English
Related papers

Related papers: Do Attention Heads in BERT Track Syntactic Depende…

200 papers

The development of different theories of discourse structure has led to the establishment of discourse corpora based on these theories. However, the existence of discourse corpora established on different theoretical bases creates…

Computation and Language · Computer Science 2024-07-18 Kun Sun , Rong Wang

Transformer-based models, such as BERT and GPT, have been widely adopted in natural language processing (NLP) due to their exceptional performance. However, recent studies show their vulnerability to textual adversarial attacks where the…

Computation and Language · Computer Science 2023-12-01 Lujia Shen , Yuwen Pu , Shouling Ji , Changjiang Li , Xuhong Zhang , Chunpeng Ge , Ting Wang

This study analyzes the attention patterns of fine-tuned encoder-only models based on the BERT architecture (BERT-based models) towards two distinct types of Multiword Expressions (MWEs): idioms and microsyntactic units (MSUs). Idioms…

Computation and Language · Computer Science 2025-05-12 Iuliia Zaitova , Vitalii Hirak , Badr M. Abdullah , Dietrich Klakow , Bernd Möbius , Tania Avgustinova

Since 2017, the Transformer-based models play critical roles in various downstream Natural Language Processing tasks. However, a common limitation of the attention mechanism utilized in Transformer Encoder is that it cannot automatically…

Computation and Language · Computer Science 2022-04-20 Ziyang Luo , Yadong Xi , Jing Ma , Zhiwei Yang , Xiaoxi Mao , Changjie Fan , Rongsheng Zhang

Attention mechanism has been used as an ancillary means to help RNN or CNN. However, the Transformer (Vaswani et al., 2017) recently recorded the state-of-the-art performance in machine translation with a dramatic reduction in training time…

Computation and Language · Computer Science 2017-12-07 Jinbae Im , Sungzoon Cho

We present a syntactic dependency treebank for naturalistic child and child-directed speech in English (MacWhinney, 2000). Our annotations largely followed the guidelines of the Universal Dependencies project (UD (Zeman et al., 2022)), with…

Computation and Language · Computer Science 2022-09-29 Zoey Liu , Emily Prud'hommeaux

Attention layers are widely used in natural language processing (NLP) and are beginning to influence computer vision architectures. Training very large transformer models allowed significant improvement in both fields, but once trained,…

Machine Learning · Computer Science 2021-05-21 Jean-Baptiste Cordonnier , Andreas Loukas , Martin Jaggi

Transformer-based models have demonstrated considerable potential for source code modeling tasks in software engineering. However, they are limited by their dependence solely on automatic self-attention weight learning mechanisms. Previous…

Software Engineering · Computer Science 2024-02-27 Jiri Gesi , Iftekhar Ahmed

Transformer models exhibit in-context learning: the ability to accurately predict the response to a novel query based on illustrative examples in the input sequence. In-context learning contrasts with traditional in-weights learning of…

Machine Learning · Computer Science 2023-12-07 Gautam Reddy

Pre-trained language models (PLMs) like BERT are being used for almost all language-related tasks, but interpreting their behavior still remains a significant challenge and many important questions remain largely unanswered. In this work,…

Computation and Language · Computer Science 2021-09-28 Samuel Stevens , Yu Su

Traditional NLP has long held (supervised) syntactic parsing necessary for successful higher-level semantic language understanding (LU). The recent advent of end-to-end neural models, self-supervised via language modeling (LM), and their…

Computation and Language · Computer Science 2021-04-29 Goran Glavaš , Ivan Vulić

Previous studies investigating the syntactic abilities of deep learning models have not targeted the relationship between the strength of the grammatical generalization and the amount of evidence to which the model is exposed during…

Computation and Language · Computer Science 2020-11-05 Tristan Thrush , Ethan Wilcox , Roger Levy

Models need appropriate inductive biases to effectively learn from small amounts of data and generalize systematically outside of the training distribution. While Transformers are highly versatile and powerful, they can still benefit from…

Computation and Language · Computer Science 2024-07-08 Matthias Lindemann , Alexander Koller , Ivan Titov

For machine reading comprehension, the capacity of effectively modeling the linguistic knowledge from the detail-riddled and lengthy passages and getting ride of the noises is essential to improve its performance. Traditional attentive…

Computation and Language · Computer Science 2019-11-21 Zhuosheng Zhang , Yuwei Wu , Junru Zhou , Sufeng Duan , Hai Zhao , Rui Wang

In creating sentence embeddings for Natural Language Inference (NLI) tasks, using transformer-based models like BERT leads to high accuracy, but require hundreds of millions of parameters. These models take in sentences as a sequence of…

Computation and Language · Computer Science 2025-12-17 Jason Lunder

Building models that take advantage of the hierarchical structure of language without a priori annotation is a longstanding goal in natural language processing. We introduce such a model for the task of machine translation, pairing a…

Computation and Language · Computer Science 2017-09-07 James Bradbury , Richard Socher

Adhering to explicit length constraints, such as generating text with a precise word count, remains a significant challenge for Large Language Models (LLMs). This study aims at investigating the differences between foundation models and…

Computation and Language · Computer Science 2025-09-03 Elisabetta Rocchetti , Alfio Ferrara

English news headlines form a register with unique syntactic properties that have been documented in linguistics literature since the 1930s. However, headlines have received surprisingly little attention from the NLP syntactic parsing…

Computation and Language · Computer Science 2023-01-26 Adrian Benton , Tianze Shi , Ozan İrsoy , Igor Malioutov

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

In this work, we extend the Bidirectional Encoder Representations from Transformers (BERT) with an emphasis on directed coattention to obtain an improved F1 performance on the SQUAD2.0 dataset. The Transformer architecture on which BERT is…

Computation and Language · Computer Science 2019-12-24 Ankit Chadha , Rewa Sood