no code implementations • 19 Apr 2024 • Nacime Bouziani, Shubhi Tyagi, Joseph Fisher, Jens Lehmann, Andrea Pierleoni
Extracting structured information from unstructured text is critical for many downstream NLP applications and is traditionally achieved by closed information extraction (cIE).
Ranked #1 on Coreference Resolution on DWIE
Coreference Resolution Document-level Closed Information Extraction +7
no code implementations • 23 May 2023 • Chenxi Whitehouse, Clara Vania, Alham Fikri Aji, Christos Christodoulopoulos, Andrea Pierleoni
We evaluate the in-domain, out-of-domain, and zero-shot cross-lingual performance of generative IE models and find models trained on WebIE show better generalisability.
2 code implementations • NAACL (ACL) 2022 • Tom Ayoola, Shubhi Tyagi, Joseph Fisher, Christos Christodoulopoulos, Andrea Pierleoni
The model is capable of generalising to large-scale knowledge bases such as Wikidata (which has 15 times more entities than Wikipedia) and of zero-shot entity linking.
Ranked #1 on Entity Linking on WebQSP-WD (using extra training data)
2 code implementations • NAACL 2022 • Tom Ayoola, Joseph Fisher, Andrea Pierleoni
Recent work in entity disambiguation (ED) has typically neglected structured knowledge base (KB) facts, and instead relied on a limited subset of KB information, such as entity descriptions or types.
Ranked #1 on Entity Disambiguation on ShadowLink-Top
no code implementations • 6 Apr 2020 • Yannis Papanikolaou, Andrea Pierleoni
Real-world Relation Extraction (RE) tasks are challenging to deal with, either due to limited training data or class imbalance issues.
no code implementations • WS 2019 • Yannis Papanikolaou, Ian Roberts, Andrea Pierleoni
We present a novel framework to deal with relation extraction tasks in cases where there is complete lack of supervision, either in the form of gold annotations, or relations from a knowledge base.
no code implementations • WS 2019 • Saatviga Sudhahar, Ian Roberts, Andrea Pierleoni
We demonstrate that our method is able to effectively rank a list of known paths between a pair of entities and also come up with plausible paths that are not present in the knowledge graph.