来解释自然语言中的任何语句。不幸的是，由于缺乏直接监督的数据，大规模系统不能很容易地通过机器学习。我们提出了一种方法，该方法学习将MRS分配给广泛的文本(使用映射到40,000多个实体的70,000多个单词的词典)，这要归功于一种结合了从知识库(例如WordNet)学习和从原始文本学习的训练方案。该模型通过对这些不同数据源进行操作的多任务训练过程，联合学习单词、实体和MRS的表示。因此，该系统最终在单个优雅的框架中提供了在语义解析上下文中获取知识和消除词义歧义的方法。在这些不同任务上的实验表明了这种方法的前景。
Open-text semantic parsers are designed to interpret any statement in natural language by inferring a corresponding meaning representation (MR – a formal representation of its sense). Unfortunately, large scale systems cannot be easily machine-learned due to a lack of directly supervised data. We propose a method that learns to assign MRs to a wide range of text (using a dictionary of more than 70,000 words mapped to more than 40,000 entities) thanks to a training scheme that combines learning from knowledge bases (e.g. WordNet) with learning from raw text. The model jointly learns representations of words, entities and MRs via a multi-task training process operating on these diverse sources of data. Hence, the system ends up providing methods for knowledge acquisition and wordsense disambiguation within the context of semantic parsing in a single elegant framework. Experiments on these various tasks indicate the promise of the approach.