出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：Machine learning techniques have demonstrated their versatility and have been successfullyapplied to a wide variety of problems. However, one of their major limitations is the treatmentof sequential information. In general the input and output for these methods is expressed asfixed-dimension vectors, but in many problem domains, as in natural language processing, theinformation is represented by variable-length sequences. In most cases, it is possible to usesome methods that transform these variable length sequences into fixed dimension vectors, buteach of these methods has its own disadvantages. In this paper we propose an alternative toobtain vector representations of fixed dimension from sequences of symbols of variable lengthand their potential applications for natural language processing..
关键词：Neural Networks; Natural Language Processing; Sequential Learning; Deep Architectures
