English
Related papers

Related papers: Sentence Embeddings by Ensemble Distillation

200 papers

In streaming settings, speech recognition models have to map sub-sequences of speech to text before the full audio stream becomes available. However, since alignment information between speech and text is rarely available during training,…

Audio and Speech Processing · Electrical Eng. & Systems 2023-12-20 Oscar Chang , Dongseong Hwang , Olivier Siohan

Tiny, causal models are crucial for embedded audio machine learning applications. Model compression can be achieved via distilling knowledge from a large teacher into a smaller student model. In this work, we propose a novel two-step…

Sound · Computer Science 2023-09-18 Rayan Daod Nathoo , Mikolaj Kegler , Marko Stamenovic

A popular approach to model compression is to train an inexpensive student model to mimic the class probabilities of a highly accurate but cumbersome teacher model. Surprisingly, this two-step knowledge distillation process often leads to…

Machine Learning · Statistics 2021-04-21 Tri Dao , Govinda M Kamath , Vasilis Syrgkanis , Lester Mackey

Linking facts across documents is a challenging task, as the language used to express the same information in a sentence can vary significantly, which complicates the task of multi-document summarization. Consequently, existing approaches…

Computation and Language · Computer Science 2019-09-27 Diego Antognini , Boi Faltings

Knowledge distillation often involves how to define and transfer knowledge from teacher to student effectively. Although recent self-supervised contrastive knowledge achieves the best performance, forcing the network to learn such knowledge…

Computer Vision and Pattern Recognition · Computer Science 2022-07-26 Chuanguang Yang , Zhulin An , Linhang Cai , Yongjun Xu

This paper proposes a novel knowledge distillation-based learning method to improve the classification performance of convolutional neural networks (CNNs) without a pre-trained teacher network, called exit-ensemble distillation. Our method…

Computer Vision and Pattern Recognition · Computer Science 2021-04-06 Hojung Lee , Jong-Seok Lee

Self-supervised methods in vision have been mostly focused on large architectures as they seem to suffer from a significant performance drop for smaller architectures. In this paper, we propose a simple self-supervised distillation…

Computer Vision and Pattern Recognition · Computer Science 2023-01-24 Quentin Duval , Ishan Misra , Nicolas Ballas

We present a novel technique for learning semantic representations, which extends the distributional hypothesis to multilingual data and joint-space embeddings. Our models leverage parallel data and learn to strongly align the embeddings of…

Computation and Language · Computer Science 2014-04-21 Karl Moritz Hermann , Phil Blunsom

Semantically meaningful sentence embeddings are important for numerous tasks in natural language processing. To obtain such embeddings, recent studies explored the idea of utilizing synthetically generated data from pretrained language…

Computation and Language · Computer Science 2022-08-31 Taehee Kim , ChaeHun Park , Jimin Hong , Radhika Dua , Edward Choi , Jaegul Choo

We introduce a new approach for smoothing and improving the quality of word embeddings. We consider a method of fusing word embeddings that were trained on the same corpus but with different initializations. We project all the models to a…

Computation and Language · Computer Science 2021-06-08 Avi Caciularu , Ido Dagan , Jacob Goldberger

Learning sentence embeddings often requires a large amount of labeled data. However, for most tasks and domains, labeled data is seldom available and creating it is expensive. In this work, we present a new state-of-the-art unsupervised…

Computation and Language · Computer Science 2021-09-13 Kexin Wang , Nils Reimers , Iryna Gurevych

Recently, BERT realized significant progress for sentence matching via word-level cross sentence attention. However, the performance significantly drops when using siamese BERT-networks to derive two sentence embeddings, which fall short in…

Artificial Intelligence · Computer Science 2021-04-20 Xingyi Cheng

Stance detection on social media is challenging for Large Language Models (LLMs), as emerging slang and colloquial language in online conversations often contain deeply implicit stance labels. Chain-of-Thought (COT) prompting has recently…

Computation and Language · Computer Science 2023-10-31 Joseph Gatto , Omar Sharif , Sarah Masud Preum

This paper introduces a novel approach called sentence-wise speech summarization (Sen-SSum), which generates text summaries from a spoken document in a sentence-by-sentence manner. Sen-SSum combines the real-time processing of automatic…

Computation and Language · Computer Science 2024-08-02 Kohei Matsuura , Takanori Ashihara , Takafumi Moriya , Masato Mimura , Takatomo Kano , Atsunori Ogawa , Marc Delcroix

In this work, we introduce several schemes to leverage description-augmented embedding similarity for dataless intent classification using current state-of-the-art (SOTA) text embedding models. We report results of our methods on four…

Computation and Language · Computer Science 2024-07-26 Ruoyu Hu , Foaad Khosmood , Abbas Edalat

Existing knowledge distillation methods mostly focus on distillation of teacher's prediction and intermediate activation. However, the structured representation, which arguably is one of the most critical ingredients of deep models, is…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Jing Yang , Xiatian Zhu , Adrian Bulat , Brais Martinez , Georgios Tzimiropoulos

Most previous scene text spotting methods rely on high-quality manual annotations to achieve promising performance. To reduce their expensive costs, we study semi-supervised text spotting (SSTS) to exploit useful information from unlabeled…

Computer Vision and Pattern Recognition · Computer Science 2025-04-15 Dongliang Luo , Hanshen Zhu , Ziyang Zhang , Dingkang Liang , Xudong Xie , Yuliang Liu , Xiang Bai

The pre-trained speech encoder wav2vec 2.0 performs very well on various spoken language understanding (SLU) tasks. However, on many tasks, it trails behind text encoders with textual input. To improve the understanding capability of SLU…

Computation and Language · Computer Science 2023-05-23 Yi Xuan Tan , Navonil Majumder , Soujanya Poria

Since the amount of information on the internet is growing rapidly, it is not easy for a user to find relevant information for his/her query. To tackle this issue, much attention has been paid to Automatic Document Summarization. The key…

Computation and Language · Computer Science 2019-02-05 Kamal Al-Sabahi , Zhang Zuping , Yang Kang

Modern language models have the capacity to store and use immense amounts of knowledge about real-world entities, but it remains unclear how to update such knowledge stored in model parameters. While prior methods for updating knowledge in…

Computation and Language · Computer Science 2023-11-01 Shankar Padmanabhan , Yasumasa Onoe , Michael J. Q. Zhang , Greg Durrett , Eunsol Choi