Do continuous word embeddings encode any useful information for constituency parsing? We isolate three ways in which word embeddings might augment a stateof-the-art statistical parser: by connecting out-of-vocabulary words to known ones, by encouraging common behavior among related in-vocabulary words, and by directly providing features for the lexicon. We test each of these hypotheses with a targeted change to a state-of-the-art baseline. Despite small gains on extremely small supervised training sets, we find that extra information from embeddings appears to make little or no difference to a parser with adequate training data. Our results support an overall hypothesis that word embeddings import syntactic information that is ultimately redundant with distinctions learned from treebanks in other ways.
Paper
Full text
How much do word embeddings encode about syntax?
Semantic Scholar · Computer Science · 2014
Abstract
Do continuous word embeddings encode any useful information for constituency parsing? We isolate three ways in which word embeddings might augment a stateof-the-art statistical parser: by connecting out-of-vocabulary words to known ones, by encouraging common behavior among related in-vocabulary words, and by directly providing features for the lexicon. We test each of these hypotheses with a targeted change to a state-of-the-art baseline. Despite small gains on extremely small supervised training sets, we find that extra information from embeddings appears to make little or no difference to a parser with adequate training data. Our results support an overall hypothesis that word embeddings import syntactic information that is ultimately redundant with distinctions learned from treebanks in other ways.