Tran, Thy Thy ; Le, Phong ; Ananiadou, Sophia (2020)
Revisiting Unsupervised Relation Extraction.
58th Annual Meeting of the Association for Computational Linguistics. virtual Conference (05.-10.07.2020)
doi: 10.18653/v1/2020.acl-main.669
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
Unsupervised relation extraction (URE) extracts relations between named entities from raw text without manually-labelled data and existing knowledge bases (KBs). URE methods can be categorised into generative and discriminative approaches, which rely either on hand-crafted features or surface form. However, we demonstrate that by using only named entities to induce relation types, we can outperform existing methods on two popular datasets. We conduct a comparison and evaluation of our findings with other URE techniques, to ascertain the important features in URE. We conclude that entity types provide a strong inductive bias for URE.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2020 |
| Autor(en): | Tran, Thy Thy ; Le, Phong ; Ananiadou, Sophia |
| Art des Eintrags: | Bibliographie |
| Titel: | Revisiting Unsupervised Relation Extraction |
| Sprache: | Englisch |
| Publikationsjahr: | Juli 2020 |
| Verlag: | ACL |
| Buchtitel: | The 58th Annual Meeting of the Association for Computational Linguistics: Proceedings of the Conference |
| Veranstaltungstitel: | 58th Annual Meeting of the Association for Computational Linguistics |
| Veranstaltungsort: | virtual Conference |
| Veranstaltungsdatum: | 05.-10.07.2020 |
| DOI: | 10.18653/v1/2020.acl-main.669 |
| URL / URN: | https://aclanthology.org/2020.acl-main.669 |
| Kurzbeschreibung (Abstract): | Unsupervised relation extraction (URE) extracts relations between named entities from raw text without manually-labelled data and existing knowledge bases (KBs). URE methods can be categorised into generative and discriminative approaches, which rely either on hand-crafted features or surface form. However, we demonstrate that by using only named entities to induce relation types, we can outperform existing methods on two popular datasets. We conduct a comparison and evaluation of our findings with other URE techniques, to ascertain the important features in URE. We conclude that entity types provide a strong inductive bias for URE. |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Ubiquitäre Wissensverarbeitung |
| Hinterlegungsdatum: | 02 Aug 2023 14:13 |
| Letzte Änderung: | 04 Aug 2023 08:43 |
| PPN: | 510355447 |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum