AMUSE: Multilingual Semantic Parsing for Question Answering over Linked Data

Hakimov S, Jebbara S, Cimiano P (2017)
In: The Semantic Web - ISWC 2017. 16th International Semantic Web Conference. Proceedings. d'Amato C, Fernandez M, Tamma V (Eds); Lecture Notes in Computer Science, 10587. Cham: Springer: 329-346.

Konferenzbeitrag | Veröffentlicht | Englisch
 
Download
OA 461.64 KB
Herausgeber*in
d'Amato, Claudia; Fernandez, Miriam; Tamma, Valentina
Abstract / Bemerkung
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 corresponding semantic representations.We rely on approximate inference techniques, Markov Chain Monte Carlo methods in particular, as well as Sample Rank to update parameters using a ranking objective. Our focus lies on developing methods that overcome the lexical gap and present a novel combination of machine translation and word embedding approaches for this purpose. As a proof of concept for our approach, we evaluate our approach on the QALD-6 datasets for English, German & Spanish.
Stichworte
question answering; multilinguality; QALD; probabilistic graphical models; factor graphs
Erscheinungsjahr
2017
Titel des Konferenzbandes
The Semantic Web - ISWC 2017. 16th International Semantic Web Conference. Proceedings
Serien- oder Zeitschriftentitel
Lecture Notes in Computer Science
Band
10587
Seite(n)
329-346
Konferenz
16th International Semantic Web Conference (ISWC 2017)
Konferenzort
Vienna
Konferenzdatum
2017-10-21 – 2017-10-25
eISBN
978-3-319-68288-4
Page URI
https://pub.uni-bielefeld.de/record/2913141

Zitieren

Hakimov S, Jebbara S, Cimiano P. AMUSE: Multilingual Semantic Parsing for Question Answering over Linked Data. In: d'Amato C, Fernandez M, Tamma V, eds. The Semantic Web - ISWC 2017. 16th International Semantic Web Conference. Proceedings. Lecture Notes in Computer Science. Vol 10587. Cham: Springer; 2017: 329-346.
Hakimov, S., Jebbara, S., & Cimiano, P. (2017). AMUSE: Multilingual Semantic Parsing for Question Answering over Linked Data. In C. d'Amato, M. Fernandez, & V. Tamma (Eds.), Lecture Notes in Computer Science: Vol. 10587. The Semantic Web - ISWC 2017. 16th International Semantic Web Conference. Proceedings (pp. 329-346). Cham: Springer. doi:10.1007/978-3-319-68288-4_20
Hakimov, Sherzod, Jebbara, Soufian, and Cimiano, Philipp. 2017. “AMUSE: Multilingual Semantic Parsing for Question Answering over Linked Data”. In The Semantic Web - ISWC 2017. 16th International Semantic Web Conference. Proceedings, ed. Claudia d'Amato, Miriam Fernandez, and Valentina Tamma, 10587:329-346. Lecture Notes in Computer Science. Cham: Springer.
Hakimov, S., Jebbara, S., and Cimiano, P. (2017). “AMUSE: Multilingual Semantic Parsing for Question Answering over Linked Data” in The Semantic Web - ISWC 2017. 16th International Semantic Web Conference. Proceedings, d'Amato, C., Fernandez, M., and Tamma, V. eds. Lecture Notes in Computer Science, vol. 10587, (Cham: Springer), 329-346.
Hakimov, S., Jebbara, S., & Cimiano, P., 2017. AMUSE: Multilingual Semantic Parsing for Question Answering over Linked Data. In C. d'Amato, M. Fernandez, & V. Tamma, eds. The Semantic Web - ISWC 2017. 16th International Semantic Web Conference. Proceedings. Lecture Notes in Computer Science. no.10587 Cham: Springer, pp. 329-346.
S. Hakimov, S. Jebbara, and P. Cimiano, “AMUSE: Multilingual Semantic Parsing for Question Answering over Linked Data”, The Semantic Web - ISWC 2017. 16th International Semantic Web Conference. Proceedings, C. d'Amato, M. Fernandez, and V. Tamma, eds., Lecture Notes in Computer Science, vol. 10587, Cham: Springer, 2017, pp.329-346.
Hakimov, S., Jebbara, S., Cimiano, P.: AMUSE: Multilingual Semantic Parsing for Question Answering over Linked Data. In: d'Amato, C., Fernandez, M., and Tamma, V. (eds.) The Semantic Web - ISWC 2017. 16th International Semantic Web Conference. Proceedings. Lecture Notes in Computer Science. 10587, p. 329-346. Springer, Cham (2017).
Hakimov, Sherzod, Jebbara, Soufian, and Cimiano, Philipp. “AMUSE: Multilingual Semantic Parsing for Question Answering over Linked Data”. The Semantic Web - ISWC 2017. 16th International Semantic Web Conference. Proceedings. Ed. Claudia d'Amato, Miriam Fernandez, and Valentina Tamma. Cham: Springer, 2017.Vol. 10587. Lecture Notes in Computer Science. 329-346.
Alle Dateien verfügbar unter der/den folgenden Lizenz(en):
Creative Commons Namensnennung - Weitergabe unter gleichen Bedingungen 3.0 Unported (CC BY-SA 3.0):
Volltext(e)
Name
461.64 KB
Access Level
OA Open Access
Zuletzt Hochgeladen
2019-09-06T09:18:50Z
MD5 Prüfsumme
3d631be0c8b3faba797bbd6ec172d055


Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Suchen in

Google Scholar