Related papers: Learning Passage Impacts for Inverted Indexes

Text classification is a fundamental language task in Natural Language Processing. A variety of sequential models is capable making good predictions yet there is lack of connection between language semantics and prediction results. This…

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…

In a number of information retrieval applications (e.g., patent search, literature review, due diligence, etc.), preventing false negatives is more important than preventing false positives. However, approaches designed to reduce review…

This paper describes a compact and effective model for low-latency passage retrieval in conversational search based on learned dense representations. Prior to our work, the state-of-the-art approach uses a multi-stage pipeline comprising…

Representation learning is a critical ingredient for natural language processing systems. Recent Transformer language models like BERT learn powerful textual representations, but these models are targeted towards token- and sentence-level…

Neural document ranking approaches, specifically transformer models, have achieved impressive gains in ranking performance. However, query processing using such over-parameterized models is both resource and time intensive. In this paper,…

Deep research has emerged as an important task that aims to address hard queries through extensive open-web exploration. To tackle it, most prior work equips large language model (LLM)-based agents with opaque web search APIs, enabling…

Although considerable efforts have been devoted to transformer-based ranking models for document search, the relevance-efficiency tradeoff remains a critical problem for ad-hoc ranking. To overcome this challenge, this paper presents BECR…

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…

Interactive search can provide a better experience by incorporating interaction feedback from the users. This can significantly improve search accuracy as it helps avoid irrelevant information and captures the users' search intents.…

Recent research has shown that mixed-initiative conversational search, based on the interaction between users and computers to clarify and improve a query, provides enormous advantages. Nonetheless, incorporating additional information…

The massive upload of text on the internet creates a huge inverted index in information retrieval systems, which hurts their efficiency. The purpose of this research is to measure the effect of the Multi-Layer Similarity model of the…

Pre-trained language models like BERT have achieved great success in a wide variety of NLP tasks, while the superior performance comes with high demand in computational resources, which hinders the application in low-latency IR systems. We…

Multiple neural language models have been developed recently, e.g., BERT and XLNet, and achieved impressive results in various NLP tasks including sentence classification, question answering and document ranking. In this paper, we explore…

Traditional information retrieval systems rely on keywords to index documents and queries. In such systems, documents are retrieved based on the number of shared keywords with the query. This lexical-focused retrieval leads to inaccurate…

Many recent approaches towards neural information retrieval mitigate their computational costs by using a multi-stage ranking pipeline. In the first stage, a number of potentially relevant candidates are retrieved using an efficient…

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…

The classical, vector space model for text retrieval is shown to give better results (up to 29% better in our experiments) if WordNet synsets are chosen as the indexing space, instead of word forms. This result is obtained for a manually…

Common document ranking pipelines in search systems are cascade systems that involve multiple ranking layers to integrate different information step-by-step. In this paper, we propose a novel re-ranker Fusion-in-T5 (FiT5), which integrates…

Search result diversification is a beneficial approach to overcome under-specified queries, such as those that are ambiguous or multi-faceted. Existing approaches often rely on massive query logs and interaction data to generate a variety…