English
Related papers

Related papers: Joint Energy-based Model Training for Better Calib…

200 papers

We aim at using Energy-based Model (EBM) framework to better understand adversarial training (AT) in classifiers, and additionally to analyze the intrinsic generative capabilities of robust classifiers. By viewing standard classifiers…

Pretraining sentence encoders with language modeling and related unsupervised tasks has recently been shown to be very effective for language understanding tasks. By supplementing language model-style pretraining with further training on…

Computation and Language · Computer Science 2019-03-01 Jason Phang , Thibault Févry , Samuel R. Bowman

Natural language processing (NLP) tasks (e.g. question-answering in English) benefit from knowledge of other tasks (e.g. named entity recognition in English) and knowledge of other languages (e.g. question-answering in Spanish). Such shared…

Computation and Language · Computer Science 2021-03-23 Ishan Tarunesh , Sushil Khyalia , Vishwajeet Kumar , Ganesh Ramakrishnan , Preethi Jyothi

Pre-trained Large Language Models (LLMs) often struggle on out-of-domain datasets like healthcare focused text. We explore specialized pre-training to adapt smaller LLMs to different healthcare datasets. Three methods are assessed:…

Computation and Language · Computer Science 2024-04-01 Niall Taylor , Dan Schofield , Andrey Kormilitzin , Dan W Joyce , Alejo Nevado-Holgado

Fine-tuning Large Language Models (LLMs) is now a common approach for text classification in a wide range of applications. When labeled documents are scarce, active learning helps save annotation efforts but requires retraining of massive…

Machine Learning · Computer Science 2024-02-27 Artem Vysogorets , Achintya Gopal

This paper presents a novel training method, Conditional Masked Language Modeling (CMLM), to effectively learn sentence representations on large scale unlabeled corpora. CMLM integrates sentence representation learning into MLM training by…

Computation and Language · Computer Science 2021-09-13 Ziyi Yang , Yinfei Yang , Daniel Cer , Jax Law , Eric Darve

The overwhelming amount of biomedical scientific texts calls for the development of effective language models able to tackle a wide range of biomedical natural language processing (NLP) tasks. The most recent dominant approaches are…

Computation and Language · Computer Science 2021-04-21 Giacomo Miolo , Giulio Mantoan , Carlotta Orsenigo

Deep energy-based models are powerful, but pose challenges for learning and inference (Belanger and McCallum, 2016). Tu and Gimpel (2018) developed an efficient framework for energy-based models by training "inference networks" to…

Computation and Language · Computer Science 2020-10-13 Lifu Tu , Richard Yuanzhe Pang , Kevin Gimpel

Joint Energy-based Model (JEM) is a recently proposed hybrid model that retains strong discriminative power of modern CNN classifiers, while generating samples rivaling the quality of GAN-based approaches. In this paper, we propose a…

Machine Learning · Computer Science 2021-09-22 Xiulong Yang , Shihao Ji

Pre-trained language models (PLMs) show impressive performance in various downstream NLP tasks. However, pre-training large language models demands substantial memory and training compute. Furthermore, due to the substantial resources…

Computation and Language · Computer Science 2024-04-01 HyunJin Kim , Young Jin Kim , JinYeong Bak

Expressing universal semantics common to all languages is helpful in understanding the meanings of complex and culture-specific sentences. The research theme underlying this scenario focuses on learning universal representations across…

Computation and Language · Computer Science 2023-10-27 Ping Guo , Xiangpeng Wei , Yue Hu , Baosong Yang , Dayiheng Liu , Fei Huang , Jun Xie

For languages with no annotated resources, transferring knowledge from rich-resource languages is an effective solution for named entity recognition (NER). While all existing methods directly transfer from source-learned model to a target…

Computation and Language · Computer Science 2020-07-16 Qianhui Wu , Zijia Lin , Guoxin Wang , Hui Chen , Börje F. Karlsson , Biqing Huang , Chin-Yew Lin

In this paper, we propose conjugate energy-based models (CEBMs), a new class of energy-based models that define a joint density over data and latent variables. The joint density of a CEBM decomposes into an intractable distribution over…

Machine Learning · Computer Science 2021-06-28 Hao Wu , Babak Esmaeili , Michael Wick , Jean-Baptiste Tristan , Jan-Willem van de Meent

Multimodal generative models have recently gained significant attention for their ability to learn representations across various modalities, enhancing joint and cross-generation coherence. However, most existing works use standard Gaussian…

Machine Learning · Computer Science 2024-10-01 Shiyu Yuan , Jiali Cui , Hanao Li , Tian Han

Artificial intelligence systems significantly impact the environment, particularly in natural language processing (NLP) tasks. These tasks often require extensive computational resources to train deep neural networks, including large-scale…

Computation and Language · Computer Science 2025-03-17 Tohida Rehman , Debarshi Kumar Sanyal , Samiran Chattopadhyay

Monolingual data have been demonstrated to be helpful in improving translation quality of both statistical machine translation (SMT) systems and neural machine translation (NMT) systems, especially in resource-poor or domain adaptation…

Computation and Language · Computer Science 2018-03-02 Zhirui Zhang , Shujie Liu , Mu Li , Ming Zhou , Enhong Chen

We present Branch-Train-Merge (BTM), a communication-efficient algorithm for embarrassingly parallel training of large language models (LLMs). We show it is possible to independently train subparts of a new class of LLMs on different…

Computation and Language · Computer Science 2022-08-08 Margaret Li , Suchin Gururangan , Tim Dettmers , Mike Lewis , Tim Althoff , Noah A. Smith , Luke Zettlemoyer

Multilingual Pre-trained Language models (multiPLMs), trained on the Masked Language Modelling (MLM) objective are commonly being used for cross-lingual tasks such as bitext mining. However, the performance of these models is still…

Computation and Language · Computer Science 2025-01-13 Aloka Fernando , Surangika Ranathunga

Large language models (LLMs) have shown remarkable capabilities in various natural language understanding tasks. With only a few demonstration examples, these LLMs can quickly adapt to target tasks without expensive gradient updates. Common…

Computation and Language · Computer Science 2023-11-14 Yue Yu , Jiaming Shen , Tianqi Liu , Zhen Qin , Jing Nathan Yan , Jialu Liu , Chao Zhang , Michael Bendersky

Pre-training has proven to be effective in unsupervised machine translation due to its ability to model deep context information in cross-lingual scenarios. However, the cross-lingual information obtained from shared BPE spaces is…

Computation and Language · Computer Science 2019-09-04 Shuo Ren , Yu Wu , Shujie Liu , Ming Zhou , Shuai Ma