PWESuite: Phonetic Word Embeddings and Tasks They Facilitate

arXiv:2304.02541v2 Announce Type: replace
Abstract: Mapping words into a fixed-dimensional vector space is the backbone of modern NLP. While most word embedding methods successfully encode semantic information, they overlook phonetic information that is crucial for many tasks. We develop three methods that use articulatory features to build phonetically informed word embeddings. To address the inconsistent evaluation of existing phonetic word embedding methods, we also contribute a task suite to fairly evaluate past, current, and future methods. We evaluate both (1) …

abstract arxiv build cs.cl embedding embeddings encode features information mapping modern nlp semantic space tasks type vector word word embeddings words