Search Results for author: Dong Nguyen

Found 37 papers, 17 papers with code

Transforming Dutch: Debiasing Dutch Coreference Resolution Systems for Non-binary Pronouns

1 code implementation30 Apr 2024 Goya van Boven, Yupei Du, Dong Nguyen

We further show that CDA remains effective in low-resource settings, in which a limited set of debiasing documents is used.

coreference-resolution counterfactual +1

PATCH -- Psychometrics-AssisTed benCHmarking of Large Language Models: A Case Study of Mathematics Proficiency

no code implementations2 Apr 2024 Qixiang Fang, Daniel L. Oberski, Dong Nguyen

Third, we release 4 datasets to support measuring and comparing LLM proficiency in grade school mathematics and science against human populations.


FTFT: Efficient and Robust Fine-Tuning by Transferring Training Dynamics

1 code implementation10 Oct 2023 Yupei Du, Albert Gatt, Dong Nguyen

Dataset cartography is a simple yet effective dual-model approach that improves the robustness of fine-tuned PLMs.

Epicurus at SemEval-2023 Task 4: Improving Prediction of Human Values behind Arguments by Leveraging Their Definitions

1 code implementation27 Feb 2023 Christian Fang, Qixiang Fang, Dong Nguyen

We describe our experiments for SemEval-2023 Task 4 on the identification of human values behind arguments (ValueEval).

Measuring the Instability of Fine-Tuning

1 code implementation15 Feb 2023 Yupei Du, Dong Nguyen

Fine-tuning pre-trained language models on downstream tasks with varying random seeds has been shown to be unstable, especially on small datasets.

Template-based Abstractive Microblog Opinion Summarisation

no code implementations8 Aug 2022 Iman Munire Bilal, Bo wang, Adam Tsakalidis, Dong Nguyen, Rob Procter, Maria Liakata

We introduce the task of microblog opinion summarisation (MOS) and share a dataset of 3100 gold-standard opinion summaries to facilitate research in this domain.

Evaluating the Construct Validity of Text Embeddings with Application to Survey Questions

1 code implementation18 Feb 2022 Qixiang Fang, Dong Nguyen, Daniel L Oberski

Our results thus highlight the necessity to examine the construct validity of text embeddings before deploying them in social science research.

Sentence valid

Understanding Public Opinion on Using Hydroxychloroquine for COVID-19 Treatment via Social Media

2 code implementations1 Jan 2022 Thuy T. Do, Du Nguyen, Anh Le, Anh Nguyen, Dong Nguyen, Nga Hoang, Uyen Le, Tuan Tran

This paper studies the reactions of social network users on the recommendation of using HCQ for COVID-19 treatment by analyzing the reaction patterns and sentiment of the tweets.

Descriptive Sentiment Analysis

Assessing the Reliability of Word Embedding Gender Bias Measures

1 code implementation EMNLP 2021 Yupei Du, Qixiang Fang, Dong Nguyen

In this paper, we assess three types of reliability of word embedding gender bias measures, namely test-retest reliability, inter-rater consistency and internal consistency.

Word Embeddings

Introducing CAD: the Contextual Abuse Dataset

1 code implementation NAACL 2021 Bertie Vidgen, Dong Nguyen, Helen Margetts, Patricia Rossini, Rebekah Tromble

Online abuse can inflict harm on users and communities, making online spaces unsafe and toxic.

Do Word Embeddings Capture Spelling Variation?

1 code implementation COLING 2020 Dong Nguyen, Jack Grieve

Analyses of word embeddings have primarily focused on semantic and syntactic properties.

Word Embeddings

Better Early than Late: Fusing Topics with Word Embeddings for Neural Question Paraphrase Identification

no code implementations22 Jul 2020 Nicole Peinelt, Dong Nguyen, Maria Liakata

Question paraphrase identification is a key task in Community Question Answering (CQA) to determine if an incoming question has been previously asked.

Community Question Answering Paraphrase Identification +2

Room to Glo: A Systematic Comparison of Semantic Change Detection Approaches with Word Embeddings

no code implementations IJCNLP 2019 Philippa Shoemark, Farhana Ferdousi Liza, Dong Nguyen, Scott Hale, Barbara McGillivray

Word embeddings are increasingly used for the automatic detection of semantic change; yet, a robust evaluation and systematic comparison of the choices involved has been lacking.

Change Detection Time Series +2

How we do things with words: Analyzing text as social and cultural data

no code implementations2 Jul 2019 Dong Nguyen, Maria Liakata, Simon DeDeo, Jacob Eisenstein, David Mimno, Rebekah Tromble, Jane Winters

Second, we hope to provide a set of best practices for working with thick social and cultural concepts.

Aiming beyond the Obvious: Identifying Non-Obvious Cases in Semantic Similarity Datasets

1 code implementation ACL 2019 Nicole Peinelt, Maria Liakata, Dong Nguyen

Existing datasets for scoring text pairs in terms of semantic similarity contain instances whose resolution differs according to the degree of difficulty.

Semantic Similarity Semantic Textual Similarity

Comparing Automatic and Human Evaluation of Local Explanations for Text Classification

no code implementations NAACL 2018 Dong Nguyen

Text classification models are becoming increasingly complex and opaque, however for many applications it is essential that the models are interpretable.

General Classification Recommendation Systems +2

Emo, Love, and God: Making Sense of Urban Dictionary, a Crowd-Sourced Online Dictionary

no code implementations22 Dec 2017 Dong Nguyen, Barbara McGillivray, Taha Yasseri

On the one hand, the promise of the "wisdom of the crowd" has inspired successful projects such as Wikipedia, which has become the primary source of crowd-based information in many languages.

A Kernel Independence Test for Geographical Language Variation

1 code implementation CL 2017 Dong Nguyen, Jacob Eisenstein

Quantifying the degree of spatial dependence for linguistic variables is a key task for analyzing dialectal variation.

Computational Sociolinguistics: A Survey

no code implementations30 Aug 2015 Dong Nguyen, A. Seza Doğruöz, Carolyn P. Rosé, Franciska de Jong

Language is a social phenomenon and variation is inherent to its social nature.

Cannot find the paper you are looking for? You can Submit a new open access paper.