Abstract
In this work, we propose a new model for aspect-based sentiment analysis. In contrast to previous approaches, we jointly model the detection of aspects and the classification of their polarity in an end-to-end trainable neural net- work. We conduct experiments with different neural architectures and word representations on the recent GermEval 2017 dataset. We were able to show considerable performance gains by using the joint modeling approach in all set- tings compared to pipeline approaches. The combination of a convolutional neural network and fasttext embeddings outperformed the best submission of the shared task in 2017, establishing a new state of the art.
Dokumententyp: | Konferenzbeitrag (Paper) |
---|---|
EU Funded Grant Agreement Number: | 740516 |
EU-Projekte: | Horizon 2020 > ERC Grants > ERC Advanced Grant > ERC Grant 740516: NonSequeToR - Non-sequence models for tokenization replacement |
Publikationsform: | Publisher's Version |
Fakultätsübergreifende Einrichtungen: | Centrum für Informations- und Sprachverarbeitung (CIS) |
Themengebiete: | 000 Informatik, Informationswissenschaft, allgemeine Werke > 000 Informatik, Wissen, Systeme
000 Informatik, Informationswissenschaft, allgemeine Werke > 004 Informatik 400 Sprache > 400 Sprache 400 Sprache > 410 Linguistik |
URN: | urn:nbn:de:bvb:19-epub-61858-9 |
Ort: | Stroudsburg PA |
Bemerkung: | ISBN 978-1-948087-84-1 |
Sprache: | Englisch |
Dokumenten ID: | 61858 |
Datum der Veröffentlichung auf Open Access LMU: | 13. Mai 2019, 10:04 |
Letzte Änderungen: | 04. Nov. 2020, 13:39 |