News for hackers. Stuff that matters.
Re:Word Embeddings: Past, Present, and Future by nl on Monday June 12, 2017 @01:06AM (#14535276)
Sense2Vec is a thing; Spacy has a demo https://demos.explosion.ai/sense2vec/?word=natural%20languag...

For many downstream tasks it doesn't seem to improve things though. NLP is hard - lots of things should work but don't because of the sparse training data. Like this slide deck says: most sentences occur only once.

Re:Word Embeddings: Past, Present, and Future by visarga on Monday June 12, 2017 @01:16AM (#14535309)
I realized after posting that I was naive. LSTMs are practically word embedding combinators. Training LSTMs should solve the problem of combining words and interpreting them in context.
Re:Word Embeddings: Past, Present, and Future by Jack000 on Monday June 12, 2017 @02:45AM (#14535521)
I thought Spacy only did part of speech disambiguation rather than sense disambiguation. ie. it would be confused if a word has multiple meanings, all of which are nouns.
Re:Word Embeddings: Past, Present, and Future by nl on Monday June 12, 2017 @08:22AM (#14536681)
This demo uses the Spacy POS tagging to build a word embedding which disambiguates multiple senses. The paper explains it: https://arxiv.org/abs/1511.06388