Related papers: Model and Evaluation: Towards Fairness in Multilin…

Contrastive learning is among the most successful methods for visual representation learning, and its performance can be further improved by jointly performing clustering on the learned representations. However, existing methods for joint…

Current advances in Natural Language Processing (NLP) have made it increasingly feasible to build applications leveraging textual data. Generally, the core of these applications rely on having a good semantic representation of text into…

Autoregressive language models are widely used for text evaluation, however, their left-to-right factorization introduces positional bias, i.e., early tokens are scored with only leftward context, conflating architectural asymmetry with…

Multilingual representations embed words from many languages into a single semantic space such that words with similar meanings are close to each other regardless of the language. These embeddings have been widely used in various settings,…

Large pre-trained language models contain societal biases and carry along these biases to downstream tasks. Current in-processing bias mitigation approaches (like adversarial training) impose debiasing by updating a model's parameters,…

Current ophthalmology clinical workflows are plagued by over-referrals, long waits, and complex and heterogeneous medical records. Large language models (LLMs) present a promising solution to automate various procedures such as triaging,…

The focus of this thesis is broadly on the alignment of lexicographical data, particularly dictionaries. In order to tackle some of the challenges in this field, two main tasks of word sense alignment and translation inference are…

We propose an unsupervised method to obtain cross-lingual embeddings without any parallel data or pre-trained word embeddings. The proposed model, which we call multilingual neural language models, takes sentences of multiple languages as…

Multilingual speech-text models rely on cross-modal language alignment to transfer knowledge between speech and text, but it remains unclear whether this reflects shared computation for the same language or modality-specific processing. We…

Research on adversarial robustness in language models is currently fragmented across applications and attacks, obscuring shared vulnerabilities. In this work, we propose unifying the study of adversarial robustness in text scoring models…

Recent generative large language models (LLMs) show remarkable performance in non-English languages, but when prompted in those languages they tend to express higher harmful social biases and toxicity levels. Prior work has shown that…

Pre-trained Large Language Models (LLMs) have significantly advanced natural language processing capabilities but are susceptible to biases present in their training data, leading to unfair outcomes in various applications. While numerous…

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…

Recent progress on unsupervised learning of cross-lingual embeddings in bilingual setting has given impetus to learning a shared embedding space for several languages without any supervision. A popular framework to solve the latter problem…

Existing studies have investigated the tendency of autoregressive language models to generate contexts that exhibit undesired biases and toxicity. Various debiasing approaches have been proposed, which are primarily categorized into…

Multimodal foundation models aim to create a unified representation space that abstracts away from surface features like language syntax or modality differences. To investigate this, we study the internal representations of three recent…

Automatic speech recognition (ASR) has benefited from advances in pretrained speech and language models, yet most systems remain constrained to monolingual settings and short, isolated utterances. While recent efforts in context-aware ASR…

Sparse language vectors from linguistic typology databases and learned embeddings from tasks like multilingual machine translation have been investigated in isolation, without analysing how they could benefit from each other's language…

Large language models (LLMs) have become a standard for multilingual evaluation, yet they exhibit a severe systematic translationese bias. In this paper, translationese bias is characterized as LLMs systematically favoring…

Multi-Label Text Classification (MLTC) is a practical yet challenging task that involves assigning multiple non-exclusive labels to each document. Previous studies primarily focus on capturing label correlations to assist label prediction…