1 |
Studies in Analytical Reproducibility: the Conquaire Project ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Bridging the Gap Between Ontology and Lexicon via Class-Specific Association Rules Mined from a Loosely-Parallel Text-Data Corpus ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Linguistic linked data: representation, generation and applications
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Recent Developments for the Linguistic Linked Open Data Infrastructure ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Recent Developments for the Linguistic Linked Open Data Infrastructure ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Recent Developments for the Linguistic Linked Open Data Infrastructure ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Recent Developments for the Linguistic Linked Open Data Infrastructure ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Recent Developments for the Linguistic Linked Open Data Infrastructure ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
D5.1 Report on Vocabularies for Interoperable Language Resources and Services ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
D5.1 Report on Vocabularies for Interoperable Language Resources and Services ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Recent Developments for the Linguistic Linked Open Data Infrastructure ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Terme-à-LLOD: Simplifying the Conversion and Hosting of Terminological Resources as Linked Data ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Terme-à-LLOD: Simplifying the Conversion and Hosting of Terminological Resources as Linked Data ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Extending Neural Question Answering with Linguistic Input Features ...
|
|
|
|
Abstract:
Considerable progress in neural question answering has been made on competitive general domain datasets. In order to explore methods to aid the generalization potential of question answering models, we reimplement a state-of-the-art architecture, perform a parameter search on an open-domain dataset and evaluate a first approach for integrating linguistic input features such as part-of-speech tags, syntactic dependency relations and semantic roles. The results show that adding these input features has a greater impact on performance than any of the architectural parameters we explore. Our findings suggest that these layers of linguistic knowledge have the potential to substantially increase the generalization capacities of neural QA models, thus facilitating cross-domain model transfer or the development of domain-agnostic QA models. ...
|
|
URL: https://zenodo.org/record/3373529 https://dx.doi.org/10.5281/zenodo.3373529
|
|
BASE
|
|
Hide details
|
|
19 |
Extending Neural Question Answering with Linguistic Input Features ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
AMUSE: Multilingual Semantic Parsing for Question Answering over Linked Data ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|