English
Related papers

Related papers: HistBERT: A Pre-trained Language Model for Diachro…

200 papers

Contextual word embedding models such as ELMo (Peters et al., 2018) and BERT (Devlin et al., 2018) have dramatically improved performance for many natural language processing (NLP) tasks in recent months. However, these models have been…

Computation and Language · Computer Science 2019-06-24 Emily Alsentzer , John R. Murphy , Willie Boag , Wei-Hung Weng , Di Jin , Tristan Naumann , Matthew B. A. McDermott

We propose procedures for evaluating and strengthening contextual embedding alignment and show that they are useful in analyzing and improving multilingual BERT. In particular, after our proposed alignment procedure, BERT exhibits…

Computation and Language · Computer Science 2020-02-14 Steven Cao , Nikita Kitaev , Dan Klein

Pre-trained language models such as BERT have become a more common choice of natural language processing (NLP) tasks. Research in word representation shows that isotropic embeddings can significantly improve performance on downstream tasks.…

Computation and Language · Computer Science 2021-08-30 Yuxin Liang , Rui Cao , Jie Zheng , Jie Ren , Ling Gao

Pre-trained contextual language models are ubiquitously employed for language understanding tasks, but are unsuitable for resource-constrained systems. Noncontextual word embeddings are an efficient alternative in these settings. Such…

Computation and Language · Computer Science 2023-04-24 Anik Saha , Alex Gittens , Bulent Yener

A considerable number of texts encountered daily are somehow connected with each other. For example, Wikipedia articles refer to other articles via hyperlinks, scientific papers relate to others via citations or (co)authors, while tweets…

Computation and Language · Computer Science 2025-08-08 Albert Roethel , Maria Ganzha , Anna Wróblewska

The use of large pretrained neural networks to create contextualized word embeddings has drastically improved performance on several natural language processing (NLP) tasks. These computationally expensive models have begun to be applied to…

Computers and Society · Computer Science 2019-12-03 Benjamin Clavié , Kobi Gal

Contextualised word vectors obtained via pre-trained language models encode a variety of knowledge that has already been exploited in applications. Complementary to these language models are probabilistic topic models that learn thematic…

Computation and Language · Computer Science 2023-01-12 Mozhgan Talebpour , Alba Garcia Seco de Herrera , Shoaib Jameel

Contextual word embedding models, such as BioBERT and Bio_ClinicalBERT, have achieved state-of-the-art results in biomedical natural language processing tasks by focusing their pre-training process on domain-specific corpora. However, such…

Computation and Language · Computer Science 2021-06-04 George Michalopoulos , Yuanxin Wang , Hussam Kaka , Helen Chen , Alexander Wong

Recently, the pre-trained language model, BERT (and its robustly optimized version RoBERTa), has attracted a lot of attention in natural language understanding (NLU), and achieved state-of-the-art accuracy in various NLU tasks, such as…

Computation and Language · Computer Science 2019-09-30 Wei Wang , Bin Bi , Ming Yan , Chen Wu , Zuyi Bao , Jiangnan Xia , Liwei Peng , Luo Si

As the name implies, contextualized representations of language are typically motivated by their ability to encode context. Which aspects of context are captured by such representations? We introduce an approach to address this question…

Computation and Language · Computer Science 2020-11-25 Michael A. Lepori , R. Thomas McCoy

Language use differs between domains and even within a domain, language use changes over time. For pre-trained language models like BERT, domain adaptation through continued pre-training has been shown to improve performance on in-domain…

Computation and Language · Computer Science 2021-09-09 Paul Röttger , Janet B. Pierrehumbert

Models based on the transformer architecture, such as BERT, have marked a crucial step forward in the field of Natural Language Processing. Importantly, they allow the creation of word embeddings that capture important semantic information…

Computation and Language · Computer Science 2021-01-01 Jacob Turton , David Vinson , Robert Elliott Smith

The Bidirectional Encoder Representations from Transformers (BERT) model has achieved the state-of-the-art performance for many natural language processing (NLP) tasks. Yet, limited research has been contributed to studying its…

Computation and Language · Computer Science 2021-09-23 Zimin Wan , Chenchen Xu , Hanna Suominen

While the success of pre-trained language models has largely eliminated the need for high-quality static word vectors in many NLP applications, such vectors continue to play an important role in tasks where words need to be modelled in the…

Computation and Language · Computer Science 2021-05-18 Na Li , Zied Bouraoui , Jose Camacho Collados , Luis Espinosa-Anke , Qing Gu , Steven Schockaert

The use of conversational assistants to search for information is becoming increasingly more popular among the general public, pushing the research towards more advanced and sophisticated techniques. In the last few years, in particular,…

Information Retrieval · Computer Science 2021-04-15 Rafael Ferreira , David Semedo , Joao Magalhaes

This paper presents new state-of-the-art models for three tasks, part-of-speech tagging, syntactic parsing, and semantic parsing, using the cutting-edge contextualized embedding framework known as BERT. For each task, we first replicate and…

Computation and Language · Computer Science 2020-05-26 Han He , Jinho D. Choi

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

How does word frequency in pre-training data affect the behavior of similarity metrics in contextualized BERT embeddings? Are there systematic ways in which some word relationships are exaggerated or understated? In this work, we explore…

Computation and Language · Computer Science 2021-04-20 Kaitlyn Zhou , Kawin Ethayarajh , Dan Jurafsky

Recently, fine-tuning pre-trained language models (e.g., multilingual BERT) to downstream cross-lingual tasks has shown promising results. However, the fine-tuning process inevitably changes the parameters of the pre-trained model and…

Computation and Language · Computer Science 2020-10-06 Zihan Liu , Genta Indra Winata , Andrea Madotto , Pascale Fung

We tackle the problem of identifying metaphors in text, treated as a sequence tagging task. The pre-trained word embeddings GloVe, ELMo and BERT have individually shown good performance on sequential metaphor identification. These…

Computation and Language · Computer Science 2021-04-08 Rui Mao , Chenghua Lin , Frank Guerin