5

I am looking for downloadable word embeddings (a.k.a. word vectors, distributed word representations). I'm aware of:

as well as the retrofitting tool.

What else is available?

2

Polyglot's webpage has word embeddings for ~ 137 languages, including English.

Distributed word representations (word embeddings) have recently contributed to competitive performance in language modeling and several NLP tasks. In this work, we train word embeddings for more than 100 languages using their corresponding Wikipedias. We quantitatively demonstrate the utility of our word embeddings by using them as the sole features for training a part of speech tagger for a subset of these languages. We find their performance to be competitive with near state-of-art methods in English, Danish and Swedish. Moreover, we investigate the semantic features captured by these embeddings through the proximity of word groupings. We will release these embeddings publicly to help researchers in the development and enhancement of multilingual applications.

Polyglot is joint work with Bryan Perozzi, and Steven Skiena.

The word embeddings are downloaded as a Python pickle files. It contains 100004 words, and word embeddings have 64 dimensions.

enter image description here

Polyglot is coded in Theano.

1

The RNNLM Toolkit's webpage contains three pre-trained word embeddings:

Word projections from RNN-80 and RNN-640 models trained on Broadcast news data + tool for computing the closest words. (extra large 1600-dimensional features from 3 models are here).

It has 82390 words.

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.