|
View: |
Part 1: Document Description
|
|
Citation |
|
|---|---|
|
Title: |
Genre-sensitive Neural Situation Entity classifier (DE, EN) |
|
Identification Number: |
doi:10.11588/data/XXKWU0 |
|
Distributor: |
heiDATA |
|
Date of Distribution: |
2019-10-22 |
|
Version: |
1 |
|
Bibliographic Citation: |
Becker, Maria, 2019, "Genre-sensitive Neural Situation Entity classifier (DE, EN)", https://doi.org/10.11588/data/XXKWU0, heiDATA, V1 |
|
Citation |
|
|
Title: |
Genre-sensitive Neural Situation Entity classifier (DE, EN) |
|
Identification Number: |
doi:10.11588/data/XXKWU0 |
|
Authoring Entity: |
Becker, Maria (Department of Computational Linguistics, Heidelberg University, Germany) |
|
Date of Production: |
2017 |
|
Distributor: |
heiDATA |
|
Access Authority: |
Becker, Maria |
|
Holdings Information: |
https://doi.org/10.11588/data/XXKWU0 |
|
Study Scope |
|
|
Keywords: |
Arts and Humanities, Computer and Information Science, situation entity, classification, entity types, German, English |
|
Topic Classification: |
semantic modeling |
|
Abstract: |
<p>This is a Classifier for situation entity types as described in Becker et al., 2017. These clause types depend on a combination of syntactic-semantic and contextual features. We explore this task in a deeplearning 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. 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.</p> <p>We provide code for the basic local model (GRU), the local model with attention (GRU+attention), and our best performing context model which uses labels of previous clauses and genre information (GRU+attention+label+genre).</p> <p>The data we used for our experiments can be found here, and we used the same train-dev-test split: <a href="https://github.com/annefried/sitent/tree/master/annotated_corpus ">https://github.com/annefried/sitent/tree/master/annotated_corpus </a></p> |
|
Kind of Data: |
program source code, python scripts |
|
Methodology and Processing |
|
|
Sources Statement |
|
|
Data Access |
|
|
Other Study Description Materials |
|
|
Related Materials |
|
|
<p><strong>Situation Entities Corpus:</strong></p> <p>Link to the corpus: <a href="https://github.com/annefried/sitent/tree/master/annotated_corpus">https://github.com/annefried/sitent/tree/master/annotated_corpus</a></p> <p>License: The corpus contains texts from Wikipedia and the written part of MASC <a href="http://www.anc.org/data/masc/">http://www.anc.org/data/masc/</a> and is a part of the <em>Situation entity type labeling system</em> (<a href="https://github.com/annefried/sitent">https://github.com/annefried/sitent</a>). Use of the corpus must be carried out in accordance with the conditions laid down in the licenses of these resources.</p> |
|
|
Related Publications |
|
|
Citation |
|
|
Title: |
<p>Becker, M., Staniek, M., Nastase, V., Palmer, A., and Frank, A. (2017c). Classifying semantic clause types: Modeling context and genre characteristics with recurrent neural networks and attention. In <em>Proceedings of the 6th Joint Conference on Lexical and Computational Semantics (*SEM 2017)</em>, pages 230–240, August 3-4, 2017, Vancouver, Canada.</p> |
|
Identification Number: |
https://www.aclweb.org/anthology/S17-1027 |
|
Bibliographic Citation: |
<p>Becker, M., Staniek, M., Nastase, V., Palmer, A., and Frank, A. (2017c). Classifying semantic clause types: Modeling context and genre characteristics with recurrent neural networks and attention. In <em>Proceedings of the 6th Joint Conference on Lexical and Computational Semantics (*SEM 2017)</em>, pages 230–240, August 3-4, 2017, Vancouver, Canada.</p> |
|
Label: |
RNN_for_Clause_Classification-master.zip |
|
Notes: |
application/zip |