Related papers: ListConRanker: A Contrastive Text Reranker with Li…

Current state-of-the-art approaches to cross-modal retrieval process text and visual input jointly, relying on Transformer-based architectures with cross-attention mechanisms that attend over all words and objects in an image. While…

Recent advancements in information retrieval have highlighted the potential of integrating visual and textual information, yet effective reranking for image-text documents remains challenging due to the modality gap and scarcity of aligned…

Optimizing reranking in advertising feeds is a constrained combinatorial problem, requiring simultaneous maximization of platform revenue and preservation of user experience. Recent generative ranking methods enable listwise optimization…

Dense retrieval has shown promising results in many information retrieval (IR) related tasks, whose foundation is high-quality text representation learning for effective search. Some recent studies have shown that autoencoder-based language…

The cross-entropy objective has proved to be an all-purpose training objective for autoregressive language models (LMs). However, without considering the penalization of problematic tokens, LMs trained using cross-entropy exhibit text…

Semantic search is an important task which objective is to find the relevant index from a database for query. It requires a retrieval model that can properly learn the semantics of sentences. Transformer-based models are widely used as…

Recently, substantial progress has been made in text ranking based on pretrained language models such as BERT. However, there are limited studies on how to leverage more powerful sequence-to-sequence models such as T5. Existing attempts…

In passage retrieval system, the initial passage retrieval results may be unsatisfactory, which can be refined by a reranking scheme. Existing solutions to passage reranking focus on enriching the interaction between query and each passage…

Context, the embedding of previous collected trajectories, is a powerful construct for Meta-Reinforcement Learning (Meta-RL) algorithms. By conditioning on an effective context, Meta-RL policies can easily generalize to new tasks within a…

There is extensive interest in metric learning methods for image retrieval. Many metric learning loss functions focus on learning a correct ranking of training samples, but strongly overfit semantically inconsistent labels and require a…

In this paper we propose a novel approach for combining first-stage lexical retrieval models and Transformer-based re-rankers: we inject the relevance score of the lexical model as a token in the middle of the input of the cross-encoder…

Text reranking models are a crucial component in modern systems like Retrieval-Augmented Generation, tasked with selecting the most relevant documents prior to generation. However, current Large Language Models (LLMs) powered rerankers…

Conventional research on large language models (LLMs) has primarily focused on refining output distributions, while paying less attention to the decoding process that transforms these distributions into final responses. Recent advances,…

State-of-the-art Machine Reading Comprehension (MRC) models for Open-domain Question Answering (QA) are typically trained for span selection using distantly supervised positive examples and heuristically retrieved negative examples. This…

Meta-reinforcement learning typically requires orders of magnitude more samples than single task reinforcement learning methods. This is because meta-training needs to deal with more diverse distributions and train extra components such as…

Semantic representation learning for sentences is an important and well-studied problem in NLP. The current trend for this task involves training a Transformer-based sentence encoder through a contrastive objective with text, i.e.,…

In monolingual dense retrieval, lots of works focus on how to distill knowledge from cross-encoder re-ranker to dual-encoder retriever and these methods achieve better performance due to the effectiveness of cross-encoder re-ranker.…

State-of-the-art neural models typically encode document-query pairs using cross-attention for re-ranking. To this end, models generally utilize an encoder-only (like BERT) paradigm or an encoder-decoder (like T5) approach. These paradigms,…

Web applications where users are presented with a limited selection of items have long employed ranking models to put the most relevant results first. Any feedback received from users is typically assumed to reflect a relative judgement on…

Generative retrieval models encode pointers to information in a corpus as an index within the model's parameters. These models serve as part of a larger pipeline, where retrieved information conditions generation for knowledge-intensive NLP…