English
Related papers

Related papers: Does BERT really agree ? Fine-grained Analysis of …

200 papers

Syntactic Transformer language models aim to achieve better generalization through simultaneously modeling syntax trees and sentences. While prior work has been focusing on adding constituency-based structures to Transformers, we introduce…

Computation and Language · Computer Science 2024-07-25 Yida Zhao , Chao Lou , Kewei Tu

Transformer-based language models have been shown to be highly effective for several NLP tasks. In this paper, we consider three transformer models, BERT, RoBERTa, and XLNet, in both small and large versions, and investigate how faithful…

Computation and Language · Computer Science 2023-12-01 Akshay Chaturvedi , Swarnadeep Bhar , Soumadeep Saha , Utpal Garain , Nicholas Asher

The introduction of pre-trained language models has revolutionized natural language research communities. However, researchers still know relatively little regarding their theoretical and empirical properties. In this regard, Peters et al.…

Computation and Language · Computer Science 2019-07-12 Ran Wang , Haibo Su , Chunye Wang , Kailin Ji , Jupeng Ding

Intent classification and slot filling are two essential tasks for natural language understanding. They often suffer from small-scale human-labeled training data, resulting in poor generalization capability, especially for rare words.…

Computation and Language · Computer Science 2019-03-01 Qian Chen , Zhu Zhuo , Wen Wang

Pretrained language models such as BERT, GPT have shown great effectiveness in language understanding. The auxiliary predictive tasks in existing pretraining approaches are mostly defined on tokens, thus may not be able to capture…

Computation and Language · Computer Science 2020-06-19 Hongchao Fang , Sicheng Wang , Meng Zhou , Jiayuan Ding , Pengtao Xie

Syntax is a latent hierarchical structure which underpins the robust and compositional nature of human language. In this work, we explore the hypothesis that syntactic dependencies can be represented in language model attention…

Computation and Language · Computer Science 2023-10-24 Jasper Jian , Siva Reddy

Large language models often fail on tasks they seem to already understand. In our experiments, this appears to be less about missing knowledge and more about certain internal circuits not being strongly activated during inference. We…

Machine Learning · Computer Science 2026-05-12 Ryyan Akhtar , Payal Pahwa , Monika Arora

Recent research has revealed that neural language models at scale suffer from poor temporal generalization capability, i.e., the language model pre-trained on static data from past years performs worse over time on emerging data. Existing…

Computation and Language · Computer Science 2022-11-01 Zhaochen Su , Zecheng Tang , Xinyan Guan , Juntao Li , Lijun Wu , Min Zhang

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

Pre-trained transformer language models have shown remarkable performance on a variety of NLP tasks. However, recent research has suggested that phrase-level representations in these models reflect heavy influences of lexical content, but…

Computation and Language · Computer Science 2021-06-02 Lang Yu , Allyson Ettinger

Contextual word embeddings such as BERT have achieved state of the art performance in numerous NLP tasks. Since they are optimized to capture the statistical properties of training data, they tend to pick up on and amplify social…

Computation and Language · Computer Science 2019-06-19 Keita Kurita , Nidhi Vyas , Ayush Pareek , Alan W Black , Yulia Tsvetkov

In English semantic similarity tasks, classic word embedding-based approaches explicitly model pairwise "interactions" between the word representations of a sentence pair. Transformer-based pretrained language models disregard this notion,…

Computation and Language · Computer Science 2019-11-11 Yinan Zhang , Raphael Tang , Jimmy Lin

Even though term-based methods such as BM25 provide strong baselines in ranking, under certain conditions they are dominated by large pre-trained masked language models (MLMs) such as BERT. To date, the source of their effectiveness remains…

Computation and Language · Computer Science 2022-07-07 David Rau , Jaap Kamps

Deep Neural Networks have taken Natural Language Processing by storm. While this led to incredible improvements across many tasks, it also initiated a new research field, questioning the robustness of these neural networks by attacking…

Computation and Language · Computer Science 2021-09-16 Jens Hauser , Zhao Meng , Damián Pascual , Roger Wattenhofer

Recent work has exhibited the surprising cross-lingual abilities of multilingual BERT (M-BERT) -- surprising since it is trained without any cross-lingual objective and with no aligned data. In this work, we provide a comprehensive study of…

Computation and Language · Computer Science 2020-02-18 Karthikeyan K , Zihan Wang , Stephen Mayhew , Dan Roth

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

Word representations induced from models with discrete latent variables (e.g.\ HMMs) have been shown to be beneficial in many NLP applications. In this work, we exploit labeled syntactic dependency trees and formalize the induction problem…

Computation and Language · Computer Science 2016-02-08 Simon Šuster , Gertjan van Noord , Ivan Titov

In this paper, we study the response of large models from the BERT family to incoherent inputs that should confuse any model that claims to understand natural language. We define simple heuristics to construct such examples. Our experiments…

Computation and Language · Computer Science 2021-03-18 Ashim Gupta , Giorgi Kvernadze , Vivek Srikumar

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

Fine-tuning pre-trained models have achieved impressive performance on standard natural language processing benchmarks. However, the resultant model generalizability remains poorly understood. We do not know, for example, how excellent…

Computation and Language · Computer Science 2023-01-26 Luoqiu Li , Xiang Chen , Hongbin Ye , Zhen Bi , Shumin Deng , Ningyu Zhang , Huajun Chen