Related papers: Efficient Title Reranker for Fast and Improved Kno…

The goal of natural language semantic code search is to retrieve a semantically relevant code snippet from a fixed set of candidates using a natural language query. Existing approaches are neither effective nor efficient enough towards a…

Multimodal document retrieval systems enable information access across text, images, and layouts, benefiting various domains like document-based question answering, report analysis, and interactive content summarization. Rerankers improve…

Active learning, a widely adopted technique for enhancing machine learning models in text and image classification tasks with limited annotation resources, has received relatively little attention in the domain of Named Entity Recognition…

Retrieval-Augmented Generation (RAG) has emerged as a standard framework for knowledge-intensive NLP tasks, combining large language models (LLMs) with document retrieval from external corpora. Despite its widespread use, most RAG pipelines…

Retrieval-augmented methods have received increasing attention to support downstream tasks by leveraging useful information from external resources. Recent studies mainly focus on exploring retrieval to solve knowledge-intensive (KI) tasks.…

Search engines play an important role in our everyday lives by assisting us in finding the information we need. When we input a complex query, however, results are often far from satisfactory. In this work, we introduce a query…

It is a challenging and practical research problem to obtain effective compression of lengthy product titles for E-commerce. This is particularly important as more and more users browse mobile E-commerce apps and more merchants make the…

The CLIP model has established itself as a cornerstone of large-scale retrieval systems. However, its performance often degrades under distributional shifts such as multilingual, long-form, or multimodal queries. To avoid the prohibitive…

Transformer-based NLP models are powerful but have high computational costs that limit deployment. Finetuned encoder-decoder models are popular in specialized domains and can outperform larger more generalized decoder-only models, such as…

Recent work in zero-shot listwise reranking using LLMs has achieved state-of-the-art results. However, these methods are not without drawbacks. The proposed methods rely on large LLMs with billions of parameters and limited context sizes.…

Retrieval-Augmented Generation (RAG) depends on document ranking to provide useful evidence for generation, but conventional reranking methods mainly optimize query-document relevance rather than generation usefulness. A relevant document…

As demonstrated by GPT-3 and T5, transformers grow in capability as parameter spaces become larger and larger. However, for tasks that require a large amount of knowledge, non-parametric memory allows models to grow dramatically with a…

The Transformer-Kernel (TK) model has demonstrated strong reranking performance on the TREC Deep Learning benchmark---and can be considered to be an efficient (but slightly less effective) alternative to BERT-based ranking models. In this…

Conducting literature reviews for scientific papers is essential for understanding research, its limitations, and building on existing work. It is a tedious task which makes an automatic literature review generator appealing. Unfortunately,…

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…

Motivation: Despite recent advancements in semantic representation driven by pre-trained and large-scale language models, addressing long tail challenges in multi-label text classification remains a significant issue. Long tail challenges…

Large language models (LLMs), with advanced linguistic capabilities, have been employed in reranking tasks through a sequence-to-sequence approach. In this paradigm, multiple passages are reranked in a listwise manner and a textual reranked…

This paper reports on a study of cross-lingual information retrieval (CLIR) using the mT5-XXL reranker on the NeuCLIR track of TREC 2022. Perhaps the biggest contribution of this study is the finding that despite the mT5 model being…

Large Language Models (LLMs) face significant challenges in specialized domains like law, where precision and domain-specific knowledge are critical. This paper presents a streamlined two-stage framework consisting of Retrieval and…

Deep Neural Networks (DNNs) typically require massive amount of computation resource in inference tasks for computer vision applications. Quantization can significantly reduce DNN computation and storage by decreasing the bitwidth of…