Michael Schlichtkrull

Also published as: Michael Sejr Schlichtkrull


2024

pdf bib
Automated Focused Feedback Generation for Scientific Writing Assistance
Eric Chamoun | Michael Schlichtkrull | Andreas Vlachos
Findings of the Association for Computational Linguistics: ACL 2024

Scientific writing is a challenging task, particularly for novice researchers who often rely on feedback from experienced peers. Recent work has primarily focused on improving surface form and style rather than manuscript content. In this paper, we propose a novel task: automated focused feedback generation for scientific writing assistance. We present SWIF2T: a Scientific WrIting Focused Feedback Tool. It is designed to generate specific, actionable and coherent comments, which identify weaknesses in a scientific paper and/or propose revisions to it. Our approach consists of four components - planner, investigator, reviewer and controller - leveraging multiple Large Language Models (LLMs) to implement them. We compile a dataset of 300 peer reviews citing weaknesses in scientific papers and conduct human evaluation. The results demonstrate the superiority in specificity, reading comprehension, and overall helpfulness of SWIF2T’s feedback compared to other approaches. In our analysis, we also identified cases where automatically generated reviews were judged better than human ones, suggesting opportunities for integration of AI-generated feedback in scientific writing.

pdf bib
Generating Media Background Checks for Automated Source Critical Reasoning
Michael Sejr Schlichtkrull
Findings of the Association for Computational Linguistics: EMNLP 2024

Not everything on the internet is true. This unfortunate fact requires both humans and models to perform complex reasoning about credibility when working with retrieved information. In NLP, this problem has seen little attention. Indeed, retrieval-augmented models are not typically expected to distrust retrieved documents. Human experts overcome the challenge by gathering signals about the context, reliability, and tendency of source documents - that is, they perform *source criticism*. We propose a novel NLP task focused on finding and summarising such signals. We introduce a new dataset of 6,709 “media background checks” derived from Media Bias / Fact Check, a volunteer-run website documenting media bias. We test open-source and closed-source LLM baselines with and without retrieval on this dataset, finding that retrieval greatly improves performance. We furthermore carry out human evaluation, demonstrating that 1) media background checks are helpful for humans, and 2) media background checks are helpful for retrieval-augmented models.

pdf bib
Proceedings of the Seventh Fact Extraction and VERification Workshop (FEVER)
Michael Schlichtkrull | Yulong Chen | Chenxi Whitehouse | Zhenyun Deng | Mubashara Akhtar | Rami Aly | Zhijiang Guo | Christos Christodoulopoulos | Oana Cocarascu | Arpit Mittal | James Thorne | Andreas Vlachos
Proceedings of the Seventh Fact Extraction and VERification Workshop (FEVER)

pdf bib
The Automated Verification of Textual Claims (AVeriTeC) Shared Task
Michael Schlichtkrull | Yulong Chen | Chenxi Whitehouse | Zhenyun Deng | Mubashara Akhtar | Rami Aly | Zhijiang Guo | Christos Christodoulopoulos | Oana Cocarascu | Arpit Mittal | James Thorne | Andreas Vlachos
Proceedings of the Seventh Fact Extraction and VERification Workshop (FEVER)

The Automated Verification of Textual Claims (AVeriTeC) shared task asks participants to retrieve evidence and predict veracity for real-world claims checked by fact-checkers. Evidence can be found either via a search engine, or via a knowledge store provided by the organisers. Submissions are evaluated using the AVeriTeC score, which considers a claim to be accurately verified if and only if both the verdict is correct and retrieved evidence is considered to meet a certain quality threshold. The shared task received 21 submissions, 18 of which surpassed our baseline. The winning team was TUDA_MAI with an AVeriTeC score of 63%. In this paper we describe the shared task, present the full results, and highlight key takeaways from the shared task.

pdf bib
Document-level Claim Extraction and Decontextualisation for Fact-Checking
Zhenyun Deng | Michael Schlichtkrull | Andreas Vlachos
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Selecting which claims to check is a time-consuming task for human fact-checkers, especially from documents consisting of multiple sentences and containing multiple claims. However, existing claim extraction approaches focus more on identifying and extracting claims from individual sentences, e.g., identifying whether a sentence contains a claim or the exact boundaries of the claim within a sentence. In this paper, we propose a method for document-level claim extraction for fact-checking, which aims to extract check-worthy claims from documents and decontextualise them so that they can be understood out of context. Specifically, we first recast claim extraction as extractive summarization in order to identify central sentences from documents, then rewrite them to include necessary context from the originating document through sentence decontextualisation. Evaluation with both automatic metrics and a fact-checking professional shows that our method is able to extract check-worthy claims from documents at a higher rate than previous work, while also improving evidence retrieval.

2023

pdf bib
Multimodal Automated Fact-Checking: A Survey
Mubashara Akhtar | Michael Schlichtkrull | Zhijiang Guo | Oana Cocarascu | Elena Simperl | Andreas Vlachos
Findings of the Association for Computational Linguistics: EMNLP 2023

Misinformation is often conveyed in multiple modalities, e.g. a miscaptioned image. Multimodal misinformation is perceived as more credible by humans, and spreads faster than its text-only counterparts. While an increasing body of research investigates automated fact-checking (AFC), previous surveys mostly focus on text. In this survey, we conceptualise a framework for AFC including subtasks unique to multimodal misinformation. Furthermore, we discuss related terms used in different communities and map them to our framework. We focus on four modalities prevalent in real-world fact-checking: text, image, audio, and video. We survey benchmarks and models, and discuss limitations and promising directions for future research

pdf bib
The Intended Uses of Automated Fact-Checking Artefacts: Why, How and Who
Michael Schlichtkrull | Nedjma Ousidhoum | Andreas Vlachos
Findings of the Association for Computational Linguistics: EMNLP 2023

Automated fact-checking is often presented as an epistemic tool that fact-checkers, social media consumers, and other stakeholders can use to fight misinformation. Nevertheless, few papers thoroughly discuss how. We document this by analysing 100 highly-cited papers, and annotating epistemic elements related to intended use, i.e., means, ends, and stakeholders. We find that narratives leaving out some of these aspects are common, that many papers propose inconsistent means and ends, and that the feasibility of suggested strategies rarely has empirical backing. We argue that this vagueness actively hinders the technology from reaching its goals, as it encourages overclaiming, limits criticism, and prevents stakeholder feedback. Accordingly, we provide several recommendations for thinking and writing about the use of fact-checking artefacts.

pdf bib
Proceedings of the Sixth Fact Extraction and VERification Workshop (FEVER)
Mubashara Akhtar | Rami Aly | Christos Christodoulopoulos | Oana Cocarascu | Zhijiang Guo | Arpit Mittal | Michael Schlichtkrull | James Thorne | Andreas Vlachos
Proceedings of the Sixth Fact Extraction and VERification Workshop (FEVER)

pdf bib
Are Embedded Potatoes Still Vegetables? On the Limitations of WordNet Embeddings for Lexical Semantics
Xuyou Cheng | Michael Schlichtkrull | Guy Emerson
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Knowledge Base Embedding (KBE) models have been widely used to encode structured information from knowledge bases, including WordNet. However, the existing literature has predominantly focused on link prediction as the evaluation task, often neglecting exploration of the models’ semantic capabilities. In this paper, we investigate the potential disconnect between the performance of KBE models of WordNet on link prediction and their ability to encode semantic information, highlighting the limitations of current evaluation protocols. Our findings reveal that some top-performing KBE models on the WN18RR benchmark exhibit subpar results on two semantic tasks and two downstream tasks. These results demonstrate the inadequacy of link prediction benchmarks for evaluating the semantic capabilities of KBE models, suggesting the need for a more targeted assessment approach.

2022

pdf bib
Proceedings of the Fifth Fact Extraction and VERification Workshop (FEVER)
Rami Aly | Christos Christodoulopoulos | Oana Cocarascu | Zhijiang Guo | Arpit Mittal | Michael Schlichtkrull | James Thorne | Andreas Vlachos
Proceedings of the Fifth Fact Extraction and VERification Workshop (FEVER)

pdf bib
UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answering
Barlas Oguz | Xilun Chen | Vladimir Karpukhin | Stan Peshterliev | Dmytro Okhonko | Michael Schlichtkrull | Sonal Gupta | Yashar Mehdad | Scott Yih
Findings of the Association for Computational Linguistics: NAACL 2022

We study open-domain question answering with structured, unstructured and semi-structured knowledge sources, including text, tables, lists and knowledge bases. Departing from prior work, we propose a unifying approach that homogenizes all sources by reducing them to text and applies the retriever-reader model which has so far been limited to text sources only. Our approach greatly improves the results on knowledge-base QA tasks by 11 points, compared to latest graph-based methods. More importantly, we demonstrate that our unified knowledge (UniK-QA) model is a simple and yet effective way to combine heterogeneous sources of knowledge, advancing the state-of-the-art results on two popular question answering benchmarks, NaturalQuestions and WebQuestions, by 3.5 and 2.6 points, respectively. The code of UniK-QA is available at: https://github.com/facebookresearch/UniK-QA.

pdf bib
A Survey on Automated Fact-Checking
Zhijiang Guo | Michael Schlichtkrull | Andreas Vlachos
Transactions of the Association for Computational Linguistics, Volume 10

Fact-checking has become increasingly important due to the speed with which both information and misinformation can spread in the modern media ecosystem. Therefore, researchers have been exploring how fact-checking can be automated, using techniques based on natural language processing, machine learning, knowledge representation, and databases to automatically predict the veracity of claims. In this paper, we survey automated fact-checking stemming from natural language processing, and discuss its connections to related tasks and disciplines. In this process, we present an overview of existing datasets and models, aiming to unify the various definitions given and identify common concepts. Finally, we highlight challenges for future research.

2021

pdf bib
Joint Verification and Reranking for Open Fact Checking Over Tables
Michael Sejr Schlichtkrull | Vladimir Karpukhin | Barlas Oguz | Mike Lewis | Wen-tau Yih | Sebastian Riedel
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Structured information is an important knowledge source for automatic verification of factual claims. Nevertheless, the majority of existing research into this task has focused on textual data, and the few recent inquiries into structured data have been for the closed-domain setting where appropriate evidence for each claim is assumed to have already been retrieved. In this paper, we investigate verification over structured data in the open-domain setting, introducing a joint reranking-and-verification model which fuses evidence documents in the verification component. Our open-domain model achieves performance comparable to the closed-domain state-of-the-art on the TabFact dataset, and demonstrates performance gains from the inclusion of multiple tables as well as a significant improvement over a heuristic retrieval baseline.

pdf bib
Proceedings of the Fourth Workshop on Fact Extraction and VERification (FEVER)
Rami Aly | Christos Christodoulopoulos | Oana Cocarascu | Zhijiang Guo | Arpit Mittal | Michael Schlichtkrull | James Thorne | Andreas Vlachos
Proceedings of the Fourth Workshop on Fact Extraction and VERification (FEVER)

pdf bib
The Fact Extraction and VERification Over Unstructured and Structured information (FEVEROUS) Shared Task
Rami Aly | Zhijiang Guo | Michael Sejr Schlichtkrull | James Thorne | Andreas Vlachos | Christos Christodoulopoulos | Oana Cocarascu | Arpit Mittal
Proceedings of the Fourth Workshop on Fact Extraction and VERification (FEVER)

The Fact Extraction and VERification Over Unstructured and Structured information (FEVEROUS) shared task, asks participating systems to determine whether human-authored claims are Supported or Refuted based on evidence retrieved from Wikipedia (or NotEnoughInfo if the claim cannot be verified). Compared to the FEVER 2018 shared task, the main challenge is the addition of structured data (tables and lists) as a source of evidence. The claims in the FEVEROUS dataset can be verified using only structured evidence, only unstructured evidence, or a mixture of both. Submissions are evaluated using the FEVEROUS score that combines label accuracy and evidence retrieval. Unlike FEVER 2018, FEVEROUS requires partial evidence to be returned for NotEnoughInfo claims, and the claims are longer and thus more complex. The shared task received 13 entries, six of which were able to beat the baseline system. The winning team was “Bust a move!”, achieving a FEVEROUS score of 27% (+9% compared to the baseline). In this paper we describe the shared task, present the full results and highlight commonalities and innovations among the participating systems.

2020

pdf bib
How do Decisions Emerge across Layers in Neural Models? Interpretation with Differentiable Masking
Nicola De Cao | Michael Sejr Schlichtkrull | Wilker Aziz | Ivan Titov
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Attribution methods assess the contribution of inputs to the model prediction. One way to do so is erasure: a subset of inputs is considered irrelevant if it can be removed without affecting the prediction. Though conceptually simple, erasure’s objective is intractable and approximate search remains expensive with modern deep NLP models. Erasure is also susceptible to the hindsight bias: the fact that an input can be dropped does not mean that the model ‘knows’ it can be dropped. The resulting pruning is over-aggressive and does not reflect how the model arrives at the prediction. To deal with these challenges, we introduce Differentiable Masking. DiffMask learns to mask-out subsets of the input while maintaining differentiability. The decision to include or disregard an input token is made with a simple model based on intermediate hidden layers of the analyzed model. First, this makes the approach efficient because we predict rather than search. Second, as with probing classifiers, this reveals what the network ‘knows’ at the corresponding layers. This lets us not only plot attribution heatmaps but also analyze how decisions are formed across network layers. We use DiffMask to study BERT models on sentiment classification and question answering.

2017

pdf bib
Cross-Lingual Dependency Parsing with Late Decoding for Truly Low-Resource Languages
Michael Schlichtkrull | Anders Søgaard
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers

In cross-lingual dependency annotation projection, information is often lost during transfer because of early decoding. We present an end-to-end graph-based neural network dependency parser that can be trained to reproduce matrices of edge scores, which can be directly projected across word alignments. We show that our approach to cross-lingual dependency parsing is not only simpler, but also achieves an absolute improvement of 2.25% averaged across 10 languages compared to the previous state of the art.

2016

pdf bib
MSejrKu at SemEval-2016 Task 14: Taxonomy Enrichment by Evidence Ranking
Michael Schlichtkrull | Héctor Martínez Alonso
Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016)