Year: 2019
Type: preprint
Abstract: The meaning of a word often varies depending on its usage in different domains. The standard word embedding models struggle to represent this variation, as they learn a single global representation for a word. We propose a method to learn domain-specific word embeddings, from text organized into hierarchical domains, such as reviews in an e-commerce website, where products follow a taxonomy. Our structured probabilistic model allows vector representations for the same word to drift away from each other for distant domains in the taxonomy, to accommodate its domain-specific meanings. By learning sets of domain-specific word representations jointly, our model can leverage domain relationships, and it scales well with the number of domains. Using large real-world review datasets, we demonstrate the effectiveness of our model compared to state-of-the-art approaches, in learning domain-specific word embeddings that are both intuitive to humans and benefit downstream NLP tasks.
Source: arXiv (Cornell University)
Authors: Poddar, Lahari, Szarvas, Gyorgy, Frermann, Lea
Institutions: Amazon (United States), The University of Melbourne
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2980960362