Related papers: BM25 Query Augmentation Learned End-to-End

Naively trained neural networks tend to experience catastrophic forgetting in sequential task settings, where data from previous tasks are unavailable. A number of methods, using various model expansion strategies, have been proposed…

Structured sparsity has emerged as a popular model pruning technique, widely adopted in various architectures, including CNNs, Transformer models, and especially large language models (LLMs) in recent years. A promising direction to further…

We define a novel concept called extended word alignment in order to improve post-editing assistance efficiency. Based on extended word alignment, we further propose a novel task called refined word-level QE that outputs refined tags and…

Newly-introduced deep learning architectures, namely BERT, XLNet, RoBERTa and ALBERT, have been proved to be robust on several NLP tasks. However, the datasets trained on these architectures are fixed in terms of size and generalizability.…

Self-supervised learning has become a popular approach in recent years for its ability to learn meaningful representations without the need for data annotation. This paper proposes a novel image augmentation technique, overlaying images,…

Multimodal Large Language Models (MLLMs) struggle with continual learning, often suffering from catastrophic forgetting when adapting to sequential tasks. We introduce a routing-based architecture that integrates new capabilities while…

Query expansion has been widely used to improve the search results of first-stage retrievers, yet its influence on second-stage, cross-encoder rankers remains under-explored. A recent work of Weller et al. [44] shows that current expansion…

The rapid progress in machine learning methods has been empowered by i) huge datasets that have been collected and annotated, ii) improved engineering (e.g. data pre-processing/normalization). The existing datasets typically include several…

This paper introduces a lightweight deep learning model for real-time speech enhancement, designed to operate efficiently on resource-constrained devices. The proposed model leverages a compact architecture that facilitates rapid inference…

Federated Learning (FL) endeavors to harness decentralized data while preserving privacy, facing challenges of performance, scalability, and collaboration. Asynchronous Federated Learning (AFL) methods have emerged as promising alternatives…

Effective Question Answering (QA) on large biomedical document collections requires effective document retrieval techniques. The latter remains a challenging task due to the domain-specific vocabulary and semantic ambiguity in user queries.…

Pretrained large language models (LLMs) are currently state-of-the-art for solving the vast majority of natural language processing tasks. While many real-world applications still require fine-tuning to reach satisfactory levels of…

The visual signal compression is a long-standing problem. Fueled by the recent advances of deep learning, exciting progress has been made. Despite better compression performance, existing end-to-end compression algorithms are still designed…

Recently embedding-based retrieval or dense retrieval have shown state of the art results, compared with traditional sparse or bag-of-words based approaches. This paper introduces a model-agnostic doc-level embedding framework through large…

Reinforcement learning is a popular machine learning paradigm which can find near optimal solutions to complex problems. Most often, these procedures involve function approximation using neural networks with gradient based updates to…

Reranking is fundamental to information retrieval and retrieval-augmented generation, with recent Large Language Models (LLMs) significantly advancing reranking quality. Most current works rely on large-scale LLMs (>7B parameters),…

Motivated by recent evidence pointing out the fragility of high-performing span prediction models, we direct our attention to multiple choice reading comprehension. In particular, this work introduces a novel method for improving answer…

Today, the dominant paradigm for training neural networks involves minimizing task loss on a large dataset. Using world knowledge to inform a model, and yet retain the ability to perform end-to-end training remains an open question. In this…

Pre-trained language models (PLMs) have proven to be effective for document re-ranking task. However, they lack the ability to fully interpret the semantics of biomedical and health-care queries and often rely on simplistic patterns for…

Recently, token-level adaptive training has achieved promising improvement in machine translation, where the cross-entropy loss function is adjusted by assigning different training weights to different tokens, in order to alleviate the…