Related papers: CODER: An efficient framework for improving retrie…
Dense encoders and LLM-based rerankers struggle with long documents: single-vector representations dilute fine-grained relevance, while cross-encoders are often too expensive for practical reranking. We present an efficient long-document…
Despite the advantages of their low-resource settings, traditional sparse retrievers depend on exact matching approaches between high-dimensional bag-of-words (BoW) representations of both the queries and the collection. As a result,…
Dense retrieval, which encodes queries and documents into a single dense vector, has become the dominant neural retrieval approach due to its simplicity and compatibility with fast approximate nearest neighbor algorithms. As the tasks dense…
Deep language models learning a hierarchical representation proved to be a powerful tool for natural language processing, text mining and information retrieval. However, representations that perform well for retrieval must capture semantic…
Although exact term match between queries and documents is the dominant method to perform first-stage retrieval, we propose a different approach, called RepBERT, to represent documents and queries with fixed-length contextualized…
In this paper, we propose a dictionary screening method for embedding compression in text classification tasks. The key purpose of this method is to evaluate the importance of each keyword in the dictionary. To this end, we first train a…
Web search provides a promising way for people to obtain information and has been extensively studied. With the surgence of deep learning and large-scale pre-training techniques, various neural information retrieval models are proposed and…
Passage reranking is a critical task in various applications, particularly when dealing with large volumes of documents. Existing neural architectures have limitations in retrieving the most relevant passage for a given question because the…
Reranking, the process of refining the output of a first-stage retriever, is often considered computationally expensive, especially with Large Language Models. Borrowing from recent advances in document compression for RAG, we reduce the…
Reranking, the process of refining the output from a first-stage retriever, is often considered computationally expensive, especially when using Large Language Models (LLMs). A common approach to mitigate this cost involves utilizing…
Generative retrieval employs sequence models for conditional generation of document IDs based on a query (DSI (Tay et al., 2022); NCI (Wang et al., 2022); inter alia). While this has led to improved performance in zero-shot retrieval, it is…
In this paper, we investigate the in-context learning ability of retrieval-augmented encoder-decoder language models. We first conduct a comprehensive analysis of existing models and identify their limitations in in-context learning,…
Effective conversational search demands a deep understanding of user intent across multiple dialogue turns. Users frequently use abbreviations and shift topics in the middle of conversations, posing challenges for conventional retrievers.…
Pre-trained transformer-based models have recently shown great performance when applied to Named Entity Recognition (NER). As the complexity of their self-attention mechanism prevents them from processing long documents at once, these…
Pseudo-relevance feedback mechanisms, from Rocchio to the relevance models, have shown the usefulness of expanding and reweighting the users' initial queries using information occurring in an initial set of retrieved documents, known as the…
We propose a new context-aware correlation filter based tracking framework to achieve both high computational speed and state-of-the-art performance among real-time trackers. The major contribution to the high computational speed lies in…
A ranker plays an indispensable role in the de facto 'retrieval & rerank' pipeline, but its training still lags behind -- learning from moderate negatives or/and serving as an auxiliary module for a retriever. In this work, we first…
Accurately retrieving relevant bid keywords for user queries is critical in Sponsored Search but remains challenging, particularly for short, ambiguous queries. Existing dense and generative retrieval models often fail to capture nuanced…
Neural information retrieval systems typically use a cascading pipeline, in which a first-stage model retrieves a candidate set of documents and one or more subsequent stages re-rank this set using contextualized language models such as…
Neural ranking models are traditionally trained on a series of random batches, sampled uniformly from the entire training set. Curriculum learning has recently been shown to improve neural models' effectiveness by sampling batches…