2015/08/31 by Simon Šuster, Šuster, Simon, Gertjan van Noord +3
Computer Science · Mathematics · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Natural Language Processing Techniques #Speech and dialogue systems #Topic Modeling #cs.CL #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.1508.07709
Add github code repository link. Fix equation 4.1
openalex publication_date 2015/08/31 · arxiv created 2016/02/05 · arxiv updated 2016/02/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Word representations induced from models with discrete latent variables (e.g. HMMs) have been shown to be beneficial in many NLP applications. In this work, we exploit labeled syntactic dependency trees and formalize the induction problem as unsupervised learning of tree-structured hidden Markov models. Syntactic functions are used as additional observed variables in the model, influencing both transition and emission components. Such syntactic information can potentially lead to capturing more fine-grain and functional distinctions between words, which, in turn, may be desirable in many NLP applications. We evaluate the word representations on two tasks -- named entity recognition and semantic frame identification. We observe improvements from exploiting syntactic function information in both cases, and the results rivaling those of state-of-the-art representation learning methods. Additionally, we revisit the relationship between sequential and unlabeled-tree models and find that the advantage of the latter is not self-evident.