Related papers: Tradutor: Building a Variety Specific Translation …

Language models based on the Transformer architecture have achieved state-of-the-art performance on a wide range of NLP tasks such as text classification, question-answering, and token classification. However, this performance is usually…

Language barriers in scientific documents hinder the diffusion and development of science and technologies. However, prior efforts in translating such documents largely overlooked the information in layouts. To bridge the gap, we introduce…

Sense representations have gone beyond word representations like Word2Vec, GloVe and FastText and achieved innovative performance on a wide range of natural language processing tasks. Although very useful in many applications, the…

An all-too-present bottleneck for text classification model development is the need to annotate training data and this need is multiplied for multilingual classifiers. Fortunately, contemporary machine translation models are both easily…

Personalized dialogue systems are an essential step toward better human-machine interaction. Existing personalized dialogue agents rely on properly designed conversational datasets, which are mostly monolingual (e.g., English), which…

With the resurgence of chat-based dialog systems in consumer and enterprise applications, there has been much success in developing data-driven and rule-based natural language models to understand human intent. Since these models require…

Recent advancements in large language models have demonstrated remarkable capabilities across various NLP tasks. But many questions remain, including whether open-source models match closed ones, why these models excel or struggle with…

Recent studies show that large language models (LLMs) are powerful tools for working with natural language, bringing advances in many areas of computational linguistics. However, these models face challenges when applied to low-resource…

English has long been assumed the $\textit{lingua franca}$ of scientific research, and this notion is reflected in the natural language processing (NLP) research involving scientific document representation. In this position piece, we…

Recent advances in training multilingual language models on large datasets seem to have shown promising results in knowledge transfer across languages and achieve high performance on downstream tasks. However, we question to what extent the…

Most existing models for multilingual natural language processing (NLP) treat language as a discrete category, and make predictions for either one language or the other. In contrast, we propose using continuous vector representations of…

Discriminative translation models utilizing source context have been shown to help statistical machine translation performance. We propose a novel extension of this work using target context information. Surprisingly, we show that this…

Recently proposed data collection frameworks for endangered language documentation aim not only to collect speech in the language of interest, but also to collect translations into a high-resource language that will render the collected…

Spreadsheets provide a flexible and easy to use software development environment, but that leads to error proneness. Work has been done to prevent errors in spreadsheets, including using models to specify distinct parts of a spreadsheet as…

While large language models (LLMs) show transformative potential in healthcare, their development remains focused on high-resource languages. This creates a critical barrier for other languages, as simple translation fails to capture unique…

Many multilingual NLP applications need to translate words between different languages, but cannot afford the computational expense of inducing or applying a full translation model. For these applications, we have designed a fast algorithm…

Despite advances in the multilingual capabilities of Large Language Models (LLMs) across diverse tasks, English remains the dominant language for LLM research and development. So, when working with a different language, this has led to the…

An acoustic model, trained on a significant amount of unlabeled data, consists of a self-supervised learned speech representation useful for solving downstream tasks, perhaps after a fine-tuning of the model in the respective downstream…

Large language models (LLMs) are demonstrably capable of cross-lingual transfer, but can produce inconsistent output when prompted with the same queries written in different languages. To understand how language models are able to…

Achieving universal translation between all human language pairs is the holy-grail of machine translation (MT) research. While recent progress in massively multilingual MT is one step closer to reaching this goal, it is becoming evident…