arXiv subjects

Isabelle Augenstein

Publications and source records attributed to Isabelle Augenstein.

At least 109 records · Page 6Linked to original sources

arXiv2021

Towards Explainable Fact Checking

The past decade has seen a substantial rise in the amount of mis- and disinformation online, from targeted disinformation campaigns to influence politics, to the unintentional spreading of misinformation about public health. This development has spurred research in the area of automatic fact checking, from approaches to detect check-worthy claims and determining the stance of tweets towards claims, to methods to determine the veracity of claims given evidence documents. These automatic methods are often content-based, using natural language processing methods, which in turn utilise deep neural networks to learn higher-order features from text in order to make predictions. As deep neural networks are black-box models, their inner workings cannot be easily explained. At the same time, it is desirable to explain how they arrive at certain decisions, especially if they are to be used for decision making. While this has been known for some time, the issues this raises have been exacerbated by models increasing in size, and by EU legislation requiring models to be used for decision making to provide explanations, and, very recently, by legislation requiring online platforms operating in the EU to provide transparent reporting on their services. Despite this, current solutions for explainability are still lacking in the area of fact checking. This thesis presents my research on automatic fact checking, including claim check-worthiness detection, stance detection and veracity prediction. Its contributions go beyond fact checking, with the thesis proposing more general machine learning solutions for natural language processing in the area of learning with limited labelled data. Finally, the thesis presents some first solutions for explainable fact checking.

cs.CL↗

arXiv2021

How Does Counterfactually Augmented Data Impact Models for Social Computing Constructs?

As NLP models are increasingly deployed in socially situated settings such as online abusive content detection, it is crucial to ensure that these models are robust. One way of improving model robustness is to generate counterfactually augmented data (CAD) for training models that can better learn to distinguish between core features and data artifacts. While models trained on this type of data have shown promising out-of-domain generalizability, it is still unclear what the sources of such improvements are. We investigate the benefits of CAD for social NLP models by focusing on three social computing constructs -- sentiment, sexism, and hate speech. Assessing the performance of models trained with and without CAD across different types of datasets, we find that while models trained on CAD show lower in-domain performance, they generalize better out-of-domain. We unpack this apparent discrepancy using machine explanations and find that CAD reduces model reliance on spurious features. Leveraging a novel typology of CAD to analyze their relationship with model performance, we find that CAD which acts on the construct directly or a diverse set of CAD leads to higher performance.

cs.CY↗

arXiv2021

Cross-Domain Label-Adaptive Stance Detection

Stance detection concerns the classification of a writer's viewpoint towards a target. There are different task variants, e.g., stance of a tweet vs. a full article, or stance with respect to a claim vs. an (implicit) topic. Moreover, task definitions vary, which includes the label inventory, the data collection, and the annotation protocol. All these aspects hinder cross-domain studies, as they require changes to standard domain adaptation approaches. In this paper, we perform an in-depth analysis of 16 stance detection datasets, and we explore the possibility for cross-domain learning from them. Moreover, we propose an end-to-end unsupervised framework for out-of-domain prediction of unseen, user-defined labels. In particular, we combine domain adaptation techniques such as mixture of experts and domain-adversarial training with label embeddings, and we demonstrate sizable performance gains over strong baselines, both (i) in-domain, i.e., for seen targets, and (ii) out-of-domain, i.e., for unseen targets. Finally, we perform an exhaustive analysis of the cross-domain results, and we highlight the important factors influencing the model performance.

cs.CL↗

arXiv2021

Time-Aware Evidence Ranking for Fact-Checking

Truth can vary over time. Fact-checking decisions on claim veracity should therefore take into account temporal information of both the claim and supporting or refuting evidence. In this work, we investigate the hypothesis that the timestamp of a Web page is crucial to how it should be ranked for a given claim. We delineate four temporal ranking methods that constrain evidence ranking differently and simulate hypothesis-specific evidence rankings given the evidence timestamps as gold standard. Evidence ranking in three fact-checking models is ultimately optimized using a learning-to-rank loss function. Our study reveals that time-aware evidence ranking not only surpasses relevance assumptions based purely on semantic similarity or position in a search results list, but also improves veracity predictions of time-sensitive claims in particular.

cs.CL↗

arXiv2021

Diagnostics-Guided Explanation Generation

Explanations shed light on a machine learning model's rationales and can aid in identifying deficiencies in its reasoning process. Explanation generation models are typically trained in a supervised way given human explanations. When such annotations are not available, explanations are often selected as those portions of the input that maximise a downstream task's performance, which corresponds to optimising an explanation's Faithfulness to a given model. Faithfulness is one of several so-called diagnostic properties, which prior work has identified as useful for gauging the quality of an explanation without requiring annotations. Other diagnostic properties are Data Consistency, which measures how similar explanations are for similar input instances, and Confidence Indication, which shows whether the explanation reflects the confidence of the model. In this work, we show how to directly optimise for these diagnostic properties when training a model to generate sentence-level explanations, which markedly improves explanation quality, agreement with human rationales, and downstream task performance on three complex reasoning tasks.

cs.LG↗

arXiv2021

Semi-Supervised Exaggeration Detection of Health Science Press Releases

Public trust in science depends on honest and factual communication of scientific papers. However, recent studies have demonstrated a tendency of news media to misrepresent scientific papers by exaggerating their findings. Given this, we present a formalization of and study into the problem of exaggeration detection in science communication. While there are an abundance of scientific papers and popular media articles written about them, very rarely do the articles include a direct link to the original paper, making data collection challenging. We address this by curating a set of labeled press release/abstract pairs from existing expert annotated studies on exaggeration in press releases of scientific papers suitable for benchmarking the performance of machine learning models on the task. Using limited data from this and previous studies on exaggeration detection in science, we introduce MT-PET, a multi-task version of Pattern Exploiting Training (PET), which leverages knowledge from complementary cloze-style QA tasks to improve few-shot learning. We demonstrate that MT-PET outperforms PET and supervised learning both when data is limited, as well as when there is an abundance of data for the main task.

cs.CL↗

arXiv2021

Inducing Language-Agnostic Multilingual Representations

Cross-lingual representations have the potential to make NLP techniques available to the vast majority of languages in the world. However, they currently require large pretraining corpora or access to typologically similar languages. In this work, we address these obstacles by removing language identity signals from multilingual embeddings. We examine three approaches for this: (i) re-aligning the vector spaces of target languages (all together) to a pivot source language; (ii) removing language-specific means and variances, which yields better discriminativeness of embeddings as a by-product; and (iii) increasing input similarity across languages by removing morphological contractions and sentence reordering. We evaluate on XNLI and reference-free MT across 19 typologically diverse languages. Our findings expose the limitations of these approaches -- unlike vector normalization, vector space re-alignment and text normalization do not achieve consistent gains across encoders and languages. Due to the approaches' additive effects, their combination decreases the cross-lingual transfer gap by 8.9 points (m-BERT) and 18.2 points (XLM-R) on average across all tasks and languages, however. Our code and models are publicly available.

cs.CL↗

arXiv2021

Joint Emotion Label Space Modelling for Affect Lexica

Emotion lexica are commonly used resources to combat data poverty in automatic emotion detection. However, vocabulary coverage issues, differences in construction method and discrepancies in emotion framework and representation result in a heterogeneous landscape of emotion detection resources, calling for a unified approach to utilising them. To combat this, we present an extended emotion lexicon of 30,273 unique entries, which is a result of merging eight existing emotion lexica by means of a multi-view variational autoencoder (VAE). We showed that a VAE is a valid approach for combining lexica with different label spaces into a joint emotion label space with a chosen number of dimensions, and that these dimensions are still interpretable. We tested the utility of the unified VAE lexicon by employing the lexicon values as features in an emotion detection model. We found that the VAE lexicon outperformed individual lexica, but contrary to our expectations, it did not outperform a naive concatenation of lexica, although it did contribute to the naive concatenation when added as an extra lexicon. Furthermore, using lexicon information as additional features on top of state-of-the-art language models usually resulted in a better performance than when no lexicon information was used.

cs.CL↗

arXiv2021

Is Sparse Attention more Interpretable?

Sparse attention has been claimed to increase model interpretability under the assumption that it highlights influential inputs. Yet the attention distribution is typically over representations internal to the model rather than the inputs themselves, suggesting this assumption may not have merit. We build on the recent work exploring the interpretability of attention; we design a set of experiments to help us understand how sparsity affects our ability to use attention as an explainability tool. On three text classification tasks, we verify that only a weak relationship between inputs and co-indexed intermediate representations exists -- under sparse attention and otherwise. Further, we do not find any plausible mappings from sparse attention distributions to a sparse set of influential inputs through other avenues. Rather, we observe in this setting that inducing sparsity may make it less plausible that attention can be used as a tool for understanding model behavior.

cs.CL↗

arXiv2021

Multi-Hop Fact Checking of Political Claims

Recent work has proposed multi-hop models and datasets for studying complex natural language reasoning. One notable task requiring multi-hop reasoning is fact checking, where a set of connected evidence pieces leads to the final verdict of a claim. However, existing datasets either do not provide annotations for gold evidence pages, or the only dataset which does (FEVER) mostly consists of claims which can be fact-checked with simple reasoning and is constructed artificially. Here, we study more complex claim verification of naturally occurring claims with multiple hops over interconnected evidence chunks. We: 1) construct a small annotated dataset, PolitiHop, of evidence sentences for claim verification; 2) compare it to existing multi-hop datasets; and 3) study how to transfer knowledge from more extensive in- and out-of-domain resources to PolitiHop. We find that the task is complex and achieve the best performance with an architecture that specifically models reasoning over evidence pieces in combination with in-domain transfer learning.

cs.CL↗

arXiv2021

Determining the Credibility of Science Communication

Most work on scholarly document processing assumes that the information processed is trustworthy and factually correct. However, this is not always the case. There are two core challenges, which should be addressed: 1) ensuring that scientific publications are credible -- e.g. that claims are not made without supporting evidence, and that all relevant supporting evidence is provided; and 2) that scientific findings are not misrepresented, distorted or outright misreported when communicated by journalists or the general public. I will present some first steps towards addressing these problems and outline remaining challenges.

cs.DL↗

arXiv2021

CiteWorth: Cite-Worthiness Detection for Improved Scientific Document Understanding

Scientific document understanding is challenging as the data is highly domain specific and diverse. However, datasets for tasks with scientific text require expensive manual annotation and tend to be small and limited to only one or a few fields. At the same time, scientific documents contain many potential training signals, such as citations, which can be used to build large labelled datasets. Given this, we present an in-depth study of cite-worthiness detection in English, where a sentence is labelled for whether or not it cites an external source. To accomplish this, we introduce CiteWorth, a large, contextualized, rigorously cleaned labelled dataset for cite-worthiness detection built from a massive corpus of extracted plain-text scientific documents. We show that CiteWorth is high-quality, challenging, and suitable for studying problems such as domain adaptation. Our best performing cite-worthiness detection model is a paragraph-level contextualized sentence labelling model based on Longformer, exhibiting a 5 F1 point improvement over SciBERT which considers only individual sentences. Finally, we demonstrate that language model fine-tuning with cite-worthiness as a secondary task leads to improved performance on downstream scientific document understanding tasks.

cs.CL↗

arXiv2021

Data-Efficient Pretraining via Contrastive Self-Supervision

For natural language processing `text-to-text' tasks, the prevailing approaches heavily rely on pretraining large self-supervised models on increasingly larger `task-external' data. Transfer learning from high-resource pretraining works well, but research has focused on settings with very large data and compute requirements, while the potential of efficient low-resource learning, without large `task-external' pretraining, remains under-explored. In this work, we evaluate against three core challenges for resource efficient learning. Namely, we analyze: (1) pretraining data ($X$) efficiency; (2) zero to few-shot label ($Y$) efficiency; and (3) long-tail generalization, since long-tail preservation has been linked to algorithmic fairness and because data in the tail is limited by definition. To address these challenges, we propose a data and compute efficient self-supervised, contrastive text encoder, pretrained on 60MB of `task-internal' text data, and compare it to RoBERTa, which was pretrained on 160GB of `task-external' text. We find our method outperforms RoBERTa, while pretraining and fine-tuning in a 1/5th of RoBERTa's fine-tuning time.

cs.CL↗

arXiv2021

Longitudinal Citation Prediction using Temporal Graph Neural Networks

Citation count prediction is the task of predicting the number of citations a paper has gained after a period of time. Prior work viewed this as a static prediction task. As papers and their citations evolve over time, considering the dynamics of the number of citations a paper will receive would seem logical. Here, we introduce the task of sequence citation prediction. The goal is to accurately predict the trajectory of the number of citations a scholarly work receives over time. We propose to view papers as a structured network of citations, allowing us to use topological information as a learning signal. Additionally, we learn how this dynamic citation network changes over time and the impact of paper meta-data such as authors, venues and abstracts. To approach the new task, we derive a dynamic citation network from Semantic Scholar spanning over 42 years. We present a model which exploits topological and temporal information using graph convolution networks paired with sequence prediction, and compare it against multiple baselines, testing the importance of topological and temporal information and analyzing model performance. Our experiments show that leveraging both the temporal and topological information greatly increases the performance of predicting citation counts over time.

cs.CL↗

arXiv2021

University of Copenhagen Participation in TREC Health Misinformation Track 2020

In this paper, we describe our participation in the TREC Health Misinformation Track 2020. We submitted $11$ runs to the Total Recall Task and 13 runs to the Ad Hoc task. Our approach consists of 3 steps: (1) we create an initial run with BM25 and RM3; (2) we estimate credibility and misinformation scores for the documents in the initial run; (3) we merge the relevance, credibility and misinformation scores to re-rank documents in the initial run. To estimate credibility scores, we implement a classifier which exploits features based on the content and the popularity of a document. To compute the misinformation score, we apply a stance detection approach with a pretrained Transformer language model. Finally, we use different approaches to merge scores: weighted average, the distance among score vectors and rank fusion.

cs.IR↗

arXiv2021

A Primer on Contrastive Pretraining in Language Processing: Methods, Lessons Learned and Perspectives

Modern natural language processing (NLP) methods employ self-supervised pretraining objectives such as masked language modeling to boost the performance of various application tasks. These pretraining methods are frequently extended with recurrence, adversarial or linguistic property masking, and more recently with contrastive learning objectives. Contrastive self-supervised training objectives enabled recent successes in image representation pretraining by learning to contrast input-input pairs of augmented images as either similar or dissimilar. However, in NLP, automated creation of text input augmentations is still very challenging because a single token can invert the meaning of a sentence. For this reason, some contrastive NLP pretraining methods contrast over input-label pairs, rather than over input-input pairs, using methods from Metric Learning and Energy Based Models. In this survey, we summarize recent self-supervised and supervised contrastive NLP pretraining methods and describe where they are used to improve language modeling, few or zero-shot learning, pretraining data-efficiency and specific NLP end-tasks. We introduce key contrastive learning concepts with lessons learned from prior research and structure works by applications and cross-field relations. Finally, we point to open challenges and future directions for contrastive NLP to encourage bringing contrastive NLP pretraining closer to recent successes in image representation pretraining.

cs.CL↗

arXiv2021

Does Typological Blinding Impede Cross-Lingual Sharing?

Bridging the performance gap between high- and low-resource languages has been the focus of much previous work. Typological features from databases such as the World Atlas of Language Structures (WALS) are a prime candidate for this, as such data exists even for very low-resource languages. However, previous work has only found minor benefits from using typological information. Our hypothesis is that a model trained in a cross-lingual setting will pick up on typological cues from the input data, thus overshadowing the utility of explicitly using such features. We verify this hypothesis by blinding a model to typological information, and investigate how cross-lingual sharing and performance is impacted. Our model is based on a cross-lingual architecture in which the latent weights governing the sharing between languages is learnt during training. We show that (i) preventing this model from exploiting typology severely reduces performance, while a control experiment reaffirms that (ii) encouraging sharing according to typology somewhat improves performance.

cs.CL↗

arXiv2021

Disembodied Machine Learning: On the Illusion of Objectivity in NLP

Machine Learning seeks to identify and encode bodies of knowledge within provided datasets. However, data encodes subjective content, which determines the possible outcomes of the models trained on it. Because such subjectivity enables marginalisation of parts of society, it is termed (social) `bias' and sought to be removed. In this paper, we contextualise this discourse of bias in the ML community against the subjective choices in the development process. Through a consideration of how choices in data and model development construct subjectivity, or biases that are represented in a model, we argue that addressing and mitigating biases is near-impossible. This is because both data and ML models are objects for which meaning is made in each step of the development pipeline, from data selection over annotation to model training and analysis. Accordingly, we find the prevalent discourse of bias limiting in its ability to address social marginalisation. We recommend to be conscientious of this, and to accept that de-biasing methods only correct for a fraction of biases.

cs.AI↗