Implementing Poincaré Embeddings

Jayant Jain gensim, Open Source 10 Comments

I have been working on implementing a model called Poincaré embeddings over the last month or so. The model is from an interesting paper by Facebook AI Research – Poincaré Embeddings for Learning Hierarchical Representations [1]. This post describes the model at a relatively high level of abstraction, and the detailed technical challenges faced in the process of implementing it.

Gensim switches to semantic versioning

Lev Konstantinovskiy gensim, Open Source

Starting with release 1.0.0, Gensim adopts semantic versioning. The time went in a flash, but Gensim has reached maturity. It's been cited in nearly 500 academic papers, used commercially in dozens of companies, organized many coding sprints and meetups and generally withstood the test of time. Between the continued Gensim support by our parent company, rare-technologies.com, and our open Student ...

WordRank embedding: “crowned” is most similar to “king”, not word2vec’s “Canute”

Parul Sethi gensim, Student Incubator

Comparisons to Word2Vec and FastText with TensorBoard visualizations. With various embedding models coming up recently, it could be a difficult task to choose one. Should you simply go with the ones widely used in NLP community such as Word2Vec, or is it possible that some other model could be more accurate for your use case? There are some evaluation metrics …

New Gensim feature: Author-topic modeling. LDA with metadata.

Ólavur Mortensen gensim

The author-topic model is an extension of Latent Dirichlet Allocation that allows data scientists to build topic representations of attached author labels. These author labels can represent any kind of discrete metadata attached to documents, for example, tags on posts on the web. In December of 2016, I wrote a blog post explaining that a Gensim implementation was on its …

Author-topic models: why I am working on a new implementation

Ólavur Mortensen gensim, Machine Learning, Open Source, programming, Student Incubator

Author-topic models promise to give data scientists a tool to simultaneously gain insight about authorship and content in terms of latent topics. The model is closely related to Latent Dirichlet Allocation (LDA). Basically, each author can be associated with multiple documents, and each document can be attributed to multiple authors. The model learns topic representations for each author, so that …

FastText and Gensim word embeddings

Jayant Jain gensim

Facebook Research open sourced a great project recently – fastText, a fast (no surprise) and effective method to learn word representations and perform text classification. I was curious about comparing these embeddings to other commonly used embeddings, so word2vec seemed like the obvious choice, especially considering fastText embeddings are an extension of word2vec. The main goal of the Fast Text …

Pycon 2016 and Gensim Sprint Recap

Lev Konstantinovskiy gensim, Machine Learning, PyCon 2 Comments

Our team was on site representing RaRe Technologies and Gensim at this year’s PyCon 2016 hosted in Portland, Oregon, from May 28th to June 5th. It was a packed, outright massive event of over 3000 attendees which included two days of focused tutorials, sponsor workshops and talks from some of the industry’s renowned experts. RaRe was a sponsor of the …