Syntactic Interchangeability in Word Embedding Models
This work addresses the problem of optimizing word embedding models for syntactic tasks, but it is incremental as it builds on existing methods to analyze hyper-parameter effects.
The study examined how well word embedding models preserve syntactic interchangeability, using part of speech as a proxy, and found that hyper-parameters like context window size affect this property, with results informing model selection for different use-cases.
Nearest neighbors in word embedding models are commonly observed to be semantically similar, but the relations between them can vary greatly. We investigate the extent to which word embedding models preserve syntactic interchangeability, as reflected by distances between word vectors, and the effect of hyper-parameters---context window size in particular. We use part of speech (POS) as a proxy for syntactic interchangeability, as generally speaking, words with the same POS are syntactically valid in the same contexts. We also investigate the relationship between interchangeability and similarity as judged by commonly-used word similarity benchmarks, and correlate the result with the performance of word embedding models on these benchmarks. Our results will inform future research and applications in the selection of word embedding model, suggesting a principle for an appropriate selection of the context window size parameter depending on the use-case.