Related papers: Tradutor: Building a Variety Specific Translation …
Multiword expressions, characterised by non-compositional meanings and syntactic irregularities, are an example of nuanced language. These expressions can be used literally or idiomatically, leading to significant changes in meaning. While…
In this work, we investigate methods for the challenging task of translating between low-resource language pairs that exhibit some level of similarity. In particular, we consider the utility of transfer learning for translating between…
In this paper we propose a study of linguistic portability strategies of large pre-trained language models (PLMs) used for open-domain dialogue systems in a high-resource language for this task. In particular the target low-resource…
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…
Translations systematically diverge from texts originally produced in the target language, a phenomenon widely referred to as translationese. Translationese has been attributed to production tendencies (e.g. interference, simplification),…
Parallel texts (bitexts) have properties that distinguish them from other kinds of parallel data. First, most words translate to only one other word. Second, bitext correspondence is noisy. This article presents methods for biasing…
The paper argues the importance of high-quality translation for spoken language translation systems. It describes an architecture suitable for rapid development of high-quality limited-domain translation systems, which has been implemented…
In this paper we share findings from our effort to build practical machine translation (MT) systems capable of translating across over one thousand languages. We describe results in three research domains: (i) Building clean, web-mined…
Mixture models trained via EM are among the simplest, most widely used and well understood latent variable models in the machine learning literature. Surprisingly, these models have been hardly explored in text generation applications such…
We investigate transfer learning based on pre-trained neural machine translation models to translate between (low-resource) similar languages. This work is part of our contribution to the WMT 2021 Similar Languages Translation Shared Task…
Most work in NLP makes the assumption that it is desirable to develop solutions in the native language in question. There is consequently a strong trend towards building native language models even for low-resource languages. This paper…
The rapid proliferation of LLMs has created a critical evaluation paradox: while LLMs claim multilingual proficiency, comprehensive non-machine-translated benchmarks exist for fewer than 30 languages, leaving >98% of the world's 7,000…
Large Language Models (LLMs) exhibit significant variations in performance across linguistic and cultural contexts, underscoring the need for systematic evaluation in diverse languages. In this work, we present the most extensive evaluation…
Despite the widespread adoption of deep learning for machine translation, it is still expensive to develop high-quality translation models. In this work, we investigate the use of pre-trained models, such as T5 for Portuguese-English and…
Discourse parsing is an integral part of understanding information flow and argumentative structure in documents. Most previous research has focused on inducing and evaluating models from the English RST Discourse Treebank. However,…
Taking advantage of computationally lightweight, but high-quality translators prompt consideration of new applications that address neglected languages. Locally run translators for less popular languages may assist data projects with…
The use of large language models (LLMs) for complex mathematical reasoning is an emergent area of research, with fast progress in methods, models, and benchmark datasets. However, most mathematical reasoning evaluations exhibit a…
We investigate how large language models perform on low-resource languages by benchmarking eight LLMs across five experimental conditions in English, Kazakh, and Mongolian. Using 50 hand-crafted questions spanning factual, reasoning,…
Translations often carry traces of the source language, a phenomenon known as translationese. We introduce the first freely available English-to-Swedish dataset contrasting translationese sentences with idiomatic alternatives, designed to…
We present Tucano 2, a fully open suite of large language models (LLMs) with 0.5-3.7 billion parameters, designed to address certain gaps in open-source development for Portuguese LLMs. Following our previous works, we now extend our…