Related papers: Generalized Biwords for Bitext Compression and Tra…

In this paper, we propose an alternative to deep neural networks for semantic information retrieval for the case of long documents. This new approach exploiting clustering techniques to take into account the meaning of words in Information…

Word embeddings have gained significant attention as learnable representations of semantic relations between words, and have been shown to improve upon the results of traditional word representations. However, little effort has been devoted…

Word and phrase tables are key inputs to machine translations, but costly to produce. New unsupervised learning methods represent words and phrases in a high-dimensional vector space, and these monolingual embeddings have been shown to…

Word embeddings derived from human-generated corpora inherit strong gender bias which can be further amplified by downstream models. Some commonly adopted debiasing approaches, including the seminal Hard Debias algorithm, apply…

In our globalized world, a growing number of situations arise where people are required to communicate in one or several foreign languages. In the case of written communication, users with a good command of a foreign language may find…

It has been shown that word embeddings derived from large corpora tend to incorporate biases present in their training data. Various methods for mitigating these biases have been proposed, but recent work has demonstrated that these methods…

With the rapid growth of textual content on the Internet, efficient large-scale semantic text retrieval has garnered increasing attention from both academia and industry. Text hashing, which projects original texts into compact binary hash…

Biclustering is a class of techniques that simultaneously clusters the rows and columns of a matrix to sort heterogeneous data into homogeneous blocks. Although many algorithms have been proposed to find biclusters, existing methods suffer…

Graph reordering is a powerful technique to increase the locality of the representations of graphs, which can be helpful in several applications. We study how the technique can be used to improve compression of graphs and inverted indexes.…

In this paper, we present an approach to learn multilingual sentence embeddings using a bi-directional dual-encoder with additive margin softmax. The embeddings are able to achieve state-of-the-art results on the United Nations (UN)…

In recent years, word embeddings have been widely used to measure biases in texts. Even if they have proven to be effective in detecting a wide variety of biases, metrics based on word embeddings lack transparency and interpretability. We…

There are two main approaches to the distributed representation of words: low-dimensional deep learning embeddings and high-dimensional distributional models, in which each dimension corresponds to a context word. In this paper, we combine…

This paper addresses a novel task of detecting sub-topic correspondence in a pair of text fragments, enhancing common notions of text similarity. This task is addressed by coupling corresponding term subsets through bipartite clustering.…

This paper studies context bisimulation for higher-order processes, in the presence of parameterization (viz. abstraction). We show that the extension of higher-order processes with process parameterization retains the characterization of…

This paper presents a new technique for creating monolingual and cross-lingual meta-embeddings. Our method integrates multiple word embeddings created from complementary techniques, textual sources, knowledge bases and languages. Existing…

Despite the impressive growth of the abilities of multilingual language models, such as XLM-R and mT5, it has been shown that they still face difficulties when tackling typologically-distant languages, particularly in the low-resource…

With the fast development of natural language processing, recent advances in information hiding focus on covertly embedding secret information into texts. These algorithms either modify a given cover text or directly generate a text…

Cross-lingual word vectors are typically obtained by fitting an orthogonal matrix that maps the entries of a bilingual dictionary from a source to a target vector space. Word vectors, however, are most commonly used for sentence or…

The paraphrase identification task involves measuring semantic similarity between two short sentences. It is a tricky task, and multilingual paraphrase identification is even more challenging. In this work, we train a bi-encoder model in a…

Variational inequalities are an important tool, which includes minimization, saddles, games, fixed-point problems. Modern large-scale and computationally expensive practical applications make distributed methods for solving these problems…