2013/12/14 by Edouard Grave, Édouard Grave, Guillaume Obozinski +4
Computer Science · #Algorithms and Data Compression #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Topic Modeling #cs.CL #cs.LG
paper · pdf · doi:10.48550/arxiv.1312.4092
New Directions in Transfer and Multi-Task: Learning Across Domains and Tasks (NIPS Workshop) (2013)
arxiv created 2013/12/14 · openalex publication_date 2013/12/14 · arxiv updated 2013/12/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Most natural language processing systems based on machine learning are not robust to domain shift. For example, a state-of-the-art syntactic dependency parser trained on Wall Street Journal sentences has an absolute drop in performance of more than ten points when tested on textual data from the Web. An efficient solution to make these methods more robust to domain shift is to first learn a word representation using large amounts of unlabeled data from both domains, and then use this representation as features in a supervised learning algorithm. In this paper, we propose to use hidden Markov models to learn word representations for part-of-speech tagging. In particular, we study the influence of using data from the source, the target or both domains to learn the representation and the different ways to represent words using an HMM.