Lista de obras - Isabelle Augenstein - Dominio Público Uruguay

A Diagnostic Study of Explainability Techniques for Text Classification ⬇️

A Latent-Variable Model for Intrinsic Probing

artículo científico publicado en 2023

A Probabilistic Generative Model of Linguistic Typology

A Supervised Approach to Extractive Summarisation of Scientific Papers

artículo científico publicado en 2017

A simple but tough-to-beat baseline for the Fake News Challenge stance detection task ⬇️

article

Adapting Neural Link Predictors for Data-Efficient Complex Query Answering ⬇️

artículo científico publicado en 2023

An Unsupervised Data-driven Method To Discover Equivalent Relations In Large Linked Datasets

article published in the Semantic Web Journal

Back to the Future -- Sequential Alignment of Text Representations ⬇️

artículo científico publicado en 2019

Back to the Future – Temporal Adaptation of Text Representations

artículo científico publicado en 2020

CiteWorth: Cite-Worthiness Detection for Improved Scientific Document Understanding ⬇️

Claim Check-Worthiness Detection as Positive Unlabelled Learning ⬇️

artículo científico publicado en 2020

DYNAMICQA: Tracing Internal Knowledge Conflicts in Language Models ⬇️

Detecting Harmful Content on Online Platforms: What Platforms Need vs. Where Research Efforts Go

scientific article published on 07 June 2023

Determining the Credibility of Science Communication ⬇️

Diagnostics-Guided Explanation Generation ⬇️

artículo científico publicado en 2021

Discourse-aware rumour stance classification in social media using sequential classifiers

artículo científico publicado en 2018

Distantly Supervised Web Relation Extraction For Knowledge Base Population

article published in the Semantic Web Journal

Does Typological Blinding Impede Cross-Lingual Sharing? ⬇️

Evaluating Input Feature Explanations through a Unified Diagnostic Evaluation Framework ⬇️

artículo científico publicado en 2024

Explaining Interactions Between Text Spans ⬇️

Extracting Relations between Non-Standard Entities using Distant Supervision and Imitation Learning

artículo científico publicado en 2015

Factuality Challenges in the Era of Large Language Models ⬇️

artículo científico publicado en 2023

Factuality challenges in the era of large language models and opportunities for fact-checking

artículo científico publicado en 2024

Faithfulness Tests for Natural Language Explanations

Few-Shot Cross-Lingual Stance Detection with Sentiment-Based Pre-Training ⬇️

artículo científico publicado en 2021

From Phonology to Syntax: Unsupervised Linguistic Typology at Different Levels with Language Embeddings ⬇️

artículo científico publicado en 2018

Generalisation in named entity recognition: A quantitative analysis

artículo científico publicado en 2017

Generating Fact Checking Explanations ⬇️

Generating Label Cohesive and Well-Formed Adversarial Claims ⬇️

artículo científico publicado en 2020

Habilitation Abstract: Towards Explainable Fact Checking

artículo científico publicado en 2022

Inducing Language-Agnostic Multilingual Representations

Information fusion as an integrative cross-cutting enabler to achieve robust, explainable, and trustworthy medical artificial intelligence

artículo científico publicado en 2022

Introduction to the Special Issue on Truth and Trust Online

artículo científico publicado en 2023

Investigating Human Values in Online Communities ⬇️

artículo científico publicado en 2024

Investigating the Impact of Model Instability on Explanations and Uncertainty ⬇️

artículo científico publicado en 2024

Is Sparse Attention more Interpretable? ⬇️

Joint Information Extraction from the Web Using Linked Data

artículo científico publicado en 2014

LODifier: Generating Linked Data from Unstructured Text

artículo científico publicado en 2012

Latent Multi-task Architecture Learning ⬇️

Linked data as background knowledge for information extraction on the web

Mapping Keywords to Linked Data Resources for Automatic Query Expansion

Measuring Gender Bias in West Slavic Language Models

Measuring and Benchmarking Large Language Models' Capabilities to Generate Persuasive Language ⬇️

artículo científico publicado en 2024

Multi-Hop Fact Checking of Political Claims ⬇️

Multi-Task Learning of Keyphrase Boundary Classification ⬇️

artículo científico publicado en 2017

Multi-task Learning of Pairwise Sequence Classification Tasks Over Disparate Label Spaces ⬇️

artículo científico publicado en 2018

MultiFC: A Real-World Multi-Domain Dataset for Evidence-Based Fact Checking of Claims ⬇️

Multilingual Event Extraction from Historical Newspaper Adverts

Natural Language Processing for the Semantic Web

book edition published in 2016

Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddings ⬇️

artículo científico publicado en 2022

Numerically Grounded Language Models for Semantic Error Correction

artículo científico publicado en 2016

PHD: Pixel-Based Language Modeling of Historical Documents ⬇️

People Make Better Edits: Measuring the Efficacy of LLM-Generated Counterfactually Augmented Data for Harmful Language Detection

Probing Pre-Trained Language Models for Cross-Cultural Differences in Values ⬇️

QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension

artículo científico publicado en 2022

Quantifying gender bias towards politicians in cross-lingual language models

artículo científico publicado en 2023

Relation Extraction from the Web Using Distant Supervision

Revealing the Parametric Knowledge of Language Models: A Unified Framework for Attribution Methods ⬇️

artículo científico publicado en 2024

Seed Selection for Distantly Supervised Web-Based Relation Extraction

artículo científico publicado en 2014

SemEval 2017 Task 10: ScienceIE - Extracting Keyphrases and Relations from Scientific Publications ⬇️

Semantic Sensitivities and Inconsistent Predictions: Measuring the Fragility of NLI Models ⬇️

artículo científico publicado en 2024

Semi-Supervised Exaggeration Detection of Health Science Press Releases ⬇️

Show Me the Work: Fact-Checkers' Requirements for Explainable Automated Fact-Checking ⬇️

artículo científico publicado en 2025

Specializing Large Language Models to Simulate Survey Response Distributions for Global Populations ⬇️

artículo científico publicado en 2025

Stance Detection with Bidirectional Conditional Encoding ⬇️

artículo científico publicado en 2016

Statistical Knowledge Patterns: Identifying Synonymous Relations in Large Linked Datasets

artículo científico publicado en 2013

The LEADING Guideline. Reporting Standards for Expert Panel, Best-Estimate Diagnosis, and Longitudinal Expert All Data (LEAD) Studies

Time-aware evidence ranking for fact-checking

Topic-Guided Sampling For Data-Efficient Multi-Domain Stance Detection ⬇️

conference paper published in 2023

Towards Explainable Fact Checking ⬇️

artículo científico publicado en 2021

Tracking Typological Traits of Uralic Languages in Distributed Language Representations ⬇️

Transformer Based Multi-Source Domain Adaptation

USFD at SemEval-2016 Task 6: Any-Target Stance Detection on Twitter with Autoencoders ⬇️

artículo científico publicado en 2016

USFD: Twitter NER with Drift Compensation and Linked Data

artículo científico publicado en 2015

Understanding Fine-grained Distortions in Reports of Scientific Findings ⬇️

artículo científico publicado en 2024

Unsupervised Discovery of Gendered Language through Latent-Variable Modeling ⬇️

artículo científico publicado en 2019

Unsupervised wrapper induction using linked data

What Can We Do to Improve Peer Review in NLP? ⬇️

artículo científico publicado en 2020

What do Language Representations Really Represent? ⬇️

Why Should This Article Be Deleted? Transparent Stance Detection in Multilingual Wikipedia Editor Discussions ⬇️

artículo científico publicado en 2023

Why Should This Article Be Deleted? Transparent Stance Detection in Multilingual Wikipedia Editor Discussions ⬇️

X-WikiRE: A Large, Multilingual Resource for Relation Extraction as Machine Comprehension ⬇️

artículo científico publicado en 2019

emoji2vec: Learning Emoji Representations from their Description ⬇️

artículo científico publicado en 2016

Web relation extraction with distant supervision ⬇️

tesis doctoral

Lista de obras de Isabelle Augenstein

A Diagnostic Study of Explainability Techniques for Text Classification ⬇️

A Latent-Variable Model for Intrinsic Probing

A Probabilistic Generative Model of Linguistic Typology

A Supervised Approach to Extractive Summarisation of Scientific Papers

A simple but tough-to-beat baseline for the Fake News Challenge stance detection task ⬇️

Adapting Neural Link Predictors for Data-Efficient Complex Query Answering ⬇️

An Unsupervised Data-driven Method To Discover Equivalent Relations In Large Linked Datasets

Back to the Future -- Sequential Alignment of Text Representations ⬇️

Back to the Future – Temporal Adaptation of Text Representations

CiteWorth: Cite-Worthiness Detection for Improved Scientific Document Understanding ⬇️

Claim Check-Worthiness Detection as Positive Unlabelled Learning ⬇️

DYNAMICQA: Tracing Internal Knowledge Conflicts in Language Models ⬇️

Detecting Harmful Content on Online Platforms: What Platforms Need vs. Where Research Efforts Go

Determining the Credibility of Science Communication ⬇️

Diagnostics-Guided Explanation Generation ⬇️

Discourse-aware rumour stance classification in social media using sequential classifiers

Distantly Supervised Web Relation Extraction For Knowledge Base Population

Does Typological Blinding Impede Cross-Lingual Sharing? ⬇️

Evaluating Input Feature Explanations through a Unified Diagnostic Evaluation Framework ⬇️

Explaining Interactions Between Text Spans ⬇️

Explaining Interactions Between Text Spans ⬇️

Extracting Relations between Non-Standard Entities using Distant Supervision and Imitation Learning

Factuality Challenges in the Era of Large Language Models ⬇️

Factuality challenges in the era of large language models and opportunities for fact-checking

Faithfulness Tests for Natural Language Explanations

Few-Shot Cross-Lingual Stance Detection with Sentiment-Based Pre-Training ⬇️

From Phonology to Syntax: Unsupervised Linguistic Typology at Different Levels with Language Embeddings ⬇️

Generalisation in named entity recognition: A quantitative analysis

Generating Fact Checking Explanations ⬇️

Generating Label Cohesive and Well-Formed Adversarial Claims ⬇️

Habilitation Abstract: Towards Explainable Fact Checking

Inducing Language-Agnostic Multilingual Representations

Information fusion as an integrative cross-cutting enabler to achieve robust, explainable, and trustworthy medical artificial intelligence

Introduction to the Special Issue on Truth and Trust Online

Investigating Human Values in Online Communities ⬇️

Investigating the Impact of Model Instability on Explanations and Uncertainty ⬇️

Is Sparse Attention more Interpretable? ⬇️

Joint Information Extraction from the Web Using Linked Data

LODifier: Generating Linked Data from Unstructured Text

Latent Multi-task Architecture Learning ⬇️

Linked data as background knowledge for information extraction on the web

Mapping Keywords to Linked Data Resources for Automatic Query Expansion

Measuring Gender Bias in West Slavic Language Models

Measuring and Benchmarking Large Language Models' Capabilities to Generate Persuasive Language ⬇️

Multi-Hop Fact Checking of Political Claims ⬇️

Multi-Task Learning of Keyphrase Boundary Classification ⬇️

Multi-task Learning of Pairwise Sequence Classification Tasks Over Disparate Label Spaces ⬇️

MultiFC: A Real-World Multi-Domain Dataset for Evidence-Based Fact Checking of Claims ⬇️

Multilingual Event Extraction from Historical Newspaper Adverts

Natural Language Processing for the Semantic Web

Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddings ⬇️

Numerically Grounded Language Models for Semantic Error Correction

PHD: Pixel-Based Language Modeling of Historical Documents ⬇️

People Make Better Edits: Measuring the Efficacy of LLM-Generated Counterfactually Augmented Data for Harmful Language Detection

Probing Pre-Trained Language Models for Cross-Cultural Differences in Values ⬇️

QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension

Quantifying gender bias towards politicians in cross-lingual language models

Relation Extraction from the Web Using Distant Supervision

Revealing the Parametric Knowledge of Language Models: A Unified Framework for Attribution Methods ⬇️

Seed Selection for Distantly Supervised Web-Based Relation Extraction

SemEval 2017 Task 10: ScienceIE - Extracting Keyphrases and Relations from Scientific Publications ⬇️

Semantic Sensitivities and Inconsistent Predictions: Measuring the Fragility of NLI Models ⬇️

Semi-Supervised Exaggeration Detection of Health Science Press Releases ⬇️

Show Me the Work: Fact-Checkers' Requirements for Explainable Automated Fact-Checking ⬇️

Specializing Large Language Models to Simulate Survey Response Distributions for Global Populations ⬇️

Stance Detection with Bidirectional Conditional Encoding ⬇️

Statistical Knowledge Patterns: Identifying Synonymous Relations in Large Linked Datasets

The LEADING Guideline. Reporting Standards for Expert Panel, Best-Estimate Diagnosis, and Longitudinal Expert All Data (LEAD) Studies

Time-aware evidence ranking for fact-checking

Topic-Guided Sampling For Data-Efficient Multi-Domain Stance Detection ⬇️

Towards Explainable Fact Checking ⬇️

Tracking Typological Traits of Uralic Languages in Distributed Language Representations ⬇️

Transformer Based Multi-Source Domain Adaptation

USFD at SemEval-2016 Task 6: Any-Target Stance Detection on Twitter with Autoencoders ⬇️

USFD: Twitter NER with Drift Compensation and Linked Data

Understanding Fine-grained Distortions in Reports of Scientific Findings ⬇️

Unsupervised Discovery of Gendered Language through Latent-Variable Modeling ⬇️

Unsupervised wrapper induction using linked data

What Can We Do to Improve Peer Review in NLP? ⬇️