Can Knowledge Graph Embeddings Tell Us What Fact-checked Claims Are About?
| Autor: | Andon Tchechmedjiev, Valentina Beretta, Konstantin Todorov, Luke Lo Seen, Sébastien Harispe, Katarina Boland |
|---|---|
| Přispěvatelé: | Euromov (EuroMov), Université de Montpellier (UM), Leibniz-Institute for the Social Sciences [Mannheim] (GESIS ), Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier (LIRMM), Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM), Informatique, Image, Intelligence Artificielle (I3A), Laboratoire de Génie Informatique et d'Ingénierie de Production (LGI2P), IMT - MINES ALES (IMT - MINES ALES), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-IMT - MINES ALES (IMT - MINES ALES), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), WEB-CUBE, Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM) |
| Předmět: |
Computer science
Graph embedding Network structure Link prediction 02 engineering and technology Claims [SCCO.LING]Cognitive science/Linguistics Social issues Data science [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] [INFO.INFO-TT]Computer Science [cs]/Document and Text Processing Knowledge graph [STAT.ML]Statistics [stat]/Machine Learning [stat.ML] 020204 information systems Topic classification 0202 electrical engineering electronic engineering information engineering Graph (abstract data type) Embedding 020201 artificial intelligence & image processing Misinformation |
| Zdroj: | HAL Proceedings of the Workshop on Insights from Negative Results in NLP Workshop on Insights from Negative Results in NLP Workshop on Insights from Negative Results in NLP, Nov 2020, Online, Dominican Republic. ⟨10.18653/v1/2020.insights-1.11⟩ Insights |
| DOI: | 10.18653/v1/2020.insights-1.11⟩ |
| Popis: | International audience; The web offers a wealth of discourse data that help researchers from various fields analyze debates about current societal issues and gauge the effects on society of important phenomena such as misinformation spread. Such analyses often revolve around claims made by people about a given topic of interest. Fact-checking portals offer partially structured information that can assist such analysis. However, exploiting the network structure of such online discourse data is as of yet under-explored. We study the effectiveness of using neural-graph embedding features for claim topic prediction and their complementarity with text em-beddings. We show that graph embeddings are modestly complementary with text embed-dings, but the low performance of graph embedding features alone indicate that the model fails to capture topological features pertinent of the topic prediction task. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|