Classifying Semantic Clause Types: Modeling Context and Genre Characteristics with Recurrent Neural Networks and Attention

Maria Becker, Michael Staniek, Vivi Nastase, Alexis Palmer, Anette Frank


Abstract
Detecting aspectual properties of clauses in the form of situation entity types has been shown to depend on a combination of syntactic-semantic and contextual features. We explore this task in a deep-learning framework, where tuned word representations capture lexical, syntactic and semantic features. We introduce an attention mechanism that pinpoints relevant context not only for the current instance, but also for the larger context. Apart from implicitly capturing task relevant features, the advantage of our neural model is that it avoids the need to reproduce linguistic features for other languages and is thus more easily transferable. We present experiments for English and German that achieve competitive performance. We present a novel take on modeling and exploiting genre information and showcase the adaptation of our system from one language to another.
Anthology ID:
S17-1027
Volume:
Proceedings of the 6th Joint Conference on Lexical and Computational Semantics (*SEM 2017)
Month:
August
Year:
2017
Address:
Vancouver, Canada
Venue:
*SEM
SIGs:
SIGSEM | SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
230–240
Language:
URL:
https://aclanthology.org/S17-1027
DOI:
10.18653/v1/S17-1027
Bibkey:
Cite (ACL):
Maria Becker, Michael Staniek, Vivi Nastase, Alexis Palmer, and Anette Frank. 2017. Classifying Semantic Clause Types: Modeling Context and Genre Characteristics with Recurrent Neural Networks and Attention. In Proceedings of the 6th Joint Conference on Lexical and Computational Semantics (*SEM 2017), pages 230–240, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
Classifying Semantic Clause Types: Modeling Context and Genre Characteristics with Recurrent Neural Networks and Attention (Becker et al., *SEM 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp-22-attachments/S17-1027.pdf