Botschen, Teresa ; Mousselly-Sergieh, Hatem ; Gurevych, Iryna (2017)
Prediction of Frame-to-Frame Relations in the FrameNet Hierarchy with Frame Embeddings.
Vancouver, Canada
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
Automatic completion of frame-to-frame (F2F) relations in the FrameNet (FN) hierarchy has received little attention, although they incorporate meta-level commonsense knowledge and are used in downstream approaches. We address the problem of sparsely annotated F2F relations. First, we examine whether the manually defined F2F relations emerge from text by learning text-based frame embeddings. Our analysis reveals insights about the difficulty of reconstructing F2F relations purely from text. Second, we present different systems for predicting F2F relations; our best-performing one uses the FN hierarchy to train on and to ground embeddings in. A comparison of systems and embeddings exposes the crucial influence of knowledge-based embeddings to a system’s performance in predicting F2F relations.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2017 |
| Autor(en): | Botschen, Teresa ; Mousselly-Sergieh, Hatem ; Gurevych, Iryna |
| Art des Eintrags: | Bibliographie |
| Titel: | Prediction of Frame-to-Frame Relations in the FrameNet Hierarchy with Frame Embeddings |
| Sprache: | Englisch |
| Publikationsjahr: | August 2017 |
| Buchtitel: | Proceedings of th 2nd Workshop on Representation Learning for NLP (RepL4NLP, held in conjunction with ACL 2017) |
| Veranstaltungsort: | Vancouver, Canada |
| URL / URN: | http://www.aclweb.org/anthology/W17-2618 |
| Kurzbeschreibung (Abstract): | Automatic completion of frame-to-frame (F2F) relations in the FrameNet (FN) hierarchy has received little attention, although they incorporate meta-level commonsense knowledge and are used in downstream approaches. We address the problem of sparsely annotated F2F relations. First, we examine whether the manually defined F2F relations emerge from text by learning text-based frame embeddings. Our analysis reveals insights about the difficulty of reconstructing F2F relations purely from text. Second, we present different systems for predicting F2F relations; our best-performing one uses the FN hierarchy to train on and to ground embeddings in. A comparison of systems and embeddings exposes the crucial influence of knowledge-based embeddings to a system’s performance in predicting F2F relations. |
| Freie Schlagworte: | reviewed;UKP_reviewed;AIPHES_area_c3 |
| ID-Nummer: | TUD-CS-2017-0123 |
| 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 14:55 |
| 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