English
Related papers

Related papers: Pre-training Tasks for Embedding-based Large-scale…

200 papers

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…

Information Retrieval · Computer Science 2025-10-07 Dipam Goswami , Liying Wang , Bartłomiej Twardowski , Joost van de Weijer

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…

Information Retrieval · Computer Science 2021-11-30 Sheng-Chieh Lin , Jheng-Hong Yang , Jimmy Lin

Retrieval augmentation has become an effective solution to empower large language models (LLMs) with external and verified knowledge sources from the database, which overcomes the limitations and hallucinations of LLMs in handling…

Information Retrieval · Computer Science 2023-11-21 Tong Wu , Yulei Qin , Enwei Zhang , Zihan Xu , Yuting Gao , Ke Li , Xing Sun

This paper studies the fast adaptive beamforming for the multiuser multiple-input single-output downlink. Existing deep learning-based approaches assume that training and testing channels follow the same distribution which causes task…

Information Theory · Computer Science 2021-09-21 Juping Zhang , Yi Yuan , Gan Zheng , Ioannis Krikidis , Kai-Kit Wong

Designing pre-training objectives that more closely resemble the downstream tasks for pre-trained language models can lead to better performance at the fine-tuning stage, especially in the ad-hoc retrieval area. Existing pre-training…

Information Retrieval · Computer Science 2021-08-24 Zhengyi Ma , Zhicheng Dou , Wei Xu , Xinyu Zhang , Hao Jiang , Zhao Cao , Ji-Rong Wen

Learning a high-dimensional dense representation for vocabulary terms, also known as a word embedding, has recently attracted much attention in natural language processing and information retrieval tasks. The embedding vectors are typically…

Information Retrieval · Computer Science 2017-07-18 Hamed Zamani , W. Bruce Croft

On a wide range of natural language processing and information retrieval tasks, transformer-based models, particularly pre-trained language models like BERT, have demonstrated tremendous effectiveness. Due to the quadratic complexity of the…

Information Retrieval · Computer Science 2022-10-18 Minghan Li , Diana Nicoleta Popa , Johan Chagnon , Yagmur Gizem Cinar , Eric Gaussier

Embeddings extracted by pre-trained Large Language Models (LLMs) have significant potential to improve information retrieval and search. Beyond the zero-shot setup in which they are being conventionally used, being able to take advantage of…

Machine Learning · Computer Science 2024-08-26 Jinsung Yoon , Sercan O Arik , Yanfei Chen , Tomas Pfister

This paper introduces a deep learning model tailored for document information analysis, emphasizing document classification, entity relation extraction, and document visual question answering. The proposed model leverages transformer-based…

Computer Vision and Pattern Recognition · Computer Science 2023-10-26 Tofik Ali , Partha Pratim Roy

Retrieval-augmented language models (LMs) have received much attention recently. However, typically the retriever is not trained jointly as a native component of the LM, but added post-hoc to an already-pretrained LM, which limits the…

Computation and Language · Computer Science 2024-07-23 Ohad Rubin , Jonathan Berant

Text embedding models serve as a fundamental component in real-world search applications. By mapping queries and documents into a shared embedding space, they deliver competitive retrieval performance with high efficiency. However, their…

Computation and Language · Computer Science 2025-11-03 Qi Liu , Yanzhao Zhang , Mingxin Li , Dingkun Long , Pengjun Xie , Jiaxin Mao

The Insertion Transformer is well suited for long form text generation due to its parallel generation capabilities, requiring $O(\log_2 n)$ generation steps to generate $n$ tokens. However, modeling long sequences is difficult, as there is…

Computation and Language · Computer Science 2019-10-30 Lala Li , William Chan

Two step document ranking, where the initial retrieval is done by a classical information retrieval method, followed by neural re-ranking model, is the new standard. The best performance is achieved by using transformer-based models as…

Information Retrieval · Computer Science 2020-09-22 Ivan Sekulić , Amir Soleimani , Mohammad Aliannejadi , Fabio Crestani

This paper addresses the gap between general-purpose text embeddings and the specific demands of item retrieval tasks. We demonstrate the shortcomings of existing models in capturing the nuances necessary for zero-shot performance on item…

Information Retrieval · Computer Science 2024-03-01 Yuxuan Lei , Jianxun Lian , Jing Yao , Mingqi Wu , Defu Lian , Xing Xie

Intermediate task fine-tuning has been shown to culminate in large transfer gains across many NLP tasks. With an abundance of candidate datasets as well as pre-trained language models, it has become infeasible to run the cross-product of…

Computation and Language · Computer Science 2021-09-13 Clifton Poth , Jonas Pfeiffer , Andreas Rücklé , Iryna Gurevych

Language models can be viewed as functions that embed text into Euclidean space, where the quality of the embedding vectors directly determines model performance, training such neural networks involves various uncertainties. This paper…

Computation and Language · Computer Science 2025-03-31 Yifei Duan , Raphael Shang , Deng Liang , Yongqiang Cai

The quality of machine learning models depends heavily on their training data. Selecting high-quality, diverse training sets for large language models (LLMs) is a difficult task, due to the lack of cheap and reliable quality metrics. While…

Machine Learning · Computer Science 2026-01-30 Robert Istvan Busa-Fekete , Julian Zimmert , Anne Xiangyi Zheng , Claudio Gentile , Andras Gyorgy

Modern large language models (LLMs) excel at tasks that require storing and retrieving knowledge, such as factual recall and question answering. Transformers are central to this capability because they can encode information during training…

Machine Learning · Statistics 2026-03-18 Nuri Mert Vural , Alberto Bietti , Mahdi Soltanolkotabi , Denny Wu

Recent works show that learning contextualized embeddings for words is beneficial for downstream tasks. BERT is one successful example of this approach. It learns embeddings by solving two tasks, which are masked language model (masked LM)…

Computation and Language · Computer Science 2020-11-10 Çağla Aksoy , Alper Ahmetoğlu , Tunga Güngör

Publications in the life sciences are characterized by a large technical vocabulary, with many lexical and semantic variations for expressing the same concept. Towards addressing the problem of relevance in biomedical literature search, we…

Information Retrieval · Computer Science 2018-03-01 Sunil Mohan , Nicolas Fiorini , Sun Kim , Zhiyong Lu