Related papers: Top-P Masking for Cross Language Information Retri…

Decoding sits between a language model and everything we do with it, yet it is still treated as a heuristic knob-tuning exercise. We argue decoding should be understood as a principled optimisation layer: at each token, we solve a…

Information retrieval (IR) is essential in search engines and dialogue systems as well as natural language processing tasks such as open-domain question answering. IR serve an important function in the biomedical domain, where content and…

Reranking is a critical stage in contemporary information retrieval (IR) systems, improving the relevance of the user-presented final results by honing initial candidate sets. This paper is a thorough guide to examine the changing reranker…

To better support retrieval applications such as web search and question answering, growing effort is made to develop retrieval-oriented language models. Most of the existing works focus on improving the semantic representation capability…

Video-and-language pre-training has shown promising results for learning generalizable representations. Most existing approaches usually model video and text in an implicit manner, without considering explicit structural representations of…

With a good code search engine, developers can reuse existing code snippets and accelerate software development process. Current code search methods can be divided into two categories: traditional information retrieval (IR) based and deep…

Unsupervised large-scale vision-language pre-training has shown promising advances on various downstream tasks. Existing methods often model the cross-modal interaction either via the similarity of the global feature of each modality which…

Accurate detection of colorectal cancer and early prevention heavily rely on precise polyp identification during gastrointestinal colonoscopy. Due to limited data, many current state-of-the-art deep learning methods for polyp segmentation…

One of the important factors that affects the performance of Cross Language Information Retrieval(CLIR)is the quality of translations being employed in CLIR. In order to improve the quality of translations, it is important to exploit…

Recently, the centerline has become a popular representation of lanes due to its advantages in solving the road topology problem. To enhance centerline prediction, we have developed a new approach called TopoMask. Unlike previous methods…

Knowledge graphs and large language models (LLMs) are key tools for biomedical knowledge integration and reasoning, facilitating structured organization of scientific articles and discovery of complex semantic relationships. However,…

Large Language Models (LLMs) have significantly impacted many facets of natural language processing and information retrieval. Unlike previous encoder-based approaches, the enlarged context window of these generative models allows for…

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,…

Although more and more language pairs are covered by machine translation services, there are still many pairs that lack translation resources. Cross-language information retrieval (CLIR) is an application which needs translation…

Multiple instance learning (MIL) was a weakly supervised learning approach that sought to assign binary class labels to collections of instances known as bags. However, due to their weak supervision nature, the MIL methods were susceptible…

The SPLADE (SParse Lexical AnD Expansion) model is a highly effective approach to learned sparse retrieval, where documents are represented by term impact scores derived from large language models. During training, SPLADE applies…

CLIP (Contrastive Language-Image Pre-training) uses contrastive learning from noise image-text pairs to excel at recognizing a wide array of candidates, yet its focus on broad associations hinders the precision in distinguishing subtle…

Cascade ranking is a widely adopted paradigm in large-scale information retrieval systems for Top-K item selection. However, the Top-K operator is non-differentiable, hindering end-to-end training. Existing methods include Learning-to-Rank…

Sparse document representations have been widely used to retrieve relevant documents via exact lexical matching. Owing to the pre-computed inverted index, it supports fast ad-hoc search but incurs the vocabulary mismatch problem. Although…

We present DR.DECR (Dense Retrieval with Distillation-Enhanced Cross-Lingual Representation), a new cross-lingual information retrieval (CLIR) system trained using multi-stage knowledge distillation (KD). The teacher of DR.DECR relies on a…