LexVec, a word embedding model written in Go that outperforms word2vec
1–10 of 45 posts
Re: LexVec, a word embedding model written in Go that outperforms word2vec
#2It feels weird how word embedding models have come to refer to both the underlying model, as well as the implementation. word2vec is the implementation of two models: the continuous bag-of-word and the skipgram models by Mikolov, while LexVec implements a version of the PPMI weighted count matrix as referenced in the README file. But the papers also discuss implementation details of LexVec that has no bearing on the final accuracy. I feel like we should make more effort to keep the models and reference implementations separate.
Re: LexVec, a word embedding model written in Go that outperforms word2vec
#3Are there IP considerations? Word2vec is patented.
Re: LexVec, a word embedding model written in Go that outperforms word2vec
#4As pre-built word vectors go, Conceptnet Numberbatch [1], introduced less flippantly as the ConceptNet Vector Ensemble [2], already outperforms this on all the measures evaluated in its paper: Rare Words, MEN-3000, and WordSim-353.
This fact is hard to publicize because somehow the luminaries of the field decided that they didn't care about these evaluations anymore, back when RW performance was around 0.4. I have had reviewers dismiss it as "incremental improvements" to improve Rare Words from 0.4 to 0.6 and to improve MEN-3000 to be as good as a high estimate of inter-annotator agreement.
It is possible to do much, much better than Google News skip-grams ("word2vec"), and one thing that helps get there is lexical knowledge of the kind that's in ConceptNet.
[1] https://blog.conceptnet.io/2016/05/25/conceptnet-numberbatch...
[2] https://blog.luminoso.com/2016/04/06/an-introduction-to-the-...
Re: LexVec, a word embedding model written in Go that outperforms word2vec
#5Reminds me of Chord[1], word2vec written in Chapel
Re: LexVec, a word embedding model written in Go that outperforms word2vec
#6As pre-built word vectors go, Conceptnet Numberbatch [1], introduced less flippantly as the ConceptNet Vector Ensemble [2], already outperforms this on all the measures evaluated in its paper: Rare Words, MEN-3000, and WordSim-353. This fact is hard to publicize because somehow the luminaries of the field decided that they didn't care about these evaluations anymore, back when RW performance was around 0.4. I have ha…
That said: LexVec gives quite good results on word-relatedness for using only distributional knowledge, and only from Wikipedia at that. Adding ConceptNet might give something that is more likely to be state-of-the-art.
Re: LexVec, a word embedding model written in Go that outperforms word2vec
#7Has anyone done any work on handing words that have overloading meanings? Something like 'lead' has two really distinct uses. It's really multiple words that happened to be spelt the same.
Re: LexVec, a word embedding model written in Go that outperforms word2vec
#8Are there IP considerations? Word2vec is patented.
System and method for generating a relationship network - K Franks, CA Myers, RM Podowski - US Patent 7,987,191, 2011 - http://www.google.com/patents/US7987191
Re: LexVec, a word embedding model written in Go that outperforms word2vec
#9It feels weird how word embedding models have come to refer to both the underlying model, as well as the implementation. word2vec is the implementation of two models: the continuous bag-of-word and the skipgram models by Mikolov, while LexVec implements a version of the PPMI weighted count matrix as referenced in the README file. But the papers also discuss implementation details of LexVec that has no bearing on the…
Aren't skip-grams equivalent to NMF of the PPMI matrix?
https://papers.nips.cc/paper/5477-neural-word-embedding-as-i....
Re: LexVec, a word embedding model written in Go that outperforms word2vec
#10Has anyone done any work on handing words that have overloading meanings? Something like 'lead' has two really distinct uses. It's really multiple words that happened to be spelt the same.
Google "word sense induction" or "word sense disambiguation". Intuitively, distributional information of the same sort that is used to derive representations for different word types in W2V or LexVec is useful for distinguishing word senses. Two (noun) senses of lead, two senses of bat, etc. are pretty easy to distinguish on the basis of a bag of words (or syntactic features) around them. Other words are polysemous: they have multiple related senses (across the language, names for materials can be used as containers; animal name for the corresponding food--but with exceptions). For some high frequency words it's a crazy gradient combination of polysemy and homonymy: 'home' for can refer to 1) a place someone lives 2) the corresponding physical structure 3) where something resides (a more 'metaphorical' sense), among other things. Obviously an individual use of a word has a gradient relationship to these senses, and speakers differ regarding what they think the substructure is (polysemous or homonymous, hierarchical or not, etc.). I've been working in my PhD on a technique to figure this out, but people clearly use a lot of information that isn't available in language corpora alone (e.g. intuitive physics).