Year: 2014
Type: conference-paper
Abstract: There is rising interest in vector-space word embeddings and their use in NLP, especially given recent methods for their fast estimation at very large scale.Nearly all this work, however, assumes a single vector per word type-ignoring polysemy and thus jeopardizing their usefulness for downstream tasks.We present an extension to the Skip-gram model that efficiently learns multiple embeddings per word type.It differs from recent related work by jointly performing word sense discrimination and embedding learning, by non-parametrically estimating the number of senses per word type, and by its efficiency and scalability.We present new state-of-the-art results in the word similarity in context task and demonstrate its scalability by training with one machine on a corpus of nearly 1 billion tokens in less than 6 hours.
DOI: 10.3115/v1/d14-1113
Institution: University of Massachusetts Amherst
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Awards: G414571346, G4713059963
OpenAlex ID: W2162456950