Continuous space models for CLIR

详细信息    查看全文

• 作者：Parth Gupta ; ^a ; ^{pgupta@dsic.upv.es} ; Rafael E. Banchs^b ; ^{rembanchs@i2r.a-star.edu.sg} ; Paolo Rosso^a ; ^{prosso@dsic.upv.es}
• 关键词：Cross-language information retrieval ; Latens space models
• 刊名：Information Processing & Management
• 出版年：2017
• 出版时间：March 2017
• 年：2017
• 卷：53
• 期：2
• 页码：359-370
• 全文大小：560 K
• 卷排序：53

文摘

We present and evaluate a novel technique for learning cross-lingual continuous space models to aid cross-language information retrieval (CLIR). Our model, which is referred to as external-data composition neural network (XCNN), is based on a composition function that is implemented on top of a deep neural network that provides a distributed learning framework. Different from most existing models, which rely only on available parallel data for training, our learning framework provides a natural way to exploit monolingual data and its associated relevance metadata for learning continuous space representations of language. Cross-language extensions of the obtained models can then be trained by using a small set of parallel data. This property is very helpful for resource-poor languages, therefore, we carry out experiments on the English-Hindi language pair. On the conducted comparative evaluation, the proposed model is shown to outperform state-of-the-art continuous space models with statistically significant margin on two different tasks: parallel sentence retrieval and ad-hoc retrieval.