English
Related papers

Related papers: Frequency Effects on Syntactic Rule Learning in Tr…

200 papers

Transformer-based models have revolutionized the field of natural language processing. To understand why they perform so well and to assess their reliability, several studies have focused on questions such as: Which linguistic properties…

Computation and Language · Computer Science 2025-11-04 Akhilesh Aravapalli , Mounika Marreddy , Radhika Mamidi , Manish Gupta , Subba Reddy Oota

Standard pretrained language models operate on sequences of subword tokens without direct access to the characters that compose each token's string representation. We probe the embedding layer of pretrained language models and show that…

Computation and Language · Computer Science 2022-06-09 Itay Itzhak , Omer Levy

In a spoken multiple-choice question answering (SMCQA) task, given a passage, a question, and multiple choices all in the form of speech, the machine needs to pick the correct choice to answer the question. While the audio could contain…

Computation and Language · Computer Science 2020-05-26 Chia-Chih Kuo , Shang-Bao Luo , Kuan-Yu Chen

Unsupervised pretraining models have been shown to facilitate a wide range of downstream NLP applications. These models, however, retain some of the limitations of traditional static word embeddings. In particular, they encode only the…

Computation and Language · Computer Science 2020-04-21 Anne Lauscher , Ivan Vulić , Edoardo Maria Ponti , Anna Korhonen , Goran Glavaš

This work describes experiments which probe the hidden representations of several BERT-style models for morphological content. The goal is to examine the extent to which discrete linguistic structure, in the form of morphological features…

Computation and Language · Computer Science 2020-04-08 Daniel Edmiston

We study the settings for which deep contextual embeddings (e.g., BERT) give large improvements in performance relative to classic pretrained embeddings (e.g., GloVe), and an even simpler baseline---random word embeddings---focusing on the…

Computation and Language · Computer Science 2020-05-20 Simran Arora , Avner May , Jian Zhang , Christopher Ré

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

How do typological properties such as word order and morphological case marking affect the ability of neural sequence models to acquire the syntax of a language? Cross-linguistic comparisons of RNNs' syntactic performance (e.g., on…

Computation and Language · Computer Science 2019-03-28 Shauli Ravfogel , Yoav Goldberg , Tal Linzen

LSTM-based recurrent neural networks are the state-of-the-art for many natural language processing (NLP) tasks. Despite their performance, it is unclear whether, or how, LSTMs learn structural features of natural languages such as…

Computation and Language · Computer Science 2020-05-05 Kaiji Lu , Piotr Mardziel , Klas Leino , Matt Fedrikson , Anupam Datta

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

Transformers-based pretrained language models achieve outstanding results in many well-known NLU benchmarks. However, while pretraining methods are very convenient, they are expensive in terms of time and resources. This calls for a study…

Computation and Language · Computer Science 2021-09-10 Laura Pérez-Mayos , Miguel Ballesteros , Leo Wanner

In this work we show how large language models (LLMs) can learn statistical dependencies between otherwise unconditionally independent variables due to dataset selection bias. To demonstrate the effect, we developed a masked gender task…

Computation and Language · Computer Science 2022-07-20 Emily McMilin

Even though BERT achieves successful performance improvements in various supervised learning tasks, applying BERT for unsupervised tasks still holds a limitation that it requires repetitive inference for computing contextual language…

Computation and Language · Computer Science 2020-04-20 Joongbo Shin , Yoonhyung Lee , Seunghyun Yoon , Kyomin Jung

Relation prediction in knowledge graphs is dominated by embedding based methods which mainly focus on the transductive setting. Unfortunately, they are not able to handle inductive learning where unseen entities and relations are present…

Computation and Language · Computer Science 2021-03-15 Hanwen Zha , Zhiyu Chen , Xifeng Yan

The main approaches to sentiment analysis are rule-based methods and ma-chine learning, in particular, deep neural network models with the Trans-former architecture, including BERT. The performance of neural network models in the tasks of…

Computation and Language · Computer Science 2021-11-22 Elena Razova , Sergey Vychegzhanin , Evgeny Kotelnikov

A well formed query is defined as a query which is formulated in the manner of an inquiry, and with correct interrogatives, spelling and grammar. While identifying well formed queries is an important task, few works have attempted to…

Computation and Language · Computer Science 2022-08-23 Avinash Madasu , Anvesh Rao Vijjini

Large neural language models are steadily contributing state-of-the-art performance to question answering and other natural language and information processing tasks. These models are expensive to train. We propose to evaluate whether such…

Computation and Language · Computer Science 2022-05-24 Fangyi Zhu , Lok You Tan , See-Kiong Ng , Stéphane Bressan

In this paper, we explore the idea of analysing the historical bias of contextual language models based on BERT by measuring their adequacy with respect to Early Modern (EME) and Modern (ME) English. In our preliminary experiments, we…

Computation and Language · Computer Science 2024-02-08 Miriam Cuscito , Alfio Ferrara , Martin Ruskov

If the same neural network architecture is trained multiple times on the same dataset, will it make similar linguistic generalizations across runs? To study this question, we fine-tuned 100 instances of BERT on the Multi-genre Natural…

Computation and Language · Computer Science 2020-11-17 R. Thomas McCoy , Junghyun Min , Tal Linzen

E-commerce platforms generate vast amounts of customer behavior data, such as clicks and purchases, from millions of unique users every day. However, effectively using this data for behavior understanding tasks is challenging because there…

Machine Learning · Computer Science 2022-02-16 Tianyu Li , Ali Cevahir , Derek Cho , Hao Gong , DuyKhuong Nguyen , Bjorn Stenger