activity
20162019
collaborators

5 papers

cs.CL2019

Why So Down? The Role of Negative (and Positive) Pointwise Mutual Information in Distributional Semantics

Alexandre Salle, Aline Villavicencio

In distributional semantics, the pointwise mutual information () weighting of the cooccurrence matrix performs far better than raw counts. There is, however, an issue…

cs.CL2019

Think Again Networks and the Delta Loss

Alexandre Salle, Marcelo Prates

This short paper introduces an abstraction called Think Again Networks (ThinkNet) which can be applied to any state-dependent function (such as a recurrent neural network).

cs.CL2018

Incorporating Subword Information into Matrix Factorization Word Embeddings

Alexandre Salle, Aline Villavicencio

The positive effect of adding subword information to word embeddings has been demonstrated for predictive models. In this paper we investigate whether similar benefits can also be…

cs.CL2016

Matrix Factorization using Window Sampling and Negative Sampling for Improved Word Representations

Alexandre Salle, Marco Idiart, Aline Villavicencio

In this paper, we propose LexVec, a new method for generating distributed word representations that uses low-rank, weighted factorization of the Positive Point-wise Mutual Informat…

cs.CL2016

Enhancing the LexVec Distributed Word Representation Model Using Positional Contexts and External Memory

Alexandre Salle, Marco Idiart, Aline Villavicencio

In this paper we take a state-of-the-art model for distributed word representation that explicitly factorizes the positive pointwise mutual information (PPMI) matrix using window s…