Imperial College London

ProfessorFrancescaToni

Faculty of EngineeringDepartment of Computing

Professor in Computational Logic
 
 
 
//

Contact

 

+44 (0)20 7594 8228f.toni Website

 
 
//

Location

 

430Huxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Publication Type
Year
to

351 results found

Rago A, Cocarascu O, Bechlivanidis C, Toni Fet al., 2021, Argumentation as a framework for interactive explanations for recommendations, KR 2020, 17th International Conference on Principles of Knowledge Representation and Reasoning, Publisher: IJCAI, Pages: 805-815, ISSN: 2334-1033

As AI systems become ever more intertwined in our personallives, the way in which they explain themselves to and inter-act with humans is an increasingly critical research area. Theexplanation of recommendations is, thus a pivotal function-ality in a user’s experience of a recommender system (RS),providing the possibility of enhancing many of its desirablefeatures in addition to itseffectiveness(accuracy wrt users’preferences). For an RS that we prove empirically is effective,we show how argumentative abstractions underpinning rec-ommendations can provide the structural scaffolding for (dif-ferent types of) interactive explanations (IEs), i.e. explana-tions empowering interactions with users. We prove formallythat these IEs empower feedback mechanisms that guaranteethat recommendations will improve with time, hence render-ing the RSscrutable. Finally, we prove experimentally thatthe various forms of IE (tabular, textual and conversational)inducetrustin the recommendations and provide a high de-gree oftransparencyin the RS’s functionality.

Conference paper

Rago A, Cocarascu O, Bechlivanidis C, Lagnado D, Toni Fet al., 2021, Argumentative explanations for interactive recommendations, Artificial Intelligence, Vol: 296, Pages: 1-22, ISSN: 0004-3702

A significant challenge for recommender systems (RSs), and in fact for AI systems in general, is the systematic definition of explanations for outputs in such a way that both the explanations and the systems themselves are able to adapt to their human users' needs. In this paper we propose an RS hosting a vast repertoire of explanations, which are customisable to users in their content and format, and thus able to adapt to users' explanatory requirements, while being reasonably effective (proven empirically). Our RS is built on a graphical chassis, allowing the extraction of argumentation scaffolding, from which diverse and varied argumentative explanations for recommendations can be obtained. These recommendations are interactive because they can be questioned by users and they support adaptive feedback mechanisms designed to allow the RS to self-improve (proven theoretically). Finally, we undertake user studies in which we vary the characteristics of the argumentative explanations, showing users' general preferences for more information, but also that their tastes are diverse, thus highlighting the need for our adaptable RS.

Journal article

Cyras K, Oliveira T, Karamlou M, Toni Fet al., 2021, Assumption-based argumentation with preferences and goals for patient-centric reasoning with interacting clinical guidelines, Argument and Computation, Vol: 12, Pages: 149-189, ISSN: 1946-2166

A paramount, yet unresolved issue in personalised medicine is that of automated reasoning with clinical guidelines in multimorbidity settings. This entails enabling machines to use computerised generic clinical guideline recommendations and patient-specific information to yield patient-tailored recommendations where interactions arising due to multimorbidities are resolved. This problem is further complicated by patient management desiderata, in particular the need to account for patient-centric goals as well as preferences of various parties involved. We propose to solve this problem of automated reasoning with interacting guideline recommendations in the context of a given patient by means of computational argumentation. In particular, we advance a structured argumentation formalism ABA+G (short for Assumption-Based Argumentation with Preferences (ABA+) and Goals) for integrating and reasoning with information about recommendations, interactions, patient’s state, preferences and prioritised goals. ABA+G combines assumption-based reasoning with preferences and goal-driven selection among reasoning outcomes. Specifically, we assume defeasible applicability of guideline recommendations with the general goal of patient well-being, resolve interactions (conflicts and otherwise undesirable situations) among recommendations based on the state and preferences of the patient, and employ patient-centered goals to suggest interaction-resolving, goal-importance maximising and preference-adhering recommendations. We use a well-established Transition-based Medical Recommendation model for representing guideline recommendations and identifying interactions thereof, and map the components in question, together with the given patient’s state, prioritised goals, and preferences over actions, to ABA+G for automated reasoning. In this, we follow principles of patient management and establish corresponding theoretical properties as well as illustrate our approach in realis

Journal article

Santos M, Toni F, 2021, Artificial intelligence-empowered technology in the home, The Home in the Digital Age, Pages: 38-55, ISBN: 9780367530174

Book chapter

Cyras K, Rago A, Emanuele A, Baroni P, Toni Fet al., 2021, Argumentative XAI: A Survey, The 30th International Joint Conference on Artificial Intelligence (IJCAI-21)

Conference paper

Cyras K, Heinrich Q, Toni F, 2021, Computational complexity of flat and generic assumption-based argumentation, with and without probabilities, Artificial Intelligence, Vol: 293, Pages: 1-36, ISSN: 0004-3702

Reasoning with probabilistic information has recently attracted considerable attention in argumentation, and formalisms of Probabilistic Abstract Argumentation (PAA), Probabilistic Bipolar Argumentation (PBA) and Probabilistic Structured Argumentation (PSA) have been proposed. These foundational advances have been complemented with investigations on the complexity of some approaches to PAA and PBA, but not to PSA. We study the complexity of an existing form of PSA, namely Probabilistic Assumption-Based Argumentation (PABA), a powerful, implemented formalism which subsumes several forms of PAA and other forms of PSA. Specifically, we establish membership (general upper bounds) and completeness (instantiated lower bounds) of reasoning in PABA for the class FP#P (of functions with a #P-oracle for counting the solutions of an NP problem) with respect to newly introduced probabilistic verification, credulous and sceptical acceptance function problems under several ABA semantics. As a by-product necessary to establish PABA complexity results, we provide a comprehensive picture of the ABA complexity landscape (for both flat and generic, possibly non-flat ABA) for the classical decision problems of verification, existence, credulous and sceptical acceptance under those ABA semantics.

Journal article

Albini E, Lertvittayakumjorn P, Rago A, Toni Fet al., 2021, DAX: deep argumentative eXplanation for neural networks, Publisher: arXiv

Despite the rapid growth in attention on eXplainable AI (XAI) of late,explanations in the literature provide little insight into the actualfunctioning of Neural Networks (NNs), significantly limiting theirtransparency. We propose a methodology for explaining NNs, providingtransparency about their inner workings, by utilising computationalargumentation (a form of symbolic AI offering reasoning abstractions for avariety of settings where opinions matter) as the scaffolding underpinning DeepArgumentative eXplanations (DAXs). We define three DAX instantiations (forvarious neural architectures and tasks) and evaluate them empirically in termsof stability, computational cost, and importance of depth. We also conducthuman experiments with DAXs for text classification models, indicating thatthey are comprehensible to humans and align with their judgement, while alsobeing competitive, in terms of user acceptance, with existing approaches to XAIthat also have an argumentative spirit.

Working paper

Rago A, Albini E, Baroni P, Toni Fet al., 2021, Influence-driven explanations for bayesian network classifiers, Publisher: arXiv

One of the most pressing issues in AI in recent years has been the need toaddress the lack of explainability of many of its models. We focus onexplanations for discrete Bayesian network classifiers (BCs), targeting greatertransparency of their inner workings by including intermediate variables inexplanations, rather than just the input and output variables as is standardpractice. The proposed influence-driven explanations (IDXs) for BCs aresystematically generated using the causal relationships between variableswithin the BC, called influences, which are then categorised by logicalrequirements, called relation properties, according to their behaviour. Theserelation properties both provide guarantees beyond heuristic explanationmethods and allow the information underpinning an explanation to be tailored toa particular context's and user's requirements, e.g., IDXs may be dialecticalor counterfactual. We demonstrate IDXs' capability to explain various forms ofBCs, e.g., naive or multi-label, binary or categorical, and also integraterecent approaches to explanations for BCs from the literature. We evaluate IDXswith theoretical and empirical analyses, demonstrating their considerableadvantages when compared with existing explanation methods.

Working paper

Cocarascu O, McLean A, French P, Toni Fet al., 2021, An Explanatory Query-Based Framework for Exploring Academic Expertise

The success of research institutions heavily relies upon identifying theright researchers "for the job": researchers may need to identify appropriatecollaborators, often from across disciplines; students may need to identifysuitable supervisors for projects of their interest; administrators may need tomatch funding opportunities with relevant researchers, and so on. Usually,finding potential collaborators in institutions is a time-consuming manualsearch task prone to bias. In this paper, we propose a novel query-basedframework for searching, scoring, and exploring research expertiseautomatically, based upon processing abstracts of academic publications. Givenuser queries in natural language, our framework finds researchers with relevantexpertise, making use of domain-specific knowledge bases and word embeddings.It also generates explanations for its recommendations. We evaluate ourframework with an institutional repository of papers from a leading university,using, as baselines, artificial neural networks and transformer-based modelsfor a multilabel classification task to identify authors of publicationabstracts. We also assess the cross-domain effectiveness of our framework witha (separate) research funding repository for the same institution. We show thatour simple method is effective in identifying matches, while satisfyingdesirable properties and being efficient.

Journal article

Oksanen J, Cocarascu O, Toni F, 2021, Automatic Product Ontology Extraction from Textual Reviews

Ontologies have proven beneficial in different settings that make use oftextual reviews. However, manually constructing ontologies is a laborious andtime-consuming process in need of automation. We propose a novel methodologyfor automatically extracting ontologies, in the form of meronomies, fromproduct reviews, using a very limited amount of hand-annotated training data.We show that the ontologies generated by our method outperform hand-craftedontologies (WordNet) and ontologies extracted by existing methods (Text2Ontoand COMET) in several, diverse settings. Specifically, our generated ontologiesoutperform the others when evaluated by human annotators as well as on anexisting Q&A dataset from Amazon. Moreover, our method is better able togeneralise, in capturing knowledge about unseen products. Finally, we considera real-world setting, showing that our method is better able to determinerecommended products based on their reviews, in alternative to using Amazon'sstandard score aggregations.

Journal article

Lertvittayakumjorn P, Choshen L, Shnarch E, Toni Fet al., 2021, GrASP: A Library for Extracting and Exploring Human-Interpretable Textual Patterns

Data exploration is an important step of every data science and machinelearning project, including those involving textual data. We provide a Pythonlibrary for GrASP, an existing algorithm for drawing patterns from textualdata. The library is equipped with a web-based interface empowering human usersto conveniently explore the data and the extracted patterns. We alsodemonstrate the use of the library in two settings (spam detection and argumentmining) and discuss future deployments of the library, e.g., beyond textualdata exploration.

Journal article

Lauren S, Belardinelli F, Toni F, 2021, Aggregating Bipolar Opinions (With Appendix)

We introduce a novel method to aggregate Bipolar Argumentation (BA)Frameworks expressing opinions by different parties in debates. We use BipolarAssumption-based Argumentation (ABA) as an all-encompassing formalism for BAunder different semantics. By leveraging on recent results on judgementaggregation in Social Choice Theory, we prove several preservation results,both positive and negative, for relevant properties of Bipolar ABA.

Journal article

Lertvittayakumjorn P, Toni F, 2021, Explanation-Based Human Debugging of NLP Models: A Survey

To fix a bug in a program, we need to locate where the bug is, understand whyit causes the problem, and patch the code accordingly. This process becomesharder when the program is a trained machine learning model and even harder foropaque deep learning models. In this survey, we review papers that exploitexplanations to enable humans to debug NLP models. We call this problemexplanation-based human debugging (EBHD). In particular, we categorize anddiscuss existing works along three main dimensions of EBHD (the bug context,the workflow, and the experimental setting), compile findings on how EBHDcomponents affect human debuggers, and highlight open problems that could befuture research directions.

Journal article

Paulino-Passos G, Toni F, 2021, Monotonicity and Noise-Tolerance in Case-Based Reasoning with Abstract Argumentation (with Appendix)

Recently, abstract argumentation-based models of case-based reasoning($AA{\text -} CBR$ in short) have been proposed, originally inspired by thelegal domain, but also applicable as classifiers in different scenarios.However, the formal properties of $AA{\text -} CBR$ as a reasoning systemremain largely unexplored. In this paper, we focus on analysing thenon-monotonicity properties of a regular version of $AA{\text -} CBR$ (that wecall $AA{\text -} CBR_{\succeq}$). Specifically, we prove that $AA{\text -}CBR_{\succeq}$ is not cautiously monotonic, a property frequently considereddesirable in the literature. We then define a variation of $AA{\text -}CBR_{\succeq}$ which is cautiously monotonic. Further, we prove that suchvariation is equivalent to using $AA{\text -} CBR_{\succeq}$ with a restrictedcasebase consisting of all "surprising" and "sufficient" cases in the originalcasebase. As a by-product, we prove that this variation of $AA{\text -}CBR_{\succeq}$ is cumulative, rationally monotonic, and empowers a principledtreatment of noise in "incoherent" casebases. Finally, we illustrate $AA{\text-} CBR$ and cautious monotonicity questions on a case study on the U.S. TradeSecrets domain, a legal casebase.

Journal article

Dejl A, He P, Mangal P, Mohsin H, Surdu B, Voinea E, Albini E, Lertvittayakumjorn P, Rago A, Toni Fet al., 2021, Argflow: A Toolkit for Deep Argumentative Explanations for Neural Networks., Publisher: ACM, Pages: 1761-1763

Conference paper

Lauren S, Belardinelli F, Toni F, 2020, Aggregating Bipolar Opinions, 20th International Conference on Autonomous Agents and Multiagent Systems

Conference paper

Kotonya N, Toni F, 2020, Explainable Automated Fact-Checking: A Survey, Barcelona. Spain, 28th International Conference on Computational Linguistics (COLING 2020), Publisher: International Committee on Computational Linguistics, Pages: 5430-5443

A number of exciting advances have been made in automated fact-checkingthanks to increasingly larger datasets and more powerful systems, leading toimprovements in the complexity of claims which can be accurately fact-checked.However, despite these advances, there are still desirable functionalitiesmissing from the fact-checking pipeline. In this survey, we focus on theexplanation functionality -- that is fact-checking systems providing reasonsfor their predictions. We summarize existing methods for explaining thepredictions of fact-checking systems and we explore trends in this topic.Further, we consider what makes for good explanations in this specific domainthrough a comparative analysis of existing fact-checking explanations againstsome desirable properties. Finally, we propose further research directions forgenerating fact-checking explanations, and describe how these may lead toimprovements in the research area.v

Conference paper

Lertvittayakumjorn P, Specia L, Toni F, 2020, FIND: human-in-the-loop debugging deep text classifiers

Since obtaining a perfect training dataset (i.e., a dataset which isconsiderably large, unbiased, and well-representative of unseen cases) ishardly possible, many real-world text classifiers are trained on the available,yet imperfect, datasets. These classifiers are thus likely to have undesirableproperties. For instance, they may have biases against some sub-populations ormay not work effectively in the wild due to overfitting. In this paper, wepropose FIND -- a framework which enables humans to debug deep learning textclassifiers by disabling irrelevant hidden features. Experiments show that byusing FIND, humans can improve CNN text classifiers which were trained underdifferent types of imperfect datasets (including datasets with biases anddatasets with dissimilar train-test distributions).

Working paper

Kotonya N, Toni F, 2020, Explainable Automated Fact-Checking for Public Health Claims, 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP(1) 2020), Publisher: ACL

Fact-checking is the task of verifying the veracity of claims by assessing their assertions against credible evidence. The vast major-ity of fact-checking studies focus exclusively on political claims. Very little research explores fact-checking for other topics, specifically subject matters for which expertise is required. We present the first study of explainable fact-checking for claims which require specific expertise. For our case study we choose the setting of public health. To support this case study we construct a new datasetPUBHEALTHof 11.8K claims accompanied by journalist crafted, gold standard explanations(i.e., judgments) to support the fact-check la-bels for claims1. We explore two tasks: veracity prediction and explanation generation. We also define and evaluate, with humans and computationally, three coherence properties of explanation quality. Our results indicate that,by training on in-domain data, gains can be made in explainable, automated fact-checking for claims which require specific expertise.

Conference paper

Lertvittayakumjorn P, Specia L, Toni F, 2020, FIND: Human-in-the-Loop Debugging Deep Text Classifiers, 2020 Conference on Empirical Methods in Natural Language Processing, Publisher: ACL

Since obtaining a perfect training dataset (i.e., a dataset which is considerably large, unbiased, and well-representative of unseen cases)is hardly possible, many real-world text classifiers are trained on the available, yet imperfect, datasets. These classifiers are thus likely to have undesirable properties. For instance, they may have biases against some sub-populations or may not work effectively in the wild due to overfitting. In this paper, we propose FIND–a framework which enables humans to debug deep learning text classifiers by disabling irrelevant hidden features. Experiments show that by using FIND, humans can improve CNN text classifiers which were trained under different types of imperfect datasets (including datasets with biases and datasets with dissimilar train-test distributions).

Conference paper

Paulino-Passos G, Toni F, 2020, Cautious Monotonicity in Case-Based Reasoning with Abstract Argumentation, arxiv

Recently, abstract argumentation-based models of case-based reasoning($AA{\text -}CBR$ in short) have been proposed, originally inspired by thelegal domain, but also applicable as classifiers in different scenarios,including image classification, sentiment analysis of text, and in predictingthe passage of bills in the UK Parliament. However, the formal properties of$AA{\text -}CBR$ as a reasoning system remain largely unexplored. In thispaper, we focus on analysing the non-monotonicity properties of a regularversion of $AA{\text -}CBR$ (that we call $AA{\text -}CBR_{\succeq}$).Specifically, we prove that $AA{\text -}CBR_{\succeq}$ is not cautiouslymonotonic, a property frequently considered desirable in the literature ofnon-monotonic reasoning. We then define a variation of $AA{\text-}CBR_{\succeq}$ which is cautiously monotonic, and provide an algorithm forobtaining it. Further, we prove that such variation is equivalent to using$AA{\text -}CBR_{\succeq}$ with a restricted casebase consisting of all"surprising" cases in the original casebase.

Journal article

Baroni P, Toni F, Verheij B, 2020, On the acceptability of arguments and its fundamental role in nonmonotonic reasoning, logic programming and n-person games: 25 years later Foreword, ARGUMENT & COMPUTATION, Vol: 11, Pages: 1-14, ISSN: 1946-2166

Journal article

Albini E, Rago A, Baroni P, Toni Fet al., 2020, Relation-Based Counterfactual Explanations for Bayesian Network Classifiers, The 29th International Joint Conference on Artificial Intelligence (IJCAI 2020)

Conference paper

Cocarascu O, Cabrio E, Villata S, Toni Fet al., 2020, A dataset independent set of baselines for relation prediction in argument mining., Publisher: arXiv

Argument Mining is the research area which aims at extracting argument components and predicting argumentative relations (i.e.,support and attack) from text. In particular, numerous approaches have been proposed in the literature to predict the relations holding between the arguments, and application-specific annotated resources were built for this purpose. Despite the fact that these resources have been created to experiment on the same task, the definition of a single relation prediction method to be successfully applied to a significant portion of these datasets is an open research problem in Argument Mining. This means that none of the methods proposed in the literature can be easily ported from one resource to another. In this paper, we address this problem by proposing a set of dataset independent strong neural baselines which obtain homogeneous results on all the datasets proposed in the literature for the argumentative relation prediction task. Thus, our baselines can be employed by the Argument Mining community to compare more effectively how well a method performs on the argumentative relation prediction task.

Working paper

Cocarascu O, Stylianou A, Cyras K, Toni Fet al., 2020, Data-empowered argumentation for dialectically explainable predictions, 24th European Conference on Artificial Intelligence (ECAI 2020), Publisher: IOS Press

Today’s AI landscape is permeated by plentiful data anddominated by powerful data-centric methods with the potential toimpact a wide range of human sectors. Yet, in some settings this po-tential is hindered by these data-centric AI methods being mostlyopaque. Considerable efforts are currently being devoted to defin-ing methods for explaining black-box techniques in some settings,while the use of transparent methods is being advocated in others,especially when high-stake decisions are involved, as in healthcareand the practice of law. In this paper we advocate a novel transpar-ent paradigm of Data-Empowered Argumentation (DEAr in short)for dialectically explainable predictions. DEAr relies upon the ex-traction of argumentation debates from data, so that the dialecticaloutcomes of these debates amount to predictions (e.g. classifications)that can be explained dialectically. The argumentation debates con-sist of (data) arguments which may not be linguistic in general butmay nonetheless be deemed to be ‘arguments’ in that they are dialec-tically related, for instance by disagreeing on data labels. We illus-trate and experiment with the DEAr paradigm in three settings, mak-ing use, respectively, of categorical data, (annotated) images and text.We show empirically that DEAr is competitive with another transpar-ent model, namely decision trees (DTs), while also providing natu-rally dialectical explanations.

Conference paper

Albini E, Baroni P, Rago A, Toni Fet al., 2020, PageRank as an Argumentation Semantics, Biennial International Conference on Computational Models of Argument (COMMA), Publisher: IOS PRESS, Pages: 55-66, ISSN: 0922-6389

Conference paper

Čyras K, Karamlou A, Lee M, Letsios D, Misener R, Toni Fet al., 2020, AI-assisted schedule explainer for nurse rostering, Pages: 2101-2103, ISSN: 1548-8403

We present an argumentation-supported explanation generating system, called Schedule Explainer, that assists with makespan scheduling. Our stand-alone generic tool explains to a lay user why a resource allocation schedule is good or not, and offers actions to improve the schedule given the user's constraints. Schedule Explainer provides actionable textual explanations via an interactive graphical interface. We illustrate our system with a proof-of-concept application tool in a nurse rostering scenario whereby a shift-lead nurse aims to account for unexpected events by rescheduling some patient procedures to nurses and is aided by the system to do so.

Conference paper

Cocarascu O, Toni F, 2020, Deploying Machine Learning Classifiers for Argumentative Relations “in the Wild”, Argumentation Library, Pages: 269-285

Argument Mining (AM) aims at automatically identifying arguments and components of arguments in text, as well as at determining the relations between these arguments, on various annotated corpora using machine learning techniques (Lippi & Torroni, 2016).

Book chapter

Cocarascu O, Rago A, Toni F, 2020, Explanation via Machine Arguing, Pages: 53-84, ISBN: 9783030600662

As AI becomes ever more ubiquitous in our everyday lives, its ability to explain to and interact with humans is evolving into a critical research area. Explainable AI (XAI) has therefore emerged as a popular topic but its research landscape is currently very fragmented. Explanations in the literature have generally been aimed at addressing individual challenges and are often ad-hoc, tailored to specific AIs and/or narrow settings. Further, the extraction of explanations is no simple task; the design of the explanations must be fit for purpose, with considerations including, but not limited to: Is the model or a result being explained? Is the explanation suited to skilled or unskilled explainees? By which means is the information best exhibited? How may users interact with the explanation? As these considerations rise in number, it quickly becomes clear that a systematic way to obtain a variety of explanations for a variety of users and interactions is much needed. In this tutorial we will overview recent approaches showing how these challenges can be addressed by utilising forms of machine arguing as the scaffolding underpinning explanations that are delivered to users. Machine arguing amounts to the deployment of methods from computational argumentation in AI with suitably mined argumentation frameworks, which provide abstractions of “debates”. Computational argumentation has been widely used to support applications requiring information exchange between AI systems and users, facilitated by the fact that the capability of arguing is pervasive in human affairs and arguing is core to a multitude of human activities: humans argue to explain, interact and exchange information. Our lecture will focus on how machine arguing can serve as the driving force of explanations in AI in different ways, namely: by building explainable systems with argumentative foundations from linguistic data focusing on reviews), or by extracting argumentative reasoning from existin

Book chapter

Jha R, Belardinelli F, Toni F, 2020, Formal Verification of Debates in Argumentation Theory., CoRR, Vol: abs/1912.05828

Journal article

This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.

Request URL: http://wlsprd.imperial.ac.uk:80/respub/WEB-INF/jsp/search-html.jsp Request URI: /respub/WEB-INF/jsp/search-html.jsp Query String: respub-action=search.html&id=00154121&limit=30&person=true