English
Related papers

Related papers: Recipes for Sequential Pre-training of Multilingua…

200 papers

Pre-trained language model representations have been successful in a wide range of language understanding tasks. In this paper, we examine different strategies to integrate pre-trained representations into sequence to sequence models and…

Computation and Language · Computer Science 2019-04-02 Sergey Edunov , Alexei Baevski , Michael Auli

Masked Language Model (MLM) framework has been widely adopted for self-supervised language pre-training. In this paper, we argue that randomly sampled masks in MLM would lead to undesirably large gradient variance. Thus, we theoretically…

Computation and Language · Computer Science 2020-10-15 Mingzhi Zheng , Dinghan Shen , Yelong Shen , Weizhu Chen , Lin Xiao

Direct speech-to-text translation systems encounter an important drawback in data scarcity. A common solution consists on pretraining the encoder on automatic speech recognition, hence losing efficiency in the training process. In this…

Computation and Language · Computer Science 2024-09-27 Belen Alastruey , Gerard I. Gállego , Marta R. Costa-jussà

Running LLMs with extended reasoning on every problem is expensive, but determining which inputs actually require additional compute remains challenging. We investigate whether their own likelihood of success is recoverable from their…

Computation and Language · Computer Science 2026-04-07 William Lugoloobi , Thomas Foster , William Bankes , Chris Russell

Transformers have gained popularity in the software engineering (SE) literature. These deep learning models are usually pre-trained through a self-supervised objective, meant to provide the model with basic knowledge about a language of…

Software Engineering · Computer Science 2023-02-09 Rosalia Tufano , Luca Pascarella , Gabriele Bavota

Pretrained, large, generative language models (LMs) have had great success in a wide range of sequence tagging and structured prediction tasks. Casting a sequence tagging task as a Seq2Seq one requires deciding the formats of the input and…

Computation and Language · Computer Science 2022-10-26 Karthik Raman , Iftekhar Naim , Jiecao Chen , Kazuma Hashimoto , Kiran Yalasangi , Krishna Srinivasan

Multi-modal Large Language Model (MLLM) refers to a model expanded from a Large Language Model (LLM) that possesses the capability to handle and infer multi-modal data. Current MLLMs typically begin by using LLMs to decompose tasks into…

Computation and Language · Computer Science 2023-09-01 Yongqiang Zhao , Zhenyu Li , Feng Zhang , Xinhai Xu , Donghong Liu

State-of-the-art neural models typically encode document-query pairs using cross-attention for re-ranking. To this end, models generally utilize an encoder-only (like BERT) paradigm or an encoder-decoder (like T5) approach. These paradigms,…

Computation and Language · Computer Science 2022-04-26 Kai Hui , Honglei Zhuang , Tao Chen , Zhen Qin , Jing Lu , Dara Bahri , Ji Ma , Jai Prakash Gupta , Cicero Nogueira dos Santos , Yi Tay , Don Metzler

Pre-training and fine-tuning, e.g., BERT, have achieved great success in language understanding by transferring knowledge from rich-resource pre-training task to the low/zero-resource downstream tasks. Inspired by the success of BERT, we…

Computation and Language · Computer Science 2019-06-24 Kaitao Song , Xu Tan , Tao Qin , Jianfeng Lu , Tie-Yan Liu

Text images contain both visual and linguistic information. However, existing pre-training techniques for text recognition mainly focus on either visual representation learning or linguistic knowledge learning. In this paper, we propose a…

Computer Vision and Pattern Recognition · Computer Science 2023-10-11 Pengyuan Lyu , Chengquan Zhang , Shanshan Liu , Meina Qiao , Yangliu Xu , Liang Wu , Kun Yao , Junyu Han , Errui Ding , Jingdong Wang

The pre-training phase of language models often begins with randomly initialized parameters. With the current trends in scaling models, training their large number of parameters can be extremely slow and costly. In contrast, small language…

Computation and Language · Computer Science 2024-09-23 Mohammad Samragh , Iman Mirzadeh , Keivan Alizadeh Vahid , Fartash Faghri , Minsik Cho , Moin Nabi , Devang Naik , Mehrdad Farajtabar

Masked Language Modeling (MLM) has proven to be an essential component of Vision-Language (VL) pretraining. To implement MLM, the researcher must make two design choices: the masking strategy, which determines which tokens to mask, and the…

Machine Learning · Computer Science 2022-12-13 Siddharth Verma , Yuchen Lu , Rui Hou , Hanchao Yu , Nicolas Ballas , Madian Khabsa , Amjad Almahairi

The world of language models is going through turbulent times, better and ever larger models are coming out at an unprecedented speed. However, we argue that, especially for the scientific community, encoder models of up to 1 billion…

Computation and Language · Computer Science 2024-04-09 Nikola Ljubešić , Vít Suchomel , Peter Rupnik , Taja Kuzman , Rik van Noord

Modern language models (LMs) are trained in an autoregressive manner, conditioned only on the prefix. In contrast, sequence labeling (SL) tasks assign labels to each individual input token, naturally benefiting from bidirectional context.…

Computation and Language · Computer Science 2026-01-27 Matija Luka Kukić , Marko Čuljak , David Dukić , Martin Tutek , Jan Šnajder

Unsupervised multitask pre-training has been the critical method behind the recent success of language models (LMs). However, supervised multitask learning still holds significant promise, as scaling it in the post-training stage trends…

Computation and Language · Computer Science 2024-12-02 Daixuan Cheng , Yuxian Gu , Shaohan Huang , Junyu Bi , Minlie Huang , Furu Wei

Language models achieve impressive performance on a variety of knowledge, language, and reasoning tasks due to the scale and diversity of pretraining data available. The standard training recipe is a two-stage paradigm: pretraining first on…

Computation and Language · Computer Science 2026-03-20 Skyler Seto , Pierre Ablin , Anastasiia Filippova , Jiayuan Ye , Louis Bethune , Angelos Katharopoulos , David Grangier

Masked language modeling has become a standard pretraining objective for training encoder-based language models. In this approach, certain tokens in the input are masked, and the model learns to predict them using the surrounding context.…

Artificial Intelligence · Computer Science 2026-05-28 Gokul Srinivasagan , Kai Hartung , Munir Georges

Self-supervised video transformer pre-training has recently benefited from the mask-and-predict pipeline. They have demonstrated outstanding effectiveness on downstream video tasks and superior data efficiency on small datasets. However,…

Computer Vision and Pattern Recognition · Computer Science 2022-10-12 Yuxin Song , Min Yang , Wenhao Wu , Dongliang He , Fu Li , Jingdong Wang

This thesis provides methods and analysis of models which make progress on this goal. The techniques outlined are task agnostic, and should provide benefit when used with nearly any transformer LM. We introduce two new finetuning methods…

Computation and Language · Computer Science 2024-08-30 Davis Yoshida

Pre-trained language models based on masked language modeling (MLM) excel in natural language understanding (NLU) tasks. While fine-tuned MLM-based encoders consistently outperform causal language modeling decoders of comparable size,…

Computation and Language · Computer Science 2024-06-07 David Dukić , Jan Šnajder