Abstract | ||
---|---|---|
We present models for embedding words in the context of surrounding words. Such models, which we refer to as token embeddings, represent the characteristics of a word that are specific to a given context, such as word sense, syntactic category, and semantic role. We explore simple, efficient token embedding models based on standard neural network architectures. We learn token embeddings on a large amount of unannotated text and evaluate them as features for part-of-speech taggers and dependency parsers trained on much smaller amounts of annotated data. We find that predictors endowed with token embeddings consistently outperform baseline predictors across a range of context window and training set sizes. |
Year | DOI | Venue |
---|---|---|
2017 | 10.18653/v1/W17-2632 | Rep4NLP@ACL |
DocType | Volume | Citations |
Conference | abs/1706.02807 | 3 |
PageRank | References | Authors |
0.65 | 24 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Lifu Tu | 1 | 26 | 2.64 |
Kevin Gimpel | 2 | 1545 | 79.71 |
Karen Livescu | 3 | 1254 | 71.43 |