English
Related papers

Related papers: Sentence Encoders on STILTs: Supplementary Trainin…

200 papers

Language model pretraining has led to significant performance gains but careful comparison between different approaches is challenging. Training is computationally expensive, often done on private datasets of different sizes, and, as we…

Computation and Language · Computer Science 2019-07-29 Yinhan Liu , Myle Ott , Naman Goyal , Jingfei Du , Mandar Joshi , Danqi Chen , Omer Levy , Mike Lewis , Luke Zettlemoyer , Veselin Stoyanov

Natural language understanding (NLU) has two core tasks: intent classification and slot filling. The success of pre-training language models resulted in a significant breakthrough in the two tasks. One of the promising solutions called BERT…

Computation and Language · Computer Science 2023-02-03 Yu Guo , Zhilong Xie , Xingyan Chen , Huangen Chen , Leilei Wang , Huaming Du , Shaopeng Wei , Yu Zhao , Qing Li , Gang Wu

Sentence embedding tasks are important in natural language processing (NLP), but improving their performance while keeping them reliable is still hard. This paper presents a framework that combines pseudo-label generation and model ensemble…

Computation and Language · Computer Science 2025-01-28 Ziwei Liu , Qi Zhang , Lifu Gao

Though achieving impressive results on many NLP tasks, the BERT-like masked language models (MLM) encounter the discrepancy between pre-training and inference. In light of this gap, we investigate the contextual representation of…

Computation and Language · Computer Science 2022-05-16 Yu Lin , Zhecheng An , Peihao Wu , Zejun Ma

Entailment has been recognized as an important metric for evaluating natural language understanding (NLU) models, and recent studies have found that entailment pretraining benefits weakly supervised fine-tuning. In this work, we design a…

Computation and Language · Computer Science 2023-05-30 Jiaxin Ge , Hongyin Luo , Yoon Kim , James Glass

Large pre-trained sentence encoders like BERT start a new chapter in natural language processing. A common practice to apply pre-trained BERT to sequence classification tasks (e.g., classification of sentences or sentence pairs) is by…

Computation and Language · Computer Science 2020-02-26 Wenxuan Zhou , Junyi Du , Xiang Ren

Most humans use visual imagination to understand and reason about language, but models such as BERT reason about language using knowledge acquired during text-only pretraining. In this work, we investigate whether vision-and-language…

Computer Vision and Pattern Recognition · Computer Science 2023-11-07 Morris Alper , Michael Fiman , Hadar Averbuch-Elor

Pretrained multilingual text encoders based on neural Transformer architectures, such as multilingual BERT (mBERT) and XLM, have achieved strong performance on a myriad of language understanding tasks. Consequently, they have been adopted…

Computation and Language · Computer Science 2021-01-22 Robert Litschko , Ivan Vulić , Simone Paolo Ponzetto , Goran Glavaš

We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models, BERT is designed to pre-train deep bidirectional…

Computation and Language · Computer Science 2019-05-28 Jacob Devlin , Ming-Wei Chang , Kenton Lee , Kristina Toutanova

Fine-tuning pretrained contextual word embedding models to supervised downstream tasks has become commonplace in natural language processing. This process, however, is often brittle: even with the same hyperparameter values, distinct random…

Computation and Language · Computer Science 2020-02-19 Jesse Dodge , Gabriel Ilharco , Roy Schwartz , Ali Farhadi , Hannaneh Hajishirzi , Noah Smith

Recently, pre-trained models have been the dominant paradigm in natural language processing. They achieved remarkable state-of-the-art performance across a wide range of related tasks, such as textual entailment, natural language inference,…

Computation and Language · Computer Science 2019-05-21 Dongfang Li , Yifei Yu , Qingcai Chen , Xinyu Li

This study examines whether the attention scores between tokens in the BERT model significantly vary based on lexical categories during the fine-tuning process for downstream tasks. Drawing inspiration from the notion that in human language…

Computation and Language · Computer Science 2024-03-26 Dongjun Jang , Sungjoo Byun , Hyopil Shin

In the last year, new models and methods for pretraining and transfer learning have driven striking performance improvements across a range of language understanding tasks. The GLUE benchmark, introduced a little over one year ago, offers a…

Computation and Language · Computer Science 2020-02-14 Alex Wang , Yada Pruksachatkun , Nikita Nangia , Amanpreet Singh , Julian Michael , Felix Hill , Omer Levy , Samuel R. Bowman

Detecting the user's intent and finding the corresponding slots among the utterance's words are important tasks in natural language understanding. Their interconnected nature makes their joint modeling a standard part of training such…

Computation and Language · Computer Science 2021-10-06 Momchil Hardalov , Ivan Koychev , Preslav Nakov

Language model pre-training has shown promising results in various downstream tasks. In this context, we introduce a cross-modal pre-trained language model, called Speech-Text BERT (ST-BERT), to tackle end-to-end spoken language…

Computation and Language · Computer Science 2021-04-13 Minjeong Kim , Gyuwan Kim , Sang-Woo Lee , Jung-Woo Ha

Supplementary Training on Intermediate Labeled-data Tasks (STILTs) is a widely applied technique, which first fine-tunes the pretrained language models on an intermediate task before on the target task of interest. While STILTs is able to…

Computation and Language · Computer Science 2021-09-02 Ting-Yun Chang , Chi-Jen Lu

In this work, we investigate the positional encoding methods used in language pre-training (e.g., BERT) and identify several problems in the existing formulations. First, we show that in the absolute positional encoding, the addition…

Computation and Language · Computer Science 2021-03-16 Guolin Ke , Di He , Tie-Yan Liu

Language model pre-training has proven to be useful in learning universal language representations. As a state-of-the-art language model pre-training model, BERT (Bidirectional Encoder Representations from Transformers) has achieved amazing…

Computation and Language · Computer Science 2020-02-06 Chi Sun , Xipeng Qiu , Yige Xu , Xuanjing Huang

The advent of deep learning has led to a significant gain in machine translation. However, most of the studies required a large parallel dataset which is scarce and expensive to construct and even unavailable for some languages. This paper…

Computation and Language · Computer Science 2023-04-04 Viet H. Pham , Thang M. Pham , Giang Nguyen , Long Nguyen , Dien Dinh

While recent research on natural language inference has considerably benefited from large annotated datasets, the amount of inference-related knowledge (including commonsense) provided in the annotated data is still rather limited. There…

Computation and Language · Computer Science 2021-09-10 Xiaoyu Yang , Xiaodan Zhu , Zhan Shi , Tianda Li