Sorokin, Daniil ; Gurevych, Iryna (2017)
Context-Aware Representations for Knowledge Base Relation Extraction.
Copenhagen, Denmark
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
We demonstrate that for sentence-level relation extraction it is beneficial to consider other relations in the sentential context while predicting the target relation. Our architecture uses an LSTM-based encoder to jointly learn representations for all relations in a single sentence. We combine the context representations with an attention mechanism to make the final prediction. Compared to a baseline system, our approach results in an average error reduction of 24% on a held-out set of relations.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2017 |
| Autor(en): | Sorokin, Daniil ; Gurevych, Iryna |
| Art des Eintrags: | Bibliographie |
| Titel: | Context-Aware Representations for Knowledge Base Relation Extraction |
| Sprache: | Englisch |
| Publikationsjahr: | September 2017 |
| Verlag: | Association for Computational Linguistics |
| Buchtitel: | Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP) |
| Veranstaltungsort: | Copenhagen, Denmark |
| URL / URN: | http://aclweb.org/anthology/D17-1188 |
| Zugehörige Links: | |
| Kurzbeschreibung (Abstract): | We demonstrate that for sentence-level relation extraction it is beneficial to consider other relations in the sentential context while predicting the target relation. Our architecture uses an LSTM-based encoder to jointly learn representations for all relations in a single sentence. We combine the context representations with an attention mechanism to make the final prediction. Compared to a baseline system, our approach results in an average error reduction of 24% on a held-out set of relations. |
| Freie Schlagworte: | UKP_a_DLinNLP;UKP_p_QAEduInf;reviewed;UKP_a_LSRA;UKP_reviewed |
| ID-Nummer: | TUD-CS-2017-0119 |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Ubiquitäre Wissensverarbeitung DFG-Graduiertenkollegs DFG-Graduiertenkollegs > Graduiertenkolleg 1994 Adaptive Informationsaufbereitung aus heterogenen Quellen |
| Hinterlegungsdatum: | 31 Mai 2017 14:28 |
| Letzte Änderung: | 24 Jan 2020 12:03 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum