Related papers: Salient Span Masking for Temporal Understanding

Many natural language processing (NLP) tasks involve reasoning with textual spans, including question answering, entity recognition, and coreference resolution. While extensive research has focused on functional architectures for…

Recovering the masked speech frames is widely applied in speech representation learning. However, most of these models use random masking in the pre-training. In this work, we proposed two kinds of masking approaches: (1) speech-level…

Continuous-time state-space models (SSMs) are flexible tools for analysing irregularly sampled sequential observations that are driven by an underlying state process. Corresponding applications typically involve restrictive assumptions…

Longitudinal passive sensing enables continuous health prediction, yet models often fail under cross-dataset distribution shifts. Traditional ML overfits cohort-specific artifacts, while Large Language Models (LLMs) struggle to reason…

A common and effective way to train translation systems between related languages is to consider sub-word level basic units. However, this increases the length of the sentences resulting in increased decoding time. The increase in length is…

In the recent trend of semi-supervised speech recognition, both self-supervised representation learning and pseudo-labeling have shown promising results. In this paper, we propose a novel approach to combine their ideas for end-to-end…

Considering the large amount of content created online by the minute, slang-aware automatic tools are critically needed to promote social good, and assist policymakers and moderators in restricting the spread of offensive language, abuse,…

Semantic Parsing aims to capture the meaning of a sentence and convert it into a logical, structured form. Previous studies show that semantic parsing enhances the performance of smaller models (e.g., BERT) on downstream tasks. However, it…

Temporal sentence grounding in videos aims to detect and localize one target video segment, which semantically corresponds to a given sentence. Existing methods mainly tackle this task via matching and aligning semantics between a sentence…

Recently, Language Models (LMs) instruction-tuned on multiple tasks, also known as multitask-prompted fine-tuning (MT), have shown the capability to generalize to unseen tasks. Previous work has shown that scaling the number of training…

Large language models (LLMs) have achieved state-of-the-art performance in various language processing tasks, motivating their adoption in simultaneous translation. Current fine-tuning methods to adapt LLMs for simultaneous translation…

The explosive growth in video streaming requires video understanding at high accuracy and low computation cost. Conventional 2D CNNs are computationally cheap but cannot capture temporal relationships; 3D CNN-based methods can achieve good…

Self-Supervised Learning is vastly used to efficiently represent speech for Spoken Language Understanding, gradually replacing conventional approaches. Meanwhile, textual SSL models are proposed to encode language-agnostic semantics.…

There is a growing need for pluralistic alignment methods that can steer language models towards individual attributes and preferences. One such method, Self-Supervised Alignment with Mutual Information (SAMI), uses conditional mutual…

We propose a Long Short-Term Memory (LSTM) with attention mechanism to classify psychological stress from self-conducted interview transcriptions. We apply distant supervision by automatically labeling tweets based on their hashtag content,…

Multimodal Large Language Models (MLLMs) have demonstrated outstanding performance across a variety of domains. However, training MLLMs is often inefficient, as much of the computation is redundant due to the long input sequences from…

A recent line of research on automated speaking assessment (ASA) has benefited from self-supervised learning (SSL) representations, which capture rich acoustic and linguistic patterns in non-native speech without underlying assumptions of…

We propose a novel task-agnostic in-domain pre-training method that sits between generic pre-training and fine-tuning. Our approach selectively masks in-domain keywords, i.e., words that provide a compact representation of the target…

Topic segmentation is important in understanding scientific documents since it can not only provide better readability but also facilitate downstream tasks such as information retrieval and question answering by creating appropriate…

Semi-supervised learning (SSL) is a popular setting aiming to effectively utilize unlabelled data to improve model performance in downstream natural language processing (NLP) tasks. Currently, there are two popular approaches to make use of…