Inproceedings3943: Unterschied zwischen den Versionen
Jg2894 (Diskussion | Beiträge) (Die Seite wurde neu angelegt: „{{Publikation Erster Autor |ErsterAutorNachname=Popovic |ErsterAutorVorname=Nicholas }} {{Publikation Author |Rank=2 |Author=Michael Färber }} {{Inproceedings…“) |
Jg2894 (Diskussion | Beiträge) |
||
Zeile 16: | Zeile 16: | ||
{{Publikation Details | {{Publikation Details | ||
|Abstract=We present FREDo, a few-shot document-level relation extraction (FSDLRE) benchmark. As opposed to existing benchmarks which are built on sentence-level relation extraction corpora, we argue that document-level corpora provide more realism, particularly regarding none-of-the-above (NOTA) distributions. Therefore, we propose a set of FSDLRE tasks and construct a benchmark based on two existing supervised learning data sets, DocRED and sciERC. We adapt the state-of-the-art sentence-level method MNAV to the document-level and develop it further for improved domain adaptation. We find FSDLRE to be a challenging setting with interesting new characteristics such as the ability to sample NOTA instances from the support set. The data, code, and trained models are available online (https://github.com/nicpopovic/FREDo). | |Abstract=We present FREDo, a few-shot document-level relation extraction (FSDLRE) benchmark. As opposed to existing benchmarks which are built on sentence-level relation extraction corpora, we argue that document-level corpora provide more realism, particularly regarding none-of-the-above (NOTA) distributions. Therefore, we propose a set of FSDLRE tasks and construct a benchmark based on two existing supervised learning data sets, DocRED and sciERC. We adapt the state-of-the-art sentence-level method MNAV to the document-level and develop it further for improved domain adaptation. We find FSDLRE to be a challenging setting with interesting new characteristics such as the ability to sample NOTA instances from the support set. The data, code, and trained models are available online (https://github.com/nicpopovic/FREDo). | ||
− | |Download= | + | |Download=FSDLRE.pdf |
|Forschungsgruppe=Web Science | |Forschungsgruppe=Web Science | ||
}} | }} |
Aktuelle Version vom 4. Juli 2022, 08:19 Uhr
Few-Shot Document-Level Relation Extraction
Few-Shot Document-Level Relation Extraction
Published: 2022
Buchtitel: Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Verlag: Association for Computational Linguistics
Referierte Veröffentlichung
BibTeX
Kurzfassung
We present FREDo, a few-shot document-level relation extraction (FSDLRE) benchmark. As opposed to existing benchmarks which are built on sentence-level relation extraction corpora, we argue that document-level corpora provide more realism, particularly regarding none-of-the-above (NOTA) distributions. Therefore, we propose a set of FSDLRE tasks and construct a benchmark based on two existing supervised learning data sets, DocRED and sciERC. We adapt the state-of-the-art sentence-level method MNAV to the document-level and develop it further for improved domain adaptation. We find FSDLRE to be a challenging setting with interesting new characteristics such as the ability to sample NOTA instances from the support set. The data, code, and trained models are available online (https://github.com/nicpopovic/FREDo).
Download: Media:FSDLRE.pdf
Text Mining, Informationsextraktion, Natürliche Sprachverarbeitung, Deep Learning