Related papers: Pyserini: An Easy-to-Use Python Toolkit to Support…
To extract answers from a large corpus, open-domain question answering (QA) systems usually rely on information retrieval (IR) techniques to narrow the search space. Standard inverted index methods such as TF-IDF are commonly used as thanks…
Deep research systems represent an emerging class of agentic information retrieval methods that generate comprehensive and well-supported reports to complex queries. However, most existing frameworks rely on dynamic commercial search APIs,…
Dual-encoder-based dense retrieval models have become the standard in IR. They employ large Transformer-based language models, which are notoriously inefficient in terms of resources and latency. We propose Fast-Forward indexes -- vector…
Human perceptual studies are the gold standard for the evaluation of many research tasks in machine learning, linguistics, and psychology. However, these studies require significant time and cost to perform. As a result, many researchers…
In recent years, the extraction of opinions and information from user-generated text has attracted a lot of interest, largely due to the unprecedented volume of content in Social Media. However, social researchers face some issues in…
This technical report details a novel approach to combining reasoning and retrieval augmented generation (RAG) within a single, lean language model architecture. While existing RAG systems typically rely on large-scale models and external…
Semantic segmentation empowers numerous real-world applications, such as autonomous driving and augmented/mixed reality. These applications often operate on high-resolution images (e.g., 8 megapixels) to capture the fine details. However,…
Recent developments of dense retrieval rely on quality representations of queries and contexts from pre-trained query and context encoders. In this paper, we introduce TOUR (Test-Time Optimization of Query Representations), which further…
Tensors are higher-order extensions of matrices. While matrix methods form the cornerstone of machine learning and data analysis, tensor methods have been gaining increasing traction. However, software support for tensor operations is not…
The semantic matching capabilities of neural information retrieval can ameliorate synonymy and polysemy problems of symbolic approaches. However, neural models' dense representations are more suitable for re-ranking, due to their…
Balancing predictive power and interpretability has long been a challenging research area, particularly in powerful yet complex models like neural networks, where nonlinearity obstructs direct interpretation. This paper introduces a novel…
Many interesting data sets available on the Internet are of a medium size---too big to fit into a personal computer's memory, but not so large that they won't fit comfortably on its hard disk. In the coming years, data sets of this…
Recent progress in deep learning has continuously improved the accuracy of dialogue response selection. In particular, sophisticated neural network architectures are leveraged to capture the rich interactions between dialogue context and…
Existing dense retrieval models struggle with reasoning-intensive retrieval task as they fail to capture implicit relevance that requires reasoning beyond surface-level semantic information. To address these challenges, we propose…
Image restoration (IR) aims to recover high-quality images from degraded inputs, with recent deep learning advancements significantly enhancing performance. However, existing methods lack a unified training benchmark for iterations and…
Multimodal representations that enable cross-modal retrieval are widely used. However, these often lack interpretability making it difficult to explain the retrieved results. Solutions such as learning sparse disentangled representations…
Our objective is to introduce to the NLP community an existing k-NN search library NMSLIB, a new retrieval toolkit FlexNeuART, as well as their integration capabilities. NMSLIB, while being one the fastest k-NN search libraries, is quite…
Learned sparse text embeddings have gained popularity due to their effectiveness in top-k retrieval and inherent interpretability. Their distributional idiosyncrasies, however, have long hindered their use in real-world retrieval systems.…
A novel representation of images for image retrieval is introduced in this paper, by using a new type of feature with remarkable discriminative power. Despite the multi-scale nature of objects, most existing models perform feature…
Research Agents enable models to gather information from the web using tools to answer user queries, requiring them to dynamically interleave internal reasoning with tool use. While such capabilities can in principle be learned via…