English
Related papers

Related papers: Less is More: Pre-train a Strong Text Encoder for …

200 papers

Unsupervised text embeddings extraction is crucial for text understanding in machine learning. Word2Vec and its variants have received substantial success in mapping words with similar syntactic or semantic meaning to vectors close to each…

Computation and Language · Computer Science 2018-05-30 Furong Huang , Animashree Anandkumar

Dense retrieval has shown promise in the first-stage retrieval process when trained on in-domain labeled datasets. However, previous studies have found that dense retrieval is hard to generalize to unseen domains due to its weak modeling of…

Information Retrieval · Computer Science 2023-05-19 Shicheng Xu , Liang Pang , Huawei Shen , Xueqi Cheng

In dense retrieval, deep encoders provide embeddings for both inputs and targets, and the softmax function is used to parameterize a distribution over a large number of candidate targets (e.g., textual passages for information retrieval).…

Machine Learning · Computer Science 2024-09-04 Nicholas Monath , Will Grathwohl , Michael Boratko , Rob Fergus , Andrew McCallum , Manzil Zaheer

Many deep neural networks are susceptible to minute perturbations of images that have been carefully crafted to cause misclassification. Ideally, a robust classifier would be immune to small variations in input images, and a number of…

Computer Vision and Pattern Recognition · Computer Science 2022-02-08 Eashan Adhikarla , Dan Luo , Brian D. Davison

Open-domain extractive question answering works well on textual data by first retrieving candidate texts and then extracting the answer from those candidates. However, some questions cannot be answered by text alone but require information…

Computation and Language · Computer Science 2021-10-20 Bogdan Kostić , Julian Risch , Timo Möller

Large pre-trained vision-language models have shown great prominence in transferring pre-acquired knowledge to various domains and downstream tasks with appropriate prompting or tuning. Existing prevalent tuning methods can be generally…

Computer Vision and Pattern Recognition · Computer Science 2023-05-31 Huahui Yi , Ziyuan Qin , Wei Xu , Miaotian Guo , Kun Wang , Shaoting Zhang , Kang Li , Qicheng Lao

Representation learning for text via pretraining a language model on a large corpus has become a standard starting point for building NLP systems. This approach stands in contrast to autoencoders, also trained on raw text, but with the…

Computation and Language · Computer Science 2021-09-14 Ivan Montero , Nikolaos Pappas , Noah A. Smith

We introduce ART, a new corpus-level autoencoding approach for training dense retrieval models that does not require any labeled training data. Dense retrieval is a central challenge for open-domain tasks, such as Open QA, where…

Computation and Language · Computer Science 2023-04-04 Devendra Singh Sachan , Mike Lewis , Dani Yogatama , Luke Zettlemoyer , Joelle Pineau , Manzil Zaheer

Dense retrieval models use bi-encoder network architectures for learning query and document representations. These representations are often in the form of a vector representation and their similarities are often computed using the dot…

Information Retrieval · Computer Science 2023-05-01 Hamed Zamani , Michael Bendersky

Large decoder-only language models (LMs) can be largely improved in terms of perplexity by retrieval (e.g., RETRO), but its impact on text generation quality and downstream task accuracy is unclear. Thus, it is still an open question: shall…

Computation and Language · Computer Science 2023-12-22 Boxin Wang , Wei Ping , Peng Xu , Lawrence McAfee , Zihan Liu , Mohammad Shoeybi , Yi Dong , Oleksii Kuchaiev , Bo Li , Chaowei Xiao , Anima Anandkumar , Bryan Catanzaro

In this paper, we propose a new dense retrieval model which learns diverse document representations with deep query interactions. Our model encodes each document with a set of generated pseudo-queries to get query-informed, multi-view…

Information Retrieval · Computer Science 2022-08-09 Zehan Li , Nan Yang , Liang Wang , Furu Wei

Autoencoders are commonly trained using element-wise loss. However, element-wise loss disregards high-level structures in the image which can lead to embeddings that disregard them as well. A recent improvement to autoencoders that helps…

Computer Vision and Pattern Recognition · Computer Science 2020-04-06 Gustav Grund Pihlgren , Fredrik Sandin , Marcus Liwicki

Speculative decoding (SD) accelerates Large Language Model (LLM) generation by using an efficient draft model to propose the next few tokens, which are verified by the LLM in a single forward call, reducing latency while preserving its…

Computation and Language · Computer Science 2025-05-30 Milan Gritta , Huiyin Xue , Gerasimos Lampouras

Sparse autoencoders (SAEs) provide a powerful mechanism for decomposing the dense representations produced by Large Language Models (LLMs) into interpretable latent features. We posit that SAEs constitute a natural foundation for Learned…

Machine Learning · Computer Science 2026-03-17 Thibault Formal , Maxime Louis , Hervé Dejean , Stéphane Clinchant

Autoencoders are commonly used in representation learning. They consist of an encoder and a decoder, which provide a straightforward way to map n-dimensional data in input space to a lower m-dimensional representation space and back. The…

Machine Learning · Computer Science 2021-11-16 Viktoria Schuster , Anders Krogh

Deep neural networks are gaining increasing popularity for the classic text classification task, due to their strong expressive power and less requirement for feature engineering. Despite such attractiveness, neural text classification…

Information Retrieval · Computer Science 2018-09-13 Yu Meng , Jiaming Shen , Chao Zhang , Jiawei Han

Weakly-supervised anomaly detection aims at learning an anomaly detector from a limited amount of labeled data and abundant unlabeled data. Recent works build deep neural networks for anomaly detection by discriminatively mapping the normal…

Machine Learning · Computer Science 2021-08-29 Yingjie Zhou , Xucheng Song , Yanru Zhang , Fanxing Liu , Ce Zhu , Lingqiao Liu

We discuss the similarities and differences between training an auto-encoder to minimize the reconstruction error, and training the same auto-encoder to compress the data via a generative model. Minimizing a codelength for the data using an…

Neural and Evolutionary Computing · Computer Science 2015-01-26 Yann Ollivier

Pre-trained Transformers (\eg BERT) have been commonly used in existing dense retrieval methods for parameter initialization, and recent studies are exploring more effective pre-training tasks for further improving the quality of dense…

Computation and Language · Computer Science 2023-06-21 Kun Zhou , Xiao Liu , Yeyun Gong , Wayne Xin Zhao , Daxin Jiang , Nan Duan , Ji-Rong Wen

Many machine learning models use the manipulation of dimensions as a driving force to enable models to identify and learn important features in data. In the case of sequential data this manipulation usually happens on the token dimension…

Machine Learning · Computer Science 2023-10-24 Daniel Biermann , Fabrizio Palumbo , Morten Goodwin , Ole-Christoffer Granmo