English
Related papers

Related papers: Visualizing and Measuring the Geometry of BERT

200 papers

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

The adaptation of pretrained language models to solve supervised tasks has become a baseline in NLP, and many recent works have focused on studying how linguistic information is encoded in the pretrained sentence representations. Among…

Computation and Language · Computer Science 2021-02-11 Laura Pérez-Mayos , Roberto Carlini , Miguel Ballesteros , Leo Wanner

Powerful sentence encoders trained for multiple languages are on the rise. These systems are capable of embedding a wide range of linguistic properties into vector representations. While explicit probing tasks can be used to verify the…

Computation and Language · Computer Science 2021-09-22 Maarten De Raedt , Fréderic Godin , Pieter Buteneers , Chris Develder , Thomas Demeester

Active learning has been shown to be an effective way to alleviate some of the effort required in utilising large collections of unlabelled data for machine learning tasks without needing to fully label them. The representation mechanism…

Information Retrieval · Computer Science 2020-04-29 Jinghui Lu , Brian MacNamee

Recently, multilingual BERT works remarkably well on cross-lingual transfer tasks, superior to static non-contextualized word embeddings. In this work, we provide an in-depth experimental study to supplement the existing literature of…

Computation and Language · Computer Science 2020-04-21 Chi-Liang Liu , Tsung-Yuan Hsu , Yung-Sung Chuang , Hung-Yi Lee

Language Models such as BERT have grown in popularity due to their ability to be pre-trained and perform robustly on a wide range of Natural Language Processing tasks. Often seen as an evolution over traditional word embedding techniques,…

Computation and Language · Computer Science 2022-06-30 Nimesh Bhana , Terence L. van Zyl

Fine-tuned Bidirectional Encoder Representations from Transformers (BERT)-based sequence classification models have proven to be effective for detecting Alzheimer's Disease (AD) from transcripts of human speech. However, previous research…

Computation and Language · Computer Science 2020-11-13 Aparna Balagopalan , Jekaterina Novikova

Large, pretrained language models infer powerful representations that encode rich semantic and syntactic content, albeit implicitly. In this work we introduce a novel neural language model that enforces, via inductive biases, explicit…

Computation and Language · Computer Science 2023-05-29 Ramsés J. Sánchez , Lukas Conrads , Pascal Welke , Kostadin Cvejoski , César Ojeda

Exploiting rich linguistic information in raw text is crucial for expressive text-to-speech (TTS). As large scale pre-trained text representation develops, bidirectional encoder representations from Transformers (BERT) has been proven to…

Computation and Language · Computer Science 2022-11-14 Yixuan Zhou , Changhe Song , Jingbei Li , Zhiyong Wu , Yanyao Bian , Dan Su , Helen Meng

Several studies have explored various advantages of multilingual pre-trained models (such as multilingual BERT) in capturing shared linguistic knowledge. However, less attention has been paid to their limitations. In this paper, we…

Computation and Language · Computer Science 2022-03-18 Sara Rajaee , Mohammad Taher Pilehvar

Neural networks models for NLP are typically implemented without the explicit encoding of language rules and yet they are able to break one performance record after another. This has generated a lot of research interest in interpreting the…

Computation and Language · Computer Science 2019-11-14 Mariya Toneva , Leila Wehbe

Increasing model size when pretraining natural language representations often results in improved performance on downstream tasks. However, at some point further model increases become harder due to GPU/TPU memory limitations and longer…

Computation and Language · Computer Science 2020-02-11 Zhenzhong Lan , Mingda Chen , Sebastian Goodman , Kevin Gimpel , Piyush Sharma , Radu Soricut

Variants of the BERT architecture specialised for producing full-sentence representations often achieve better performance on downstream tasks than sentence embeddings extracted from vanilla BERT. However, there is still little…

Computation and Language · Computer Science 2023-01-31 Dmitry Nikolaev , Sebastian Padó

Attention based language models have become a critical component in state-of-the-art natural language processing systems. However, these models have significant computational requirements, due to long training times, dense operations and…

Computation and Language · Computer Science 2021-06-11 Ivan Chelombiev , Daniel Justus , Douglas Orr , Anastasia Dietrich , Frithjof Gressmann , Alexandros Koliousis , Carlo Luschi

Pre-trained language models such as BERT have been a key ingredient to achieve state-of-the-art results on a variety of tasks in natural language processing and, more recently, also in information retrieval.Recent research even claims that…

Information Retrieval · Computer Science 2022-05-03 Emma J. Gerritse , Faegheh Hasibi , Arjen P. de Vries

Despite the recent success of deep neural networks in natural language processing (NLP), their interpretability remains a challenge. We analyze the representations learned by neural machine translation models at various levels of…

Computation and Language · Computer Science 2019-11-04 Yonatan Belinkov , Nadir Durrani , Fahim Dalvi , Hassan Sajjad , James Glass

This paper describes a language representation model which combines the Bidirectional Encoder Representations from Transformers (BERT) learning mechanism described in Devlin et al. (2018) with a generalization of the Universal Transformer…

Computation and Language · Computer Science 2019-05-17 Alon Rozental , Zohar Kelrich , Daniel Fleischer

Attention-based models have shown significant improvement over traditional algorithms in several NLP tasks. The Transformer, for instance, is an illustrative example that generates abstract representations of tokens inputted to an encoder…

Computation and Language · Computer Science 2019-11-15 Dhanasekar Sundararaman , Vivek Subramanian , Guoyin Wang , Shijing Si , Dinghan Shen , Dong Wang , Lawrence Carin

Token embeddings in multilingual BERT (m-BERT) contain both language and semantic information. We find that the representation of a language can be obtained by simply averaging the embeddings of the tokens of the language. Given this…

Computation and Language · Computer Science 2021-11-02 Chi-Liang Liu , Tsung-Yuan Hsu , Yung-Sung Chuang , Chung-Yi Li , Hung-yi Lee

This study investigates the internal mechanisms of BERT, a transformer-based large language model, with a focus on its ability to cluster narrative content and authorial style across its layers. Using a dataset of narratives developed via…

Computation and Language · Computer Science 2025-01-15 Awritrojit Banerjee , Achim Schilling , Patrick Krauss