Publications

Foundation models (FMs) learn from large volumes of unlabeled data to demonstrate superior performance across a wide range of tasks. However, FMs developed for biomedical domains have largely remained unimodal, i.e., independently trained and used for tasks on protein sequences alone, small-molecule structures alone, or clinical data alone. To overcome this limitation, we present BioBRIDGE, a parameter-efficient

Recent developments in active learning algorithms for NLP tasks show promising results in terms of reducing labelling complexity. In this paper we extend this effort to imbalanced datasets; we bridge between the active learning approach of obtaining diverse and informative examples, and the heuristic of class balancing used in imbalanced datasets. We develop a novel tune-free weighting technique that can

Voice conversion (VC) systems are widely used for several applications, from speaker anonymisation to personalised speech synthesis. Supervised approaches learn a mapping between different speakers using parallel data, which is expensive to produce. Un-supervised approaches are typically trained to reconstruct the in-put signal, which is composed of the content and the speaker in-formation. Disentangling

Cross-triggering is a critical problem for applications of audio event detection (AED), particularly in low-resource settings. However, not much attention (if not none) has been paid to this problem in the AED research community. In this work, we tackle this problem via a regularization approach. We propose a regularizer, namely mutual exclusivity regularizer, that is able to enforce pairwise exclusivity

We introduce a text-to-speech (TTS) model called BASE TTS, which stands for Big Adaptive Streamable TTS with Emergent abilities. BASE TTS is the largest TTS model to-date, trained on 100K hours of public domain speech data, achieving a new state-of-the-art in speech naturalness. It deploys a 1-billion- parameter autoregressive Transformer that converts raw texts into discrete codes ("speechcodes") followed

Products on e-commerce websites are usually organized based on seller-provided product attributes. Customers looking for a product typically have certain needs or product use-cases in mind, for e.g., a headphone for gym classes, or a printer for a small business. However, they often struggle to map these use-cases to product attributes and subsequently fail to find the product they need. In this talk, we

It has been shown that post-quantum key exchange and authentication with ML-KEM and ML-DSA, NIST’s postquantum algorithm picks, will have an impact on TLS 1.3 performance used in the Web or other applications. Studies so far have focused on the overhead of quantum-resistant algorithms on TLS time-to-first-byte (handshake time). Although these works have been important in quantifying the slowdown in connection

Large language models (LLMs) have shown remarkable generalization capability with exceptional performance in various language modeling tasks. However, they still exhibit inherent limitations in precisely capturing and returning grounded knowledge. While existing work has explored utilizing knowledge graphs (KGs) to enhance language modeling via joint training and customized model architectures, applying

Keyphrase extraction is the task of identifying a set of keyphrases present in a document that captures its most salient topics. Scientific domain-specific pre-training has led to achieving state-of-the-art keyphrase extraction performance with a majority of benchmarks being within the domain. In this work, we explore how to effectively enable the cross-domain generalization capabilities of such models

One interesting approach to Question Answering (QA) is to search for semantically similar questions, which have been answered before. This task is different from answer retrieval as it focuses on questions rather than only on the answers, therefore it requires different model training on different data. In this work, we introduce a novel unsupervised pre-training method specialized for retrieving and ranking

We explore how weak supervision on abundant unlabeled data can be leveraged to improve few-shot performance in aspect-based sentiment analysis (ABSA) tasks. We propose a pipeline approach to construct a noisy ABSA dataset, and we use it to adapt a pre-trained sequence-to-sequence model to the ABSA tasks. We test the resulting model on three widely used ABSA datasets, before and after fine-tuning. Our pro-posed

Product returns are an increasing environmental problem, as an estimated 25% of returned products end up as landfill [10]. Returns are expensive for retailers as well, and it is estimated that 15-40% of all online purchases are returned [34]. The problem could be mitigated by identifying issues with a product that are likely to lead to its return, before many have sold. Understanding and predicting return

Text classification is an important problem with a wide range of applications in NLP. However, naturally occurring data is imbalanced which can induce biases when training classification models. In this work, we introduce a novel contrastive learning (CL) approach to help with imbalanced text classification task. CL has an inherent structure which pushes similar data closer in embedding space and vice versa

We introduce flexibility to the supervised learning-based speech enhancement framework to achieve scalable and efficient speech enhancement (SESE). To this end, SESE conducts a series of segmented speech enhancement inference routines, each of which incrementally improves the result of its preceding inference. The formulation is conceptually similar to cold diffusion, while we modify the sampling process

Computing the optimal transport distance between statistical distributions is a fundamental task in machine learning. One remarkable recent advancement is en- tropic regularization and the Sinkhorn algorithm, which utilizes only matrix scaling and guarantees an approximated solution with near-linear runtime. Despite the success of the Sinkhorn algorithm, its runtime may still be slow due to the potentially