Related papers: Top-P Masking for Cross Language Information Retri…
Learned Sparse Retrieval (LSR) models encode text as weighted term vectors, which need to be sparse to leverage inverted index structures during retrieval. SPLADE, the most popular LSR model, uses FLOPS regularization to encourage vector…
This paper explores a novel technique for improving recall in cross-language information retrieval (CLIR) systems using iterative query refinement grounded in the user's lexical-semantic space. The proposed methodology combines multi-level…
Federated learning (FL) is a novel machine learning setting that enables on-device intelligence via decentralized training and federated optimization. Deep neural networks' rapid development facilitates the learning techniques for modeling…
We propose a scheme for multi-layer representation of images. The problem is first treated from an information-theoretic viewpoint where we analyze the behavior of different sources of information under a multi-layer data compression…
The advent of multilingual language models has generated a resurgence of interest in cross-lingual information retrieval (CLIR), which is the task of searching documents in one language with queries from another. However, the rapid pace of…
As long-context inference becomes central to large language models (LLMs), attention over growing key-value caches emerges as a dominant decoding bottleneck, motivating sparse attention for scalable inference. Fixed-budget top-k sparse…
Cross-language information retrieval (CLIR), where queries and documents are in different languages, has of late become one of the major topics within the information retrieval community. This paper proposes a Japanese/English CLIR system,…
Deep representation learning has become one of the most widely adopted approaches for visual search, recommendation, and identification. Retrieval of such representations from a large database is however computationally challenging.…
Expansion-enhanced sparse lexical representation improves information retrieval (IR) by minimizing vocabulary mismatch problems during lexical matching. In this paper, we explore the potential of jointly learning dense semantic…
Specialist language models (LMs) focus on a specific task or domain on which they often outperform generalist LMs of the same size. However, the specialist data needed to pretrain these models is only available in limited amount for most…
Top-$k$ decoding is a widely used method for sampling from LLMs: at each token, only the largest $k$ next-token-probabilities are kept, and the next token is sampled after re-normalizing them to sum to unity. Top-$k$ and other sampling…
In this paper, we rethink sparse lexical representations for image retrieval. By utilizing multi-modal large language models (M-LLMs) that support visual prompting, we can extract image features and convert them into textual data, enabling…
The main issue in Cross Language Information Retrieval (CLIR) is the poor performance of retrieval in terms of average precision when compared to monolingual retrieval performance. The main reasons behind poor performance of CLIR are…
This paper proposes an image interpolation algorithm exploiting sparse representation for natural images. It involves three main steps: (a) obtaining an initial estimate of the high resolution image using linear methods like FIR filtering,…
Reinforcement learning (RL) has garnered increasing attention in text-to-image (T2I) generation. However, most existing RL approaches are tailored to either diffusion models or autoregressive models, overlooking an important alternative:…
Two key assumptions shape the usual view of ranked retrieval: (1) that the searcher can choose words for their query that might appear in the documents that they wish to see, and (2) that ranking retrieved documents will suffice because the…
Diffusion language models are a promising alternative to autoregressive models due to their potential for faster generation. Among discrete diffusion approaches, Masked diffusion currently dominates, largely driven by strong perplexity on…
Retriever-reader models achieve competitive performance across many different NLP tasks such as open question answering and dialogue conversations. In this work, we notice these models easily overfit the top-rank retrieval passages and…
We propose a novel framework for image clustering that incorporates joint representation learning and clustering. Our method consists of two heads that share the same backbone network - a "representation learning" head and a "clustering"…
Information Retrieval (IR) is an important application area of Natural Language Processing (NLP) where one encounters the genuine challenge of processing large quantities of unrestricted natural language text. While much effort has been…