Related papers: Ensembling Transformers for Cross-domain Automatic…

Pretrained language models are now ubiquitous in Natural Language Processing. Despite their success, most available models have either been trained on English data or on the concatenation of data in multiple languages. This makes practical…

State-of-the-art multilingual machine translation relies on a universal encoder-decoder, which requires retraining the entire system to add new languages. In this paper, we propose an alternative approach that is based on language-specific…

This paper is devoted to the extraction of entities and semantic relations between them from scientific texts, where we consider scientific terms as entities. In this paper, we present a dataset that includes annotations for two tasks and…

Pronouns are a long-standing challenge in machine translation. We present a study of the performance of a range of rule-based, statistical and neural MT systems on pronoun translation based on an extensive manual evaluation using the…

Code-switching (CS) occurs when a speaker alternates words of two or more languages within a single sentence or across sentences. Automatic speech recognition (ASR) of CS speech has to deal with two or more languages at the same time. In…

The overreliance on large parallel corpora significantly limits the applicability of machine translation systems to the majority of language pairs. Back-translation has been dominantly used in previous approaches for unsupervised neural…

Transformer-based language models have achieved remarkable success in few-shot in-context learning and drawn a lot of research interest. However, these models' performance greatly depends on the choice of the example prompts and also has…

Representation learning is an essential problem in a wide range of applications and it is important for performing downstream tasks successfully. In this paper, we propose a new model that learns coupled representations of domains, intents,…

There are several approaches for improving neural machine translation for low-resource languages: Monolingual data can be exploited via pretraining or data augmentation; Parallel corpora on related language pairs can be used via parameter…

State-of-the-art multilingual models depend on vocabularies that cover all of the languages the model will expect to see at inference time, but the standard methods for generating those vocabularies are not ideal for massively multilingual…

In this article, we present the BTransformer18 model, a deep learning architecture designed for multi-label relation extraction in French texts. Our approach combines the contextual representation capabilities of pre-trained language models…

Pre-trained word embeddings are the primary method for transfer learning in several Natural Language Processing (NLP) tasks. Recent works have focused on using unsupervised techniques such as language modeling to obtain these embeddings. In…

Dense retrieval models using a transformer-based bi-encoder design have emerged as an active area of research. In this work, we focus on the task of monolingual retrieval in a variety of typologically diverse languages using one such…

In this paper, we present a novel multi-channel speech extraction system to simultaneously extract multiple clean individual sources from a mixture in noisy and reverberant environments. The proposed method is built on an improved…

We present an approach to neural machine translation (NMT) that supports multiple domains in a single model and allows switching between the domains when translating. The core idea is to treat text domains as distinct languages and use…

Monolingual data has been demonstrated to be helpful in improving the translation quality of neural machine translation (NMT). The current methods stay at the usage of word-level knowledge, such as generating synthetic parallel data or…

Sociodemographic factors (e.g., gender or age) shape our language. Previous work showed that incorporating specific sociodemographic factors can consistently improve performance for various NLP tasks in traditional NLP models. We…

Many NLP applications require models to be interpretable. However, many successful neural architectures, including transformers, still lack effective interpretation methods. A possible solution could rely on building explanations from…

Unsupervised spoken term discovery consists of two tasks: finding the acoustic segment boundaries and labeling acoustically similar segments with the same labels. We perform segmentation based on the assumption that the frame feature…

We address the problem of tuning word embeddings for specific use cases and domains. We propose a new method that automatically combines multiple domain-specific embeddings, selected from a wide range of pre-trained domain-specific…