Related papers: SSE: Multimodal Semantic Data Selection and Enrich…
Large Language Models have significantly advanced the field of code generation, demonstrating the ability to produce functionally correct code snippets. However, advancements in generative AI for code overlook foundational Software…
Speech Emotion Recognition (SER) presents a significant yet persistent challenge in human-computer interaction. While deep learning has advanced spoken language processing, achieving high performance on limited datasets remains a critical…
Unstructured text has long been difficult to automatically analyze at scale. Large language models (LLMs) now offer a way forward by enabling {\em semantic data processing}, where familiar data processing operators (e.g., map, reduce,…
Event extraction (EE) is a fundamental task in natural language processing (NLP) that involves identifying and extracting event information from unstructured text. Effective EE in real-world scenarios requires two key steps: selecting…
It is commonly acknowledged that the availability of the huge amount of (training) data is one of the most important factors for many recent advances in Artificial Intelligence (AI). However, datasets are often designed for specific tasks…
Text data augmentation, i.e., the creation of new textual data from an existing text, is challenging. Indeed, augmentation transformations should take into account language complexity while being relevant to the target Natural Language…
Self-supervised learning (SSL) has been able to leverage unlabeled data to boost the performance of automatic speech recognition (ASR) models when we have access to only a small amount of transcribed speech data. However, this raises the…
Recently, significant progress has been made on semantic segmentation. However, the success of supervised semantic segmentation typically relies on a large amount of labelled data, which is time-consuming and costly to obtain. Inspired by…
This paper proposes to address the word sense ambiguity issue in an unsupervised manner, where word sense representations are learned along a word sense selection mechanism given contexts. Prior work focused on designing a single model to…
Joint Entity and Relation Extraction (JERE) is highly sensitive to training data quality, making data augmentation a natural way to improve generalization. However, existing augmentation methods often weaken entity relevance and disrupt…
This work introduces VERSE, a methodology for analyzing and improving Vision-Language Models applied to Visually-rich Document Understanding by exploring their visual embedding space. VERSE enables the visualization of latent…
When designing robots to assist in everyday human activities, it is crucial to enhance user requests with visual cues from their surroundings for improved intent understanding. This process is defined as a multimodal classification task.…
Recent advances in machine learning have significantly impacted the field of information extraction, with Language Models (LMs) playing a pivotal role in extracting structured information from unstructured text. Prior works typically…
Selecting high-quality and diverse training samples from extensive datasets plays a crucial role in reducing training overhead and enhancing the performance of Large Language Models (LLMs). However, existing studies fall short in assessing…
Scalable and accurate identification of specific clinical outcomes has been enabled by machine-learning applied to electronic medical record (EMR) systems. The development of classification models requires the collection of a complete…
Speaker extraction (SE) aims to segregate the speech of a target speaker from a mixture of interfering speakers with the help of auxiliary information. Several forms of auxiliary information have been employed in single-channel SE, such as…
Integrating Artificial Intelligence into Software Engineering (SE) requires having a curated collection of models suited to SE tasks. With millions of models hosted on Hugging Face (HF) and new ones continuously being created, it is…
Speech emotion recognition (SER) plays a crucial role in human-computer interaction. The emergence of edge devices in the Internet of Things (IoT) presents challenges in constructing intricate deep learning models due to constraints in…
Active event perception, the ability to dynamically detect, track, and summarize events in real time, is essential for embodied intelligence in tasks such as human-AI collaboration, assistive robotics, and autonomous navigation. However,…
Cross-lingual Speech Emotion Recognition (CLSER) aims to identify emotional states in unseen languages. However, existing methods heavily rely on the semantic synchrony of complete labels and static feature stability, hindering low-resource…