6 papers · 1 filter
Native Language Identification with Large Language Models
Wei Zhang, Alexandre Salle
We present the first experiments on Native Language Identification (NLI) using LLMs such as GPT-4. NLI is the task of predicting a writer's first language by analyzing their writin…
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…
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).
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…
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…
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…