Related papers: On Single and Multiple Representations in Dense Pa…

Dense Retrieval (DR) models have proven to be effective for Document Retrieval and Information Grounding tasks. Usually, these models are trained and optimized for improving the relevance of top-ranked documents for a given query. Previous…

Recent large language models (LLMs) have demonstrated exceptional performance on general-purpose text embedding tasks. While dense embeddings have dominated related research, we introduce the first lexicon-based embeddings (LENS) leveraging…

Multimodal representations that enable cross-modal retrieval are widely used. However, these often lack interpretability making it difficult to explain the retrieved results. Solutions such as learning sparse disentangled representations…

Recently, various studies have been directed towards exploring dense passage retrieval techniques employing pre-trained language models, among which the masked auto-encoder (MAE) pre-training architecture has emerged as the most promising.…

Recent progress in Natural Language Understanding (NLU) is driving fast-paced advances in Information Retrieval (IR), largely owed to fine-tuning deep language models (LMs) for document ranking. While remarkably effective, the ranking…

Recently, pre-trained contextual models, such as BERT, have shown to perform well in language related tasks. We revisit the design decisions that govern the applicability of these models for the passage re-ranking task in open-domain…

The application of Deep Neural Networks for ranking in search engines may obviate the need for the extensive feature engineering common to current learning-to-rank methods. However, we show that combining simple relevance matching features…

In this paper, we present our approaches for the case law retrieval and the legal case entailment task in the Competition on Legal Information Extraction/Entailment (COLIEE) 2021. As first stage retrieval methods combined with neural…

Similar question retrieval is a core task in community-based question answering (CQA) services. To balance the effectiveness and efficiency, the question retrieval system is typically implemented as multi-stage rankers: The first-stage…

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…

Recently embedding-based retrieval or dense retrieval have shown state of the art results, compared with traditional sparse or bag-of-words based approaches. This paper introduces a model-agnostic doc-level embedding framework through large…

Recently, dense passage retrieval has become a mainstream approach to finding relevant information in various natural language processing tasks. A number of studies have been devoted to improving the widely adopted dual-encoder…

Dense Retrieval (DR) reaches state-of-the-art results in first-stage retrieval, but little is known about the mechanisms that contribute to its success. Therefore, in this work, we conduct an interpretation study of recently proposed DR…

Embedding-based retrieval aims to learn a shared semantic representation space for both queries and items, enabling efficient and effective item retrieval through approximate nearest neighbor (ANN) algorithms. In current industrial…

A common retrieve-and-rerank paradigm involves retrieving relevant candidates from a broad set using a fast bi-encoder (BE), followed by applying expensive but accurate cross-encoders (CE) to a limited candidate set. However, relying on…

With the rapid growth of the scientific literature, manually selecting appropriate citations for a paper is becoming increasingly challenging and time-consuming. While several approaches for automated citation recommendation have been…

Conversational search supports multi-turn user-system interactions to solve complex information needs. Different from the traditional single-turn ad-hoc search, conversational search encounters a more challenging problem of…

Distantly supervised relation extraction intrinsically suffers from noisy labels due to the strong assumption of distant supervision. Most prior works adopt a selective attention mechanism over sentences in a bag to denoise from wrongly…

Pretrained contextual and non-contextual subword embeddings have become available in over 250 languages, allowing massively multilingual NLP. However, while there is no dearth of pretrained embeddings, the distinct lack of systematic…

Dense retrieval is becoming one of the standard approaches for document and passage ranking. The dual-encoder architecture is widely adopted for scoring question-passage pairs due to its efficiency and high performance. Typically, dense…