Related papers: E2Rank: Your Text Embedding can Also be an Effecti…

This paper presents preliminary works on using Word Embedding (word2vec) for query expansion in the context of Personalized Information Retrieval. Traditionally, word embeddings are learned on a general corpus, like Wikipedia. In this work…

Reranking documents based on their relevance to a given query is a critical task in information retrieval. Traditional reranking methods often lack transparency and rely on proprietary models, hindering reproducibility and interpretability.…

LLMs confront inherent limitations in terms of its knowledge, memory, and action. The retrieval augmentation stands as a vital mechanism to address these limitations, which brings in useful information from external sources to augment the…

Embedders play a central role in machine learning, projecting any object into numerical representations that can, in turn, be leveraged to perform various downstream tasks. The evaluation of embedding models typically depends on…

Embedding-based retrieval (EBR) is a technique to use embeddings to represent query and document, and then convert the retrieval problem into a nearest neighbor search problem in the embedding space. Some previous works have mainly focused…

This paper introduces RETSim (Resilient and Efficient Text Similarity), a lightweight, multilingual deep learning model trained to produce robust metric embeddings for near-duplicate text retrieval, clustering, and dataset deduplication…

We present Regularized Linear Embedding (RLE), a novel method that projects a collection of linked documents (e.g. citation network) into a pretrained word embedding space. In addition to the textual content, we leverage a matrix of…

Text embeddings are useful features in many applications such as semantic search and computing text similarity. Previous work typically trains models customized for different use cases, varying in dataset choice, training objective and…

Text embeddings are typically evaluated on a limited set of tasks, which are constrained by language, domain, and task diversity. To address these limitations and provide a more comprehensive evaluation, we introduce the Massive…

Millions of repetitive code snippets are submitted to code repositories every day. To search from these large codebases using simple natural language queries would allow programmers to ideate, prototype, and develop easier and faster.…

Text embedding models enable semantic search, powering several NLP applications like Retrieval Augmented Generation by efficient information retrieval (IR). However, text embedding models are commonly studied in scenarios where the training…

Recent information retrieval (IR) models are pre-trained and instruction-tuned on massive datasets and tasks, enabling them to perform well on a wide range of tasks and potentially generalize to unseen tasks with instructions. However,…

Job descriptions are posted on many online channels, including company websites, job boards or social media platforms. These descriptions are usually published with varying text for the same job, due to the requirements of each platform or…

To support complex search tasks, where the initial information requirements are complex or may change during the search, a search engine must adapt the information delivery as the user's information requirements evolve. To support this…

Cross-Encoder (CE) and Dual-Encoder (DE) models are two fundamental approaches for query-document relevance in information retrieval. To predict relevance, CE models use joint query-document embeddings, while DE models maintain factorized…

This paper presents E5, a family of state-of-the-art text embeddings that transfer well to a wide range of tasks. The model is trained in a contrastive manner with weak supervision signals from our curated large-scale text pair dataset…

Large Language Models (LLMs) have demonstrated exceptional performance in the task of text ranking for information retrieval. While Pointwise ranking approaches offer computational efficiency by scoring documents independently, they often…

Owing to the rapidly growing multimedia content available on the Internet, extractive spoken document summarization, with the purpose of automatically selecting a set of representative sentences from a spoken document to concisely express…

Large Language Models (LLMs) have demonstrated superior listwise ranking performance. However, their superior performance often relies on large-scale parameters (\eg, GPT-4) and a repetitive sliding window process, which introduces…

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…