相关论文: PLAID SHIRTTT for Large-Scale Streaming Dense Retr…

Cross-Encoder (CE) and Dual-Encoder (DE) models are two fundamental approaches for query-document relevance in information retrieval. To predict relevance, CE models use joint query-document embeddings, while DE models maintain factorized…

For online speaker diarization, samples arrive incrementally, and the overall distribution of the samples is invisible. Moreover, in most existing clustering-based methods, the training objective of the embedding extractor is not designed…

While recent research advances in speaker diarization mostly focus on improving the quality of diarization results, there is also an increasing interest in improving the efficiency of diarization systems. In this paper, we demonstrate that…

Neural information retrieval systems excel in high-resource languages but remain underexplored for morphologically rich, lower-resource languages such as Turkish. Dense bi-encoders currently dominate Turkish IR, yet late-interaction models…

Measuring advances in retrieval requires test collections with relevance judgments that can faithfully distinguish systems. This paper presents NeuCLIRTech, an evaluation collection for cross-language retrieval over technical information.…

Traditionally, sparse retrieval systems relied on lexical representations to retrieve documents, such as BM25, dominated information retrieval tasks. With the onset of pre-trained transformer models such as BERT, neural sparse retrieval has…

Recent progress in neural information retrieval has demonstrated large gains in effectiveness, while often sacrificing the efficiency and interpretability of the neural model compared to classical approaches. This paper proposes ColBERTer,…

Although Transformers have successfully transitioned from their language modelling origins to image-based applications, their quadratic computational complexity remains a challenge, particularly for dense prediction. In this paper we…

Scientific simulations and experimental measurements produce vast amounts of spatio-temporal data, yet extracting meaningful insights remains challenging due to high dimensionality, complex structures, and missing information. Traditional…

We study serving retrieval models, specifically late interaction models like ColBERT, to many concurrent users at once and under a small budget, in which the index may not fit in memory. We present ColBERT-serve, a novel serving system that…

Instruction tuning is essential for aligning large language models (LLMs) to downstream tasks and commonly relies on large, diverse corpora. However, small, high-quality subsets, known as coresets, can deliver comparable or superior…

In-context learning (ICL) has emerged as a powerful paradigm for Large Visual Language Models (LVLMs), enabling them to leverage a few examples directly from input contexts. However, the effectiveness of this approach is heavily reliant on…

This paper summarizes our approaches submitted to the case law retrieval task in the Competition on Legal Information Extraction/Entailment (COLIEE) 2022. Our methodology consists of four steps; in detail, given a legal case as a query, we…

Exploiting information induced from (query-specific) clustering of top-retrieved documents has long been proposed as a means for improving precision at the very top ranks of the returned results. We present a novel language model approach…

As Large Language Models (LLMs) scale to million-token contexts, traditional Mechanistic Interpretability techniques for analyzing attention scale quadratically with context length, demanding terabytes of memory beyond 100,000 tokens. We…

This study addresses the challenge of improving dense retrieval performance for queries containing numerical conditions, such as ``companies with more than one billion dollars in R&D expenditure.'' Although recent research has shown that…

In the era of large language models (LLMs), supervised neural methods remain the state-of-the-art (SOTA) for Coreference Resolution. Yet, their full potential is underexplored, particularly in incremental clustering, which faces the…

Text clustering is an important method for organising the increasing volume of digital content, aiding in the structuring and discovery of hidden patterns in uncategorised data. The effectiveness of text clustering largely depends on the…

Large-scale text retrieval technology has been widely used in various practical business scenarios. This paper presents our systems for the TREC 2022 Deep Learning Track. We explain the hybrid text retrieval and multi-stage text ranking…

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…