Papers by Michael Schlichtkrull
Document-level Claim Extraction and Decontextualisation for Fact-Checking (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods for document-level claim extraction focus on identifying and extracting claims from individual sentences. |
| Approach: | They propose a method for document-level claim extraction for fact-checking which aims to extract check-worthy claims from documents and decontextualise them so they can be understood out of context. |
| Outcome: | The proposed method extracts check-worthy claims from documents and decontextualises them so they can be understood out of context. |
Multimodal Automated Fact-Checking: A Survey (2023.findings-emnlp)
Copied to clipboard
Mubashara Akhtar, Michael Schlichtkrull, Zhijiang Guo, Oana Cocarascu, Elena Simperl, Andreas Vlachos
| Challenge: | Existing studies on automated fact-checking focus on text, but they focus on a single modality, text . multimodal misinformation is perceived as more credible by humans and spreads faster than text-only counterparts. |
| Approach: | They propose a framework for automated fact-checking that includes subtasks unique to multimodal misinformation. |
| Outcome: | The proposed framework includes subtasks unique to multimodal misinformation. |
A Survey on Automated Fact-Checking (2022.tacl-1)
Copied to clipboard
| Challenge: | Fact-checking is an essential task in journalism due to the speed with which information and misinformation can spread in the media ecosystem. |
| Approach: | They propose to use natural language processing to automate fact-checking by identifying common concepts and defining definitions. |
| Outcome: | The proposed method can predict the veracity of claims using natural language processing, machine learning, and databases. |
Are Embedded Potatoes Still Vegetables? On the Limitations of WordNet Embeddings for Lexical Semantics (2023.emnlp-main)
Copied to clipboard
| Challenge: | Knowledge Base Embedding (KBE) models are widely used to encode structured information from knowledge bases, including WordNet, but the evaluation task is often focused on link prediction, ignoring their semantic capabilities. |
| Approach: | They propose to evaluate the performance of Knowledge Base Embedding (KBE) models of WordNet on link prediction and their ability to encode semantic information. |
| Outcome: | The proposed model performs poorly on two semantic tasks and two downstream tasks. |
Ev2R: Evaluating Evidence Retrieval in Automated Fact-Checking (2026.tacl-1)
Copied to clipboard
| Challenge: | Current methods for automated fact-checking rely on relying on other evaluation metrics and closed knowledge sources. |
| Approach: | They propose a method which combines evidence evaluation with verdict-level proxy scoring. |
| Outcome: | The proposed method outperforms existing methods in accuracy and robustness against human ratings and adversarial tests. |
The Intended Uses of Automated Fact-Checking Artefacts: Why, How and Who (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Automated fact-checking is often presented as an epistemic tool fact-seekers, social media consumers, and other stakeholders can use to fight misinformation. |
| Approach: | They analyse 100 highly-cited papers and annotate epistemic elements related to intended use, i.e., means, ends, and stakeholders. |
| Outcome: | The proposed strategies are often left out of the literature and lack empirical backing. |
UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answering (2022.findings-naacl)
Copied to clipboard
Barlas Oguz, Xilun Chen, Vladimir Karpukhin, Stan Peshterliev, Dmytro Okhonko, Michael Schlichtkrull, Sonal Gupta, Yashar Mehdad, Scott Yih
| Challenge: | a recent study aims to answer factual questions using a structured knowledge base (KBQA). |
| Approach: | They propose a unifying approach that homogenizes all knowledge sources by reducing them to text . they demonstrate that UniK-QA is a simple and yet effective way to combine heterogeneous sources of knowledge. |
| Outcome: | The proposed approach improves state-of-the-art results on knowledge-base QA tasks by 11 points compared to graph-based methods. |
Generating Media Background Checks for Automated Source Critical Reasoning (2024.findings-emnlp)
Copied to clipboard
| Challenge: | retrieved information is not always reliable, but retrieval-augmented models are not expected to distrust it. |
| Approach: | They propose a task where retrieval-augmented models summarise information about the context, reliability, and tendency of media sources. |
| Outcome: | The proposed task shows that retrieval greatly improves performance on open-source and closed-source datasets, and that it is useful for humans and retrieval-augmented models. |
Automated Focused Feedback Generation for Scientific Writing Assistance (2024.findings-acl)
Copied to clipboard
| Challenge: | Recent work has focused on improving surface form and style rather than manuscript content. |
| Approach: | They propose to use a scientific writing focused feedback tool to generate specific, actionable and coherent comments which identify weaknesses in a paper and/or propose revisions to it. |
| Outcome: | The proposed tool outperforms existing approaches in specificity, reading comprehension and overall helpfulness of the generated reviews. |