English
Related papers

Related papers: BERTnesia: Investigating the capture and forgettin…

200 papers

The pre-training models such as BERT have achieved great results in various natural language processing problems. However, a large number of parameters need significant amounts of memory and the consumption of inference time, which makes it…

Computation and Language · Computer Science 2020-12-15 Hao Fu , Shaojun Zhou , Qihong Yang , Junjie Tang , Guiquan Liu , Kaikui Liu , Xiaolong Li

Pre-trained models have brought significant improvements to many NLP tasks and have been extensively analyzed. But little is known about the effect of fine-tuning on specific tasks. Intuitively, people may agree that a pre-trained model…

Computation and Language · Computer Science 2020-06-03 Jie Cai , Zhengzhou Zhu , Ping Nie , Qian Liu

Transformer-based language models trained on large text corpora have enjoyed immense popularity in the natural language processing community and are commonly used as a starting point for downstream tasks. While these models are undeniably…

Machine Learning · Computer Science 2021-11-17 Vinitra Swamy , Angelika Romanou , Martin Jaggi

Adding linguistic information (syntax or semantics) to neural machine translation (NMT) has mostly focused on using point estimates from pre-trained models. Directly using the capacity of massive pre-trained contextual word embedding models…

Computation and Language · Computer Science 2021-04-08 Hassan S. Shavarani , Anoop Sarkar

Language model pre-training, such as BERT, has achieved remarkable results in many NLP tasks. However, it is unclear why the pre-training-then-fine-tuning paradigm can improve performance and generalization capability across different…

Computation and Language · Computer Science 2019-08-16 Yaru Hao , Li Dong , Furu Wei , Ke Xu

A typical architecture for end-to-end entity linking systems consists of three steps: mention detection, candidate generation and entity disambiguation. In this study we investigate the following questions: (a) Can all those steps be…

Computation and Language · Computer Science 2021-01-14 Samuel Broscheit

Pretrained language models have achieved a new state of the art on many NLP tasks, but there are still many open questions about how and why they work so well. We investigate the contextualization of words in BERT. We quantify the amount of…

Computation and Language · Computer Science 2020-10-13 Mengjie Zhao , Philipp Dufter , Yadollah Yaghoobzadeh , Hinrich Schütze

We study the problem of incorporating prior knowledge into a deep Transformer-based model,i.e.,Bidirectional Encoder Representations from Transformers (BERT), to enhance its performance on semantic textual matching tasks. By probing and…

Computation and Language · Computer Science 2021-02-23 Tingyu Xia , Yue Wang , Yuan Tian , Yi Chang

We present a systematic investigation of layer-wise BERT activations for general-purpose text representations to understand what linguistic information they capture and how transferable they are across different tasks. Sentence-level…

Computation and Language · Computer Science 2019-10-25 Xiaofei Ma , Zhiguo Wang , Patrick Ng , Ramesh Nallapati , Bing Xiang

Aspect based sentiment analysis aims to identify the sentimental tendency towards a given aspect in text. Fine-tuning of pretrained BERT performs excellent on this task and achieves state-of-the-art performances. Existing BERT-based works…

Computation and Language · Computer Science 2020-02-13 Youwei Song , Jiahai Wang , Zhiwei Liang , Zhiyue Liu , Tao Jiang

Progress in natural language processing (NLP) models that estimate representations of word sequences has recently been leveraged to improve the understanding of language processing in the brain. However, these models have not been…

Neurons and Cognition · Quantitative Biology 2019-11-11 Dan Schwartz , Mariya Toneva , Leila Wehbe

Large pre-trained language models have been shown to encode large amounts of world and commonsense knowledge in their parameters, leading to substantial interest in methods for extracting that knowledge. In past work, knowledge was…

Computation and Language · Computer Science 2021-03-12 Adi Haviv , Jonathan Berant , Amir Globerson

Recently, pre-trained contextual models, such as BERT, have shown to perform well in language related tasks. We revisit the design decisions that govern the applicability of these models for the passage re-ranking task in open-domain…

Information Retrieval · Computer Science 2021-08-31 Jurek Leonhardt , Fabian Beringer , Avishek Anand

Deep language models such as BERT pre-trained on large corpus have given a huge performance boost to the state-of-the-art information retrieval ranking systems. Knowledge embedded in such models allows them to pick up complex matching…

Information Retrieval · Computer Science 2020-07-23 Luyu Gao , Zhuyun Dai , Jamie Callan

Machine reading comprehension is an essential natural language processing task, which takes into a pair of context and query and predicts the corresponding answer to query. In this project, we developed an end-to-end question answering…

Computation and Language · Computer Science 2024-04-05 Jiawei Li , Yue Zhang

The latest work on language representations carefully integrates contextualized features into language model training, which enables a series of success especially in various machine reading comprehension and natural language inference…

Computation and Language · Computer Science 2020-02-05 Zhuosheng Zhang , Yuwei Wu , Hai Zhao , Zuchao Li , Shuailiang Zhang , Xi Zhou , Xiang Zhou

Although BERT is widely used by the NLP community, little is known about its inner workings. Several attempts have been made to shed light on certain aspects of BERT, often with contradicting conclusions. A much raised concern focuses on…

Computation and Language · Computer Science 2020-10-13 Nikolaos Manginas , Ilias Chalkidis , Prodromos Malakasiotis

Most of the recent works on probing representations have focused on BERT, with the presumption that the findings might be similar to the other models. In this work, we extend the probing studies to two other models in the family, namely…

Computation and Language · Computer Science 2021-09-16 Mohsen Fayyaz , Ehsan Aghazadeh , Ali Modarressi , Hosein Mohebbi , Mohammad Taher Pilehvar

While large language models like BERT demonstrate strong empirical performance on semantic tasks, whether this reflects true conceptual competence or surface-level statistical association remains unclear. I investigate whether BERT encodes…

Computation and Language · Computer Science 2025-06-16 Cole Gawin

Recently, the development of pre-trained language models has brought natural language processing (NLP) tasks to the new state-of-the-art. In this paper we explore the efficiency of various pre-trained language models. We pre-train a list of…

Computation and Language · Computer Science 2023-07-27 Tong Guo