Related papers: Recall, Expand and Multi-Candidate Cross-Encode: F…

Referring Expression Comprehension (REC) is a foundational cross-modal task that evaluates the interplay of language understanding, image comprehension, and language-to-image grounding. It serves as an essential testing ground for…

Textual noise, such as typos or abbreviations, is a well-known issue that penalizes vanilla Transformers for most downstream tasks. We show that this is also the case for sentence similarity, a fundamental task in multiple domains, e.g.…

End-to-end automatic speech recognition systems often fail to transcribe domain-specific named entities, causing catastrophic failures in downstream tasks. Numerous fast and lightweight named entity correction (NEC) models have been…

This paper presents an efficient speech enhancement (SE) approach that reuses a processing block repeatedly instead of conventional stacking. Rather than increasing the number of blocks for learning deep latent representations, repeating a…

Most efforts to improve the reasoning capabilities of large language models (LLMs) involve either scaling the number of parameters and the size of training data, or scaling inference computation by letting models generate complex chains of…

This paper explores learning rich self-supervised entity representations from large amounts of the associated text. Once pre-trained, these models become applicable to multiple entity-centric tasks such as ranked retrieval, knowledge base…

Contextualised word embeddings is a powerful tool to detect contextual synonyms. However, most of the current state-of-the-art (SOTA) deep learning concept extraction methods remain supervised and underexploit the potential of the context.…

Machine learning models are widely used in real-world applications. However, their complexity makes it often challenging to interpret the rationale behind their decisions. Counterfactual explanations (CEs) have emerged as a viable solution…

Fine-grained entity typing aims to assign entity mentions in the free text with types arranged in a hierarchical structure. Traditional distant supervision based methods employ a structured data source as a weak supervision and do not need…

Document-level event extraction (DEE) faces two main challenges: arguments-scattering and multi-event. Although previous methods attempt to address these challenges, they overlook the interference of event-unrelated sentences during event…

Recent reasoning Large Language Models (LLMs) demonstrate remarkable problem-solving abilities but often generate long thinking traces whose utility is unclear. Our work aims to improve their efficiency, enabling them to reach high…

Named entity recognition (NER) is highly sensitive to sentential syntactic and semantic properties where entities may be extracted according to how they are used and placed in the running text. To model such properties, one could rely on…

It is common that entity mentions can contain other mentions recursively. This paper introduces a scalable transition-based method to model the nested structure of mentions. We first map a sentence with nested mentions to a designated…

A typical architecture for end-to-end entity linking systems consists of three steps: mention detection, candidate generation and entity disambiguation. In this study we investigate the following questions: (a) Can all those steps be…

Entity Linking (EL) has traditionally relied on large annotated datasets and extensive model fine-tuning. While recent few-shot methods leverage large language models (LLMs) through prompting to reduce training requirements, they often…

Large language models often fail on multi-step reasoning due to fixed reasoning strategies that ignore problem specific difficulty. We introduce CARD (Complexity Agnostic Recursive Decomposition), a framework that predicts problem…

Large-scale source-code clone detection is a challenging task. In our previous work, we proposed an approach (SSCD) that leverages artificial neural networks and approximates nearest neighbour search to effectively and efficiently locate…

As an effective approach to tune pre-trained language models (PLMs) for specific tasks, prompt-learning has recently attracted much attention from researchers. By using \textit{cloze}-style language prompts to stimulate the versatile…

Transformer-based text classifiers such as BERT, RoBERTa, T5, and GPT have shown strong performance in natural language processing tasks but remain vulnerable to adversarial examples. These vulnerabilities raise significant security…

Composed image retrieval aims to find an image that best matches a given multi-modal user query consisting of a reference image and text pair. Existing methods commonly pre-compute image embeddings over the entire corpus and compare these…