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 ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Extending Neural Question Answering with Linguistic Input Features ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
AMUSE: Multilingual Semantic Parsing for Question Answering over Linked Data ...
|
|
|
|
Abstract:
The task of answering natural language questions over RDF data has received wide interest in recent years, in particular in the context of the series of QALD benchmarks. The task consists of mapping a natural language question to an executable form, e.g. SPARQL, so that answers from a given KB can be extracted. So far, most systems proposed are i) monolingual and ii) rely on a set of hard-coded rules to interpret questions and map them into a SPARQL query. We present the first multilingual QALD pipeline that induces a model from training data for mapping a natural language question into logical form as probabilistic inference. In particular, our approach learns to map universal syntactic dependency representations to a language-independent logical form based on DUDES (Dependency-based Underspecified Discourse Representation Structures) that are then mapped to a SPARQL query as a deterministic second step. Our model builds on factor graphs that rely on features extracted from the dependency graph and ... : International Semantic Web Conference, 2017 ...
|
|
Keyword:
Artificial Intelligence cs.AI; Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.1802.09296 https://arxiv.org/abs/1802.09296
|
|
BASE
|
|
Hide details
|
|
|
|