Word Representations, Tree Models and Syntactic Functions
This work addresses the need for more fine-grained word representations in NLP applications, though it is incremental as it builds on existing models with added syntactic functions.
The authors tackled the problem of inducing word representations by incorporating syntactic function information into tree-structured hidden Markov models, resulting in improvements on named entity recognition and semantic frame identification tasks that rival state-of-the-art methods.
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.