Understanding Search Queries in Natural Language

Varování

Publikace nespadá pod Filozofickou fakultu, ale pod Fakultu informatiky. Oficiální stránka publikace je na webu muni.cz.

Autoři

NEVĚŘILOVÁ Zuzana KVAŠŠAY Matej

Rok publikování 2018
Druh Článek ve sborníku
Konference Proceedings of Recent Advances in Slavonic Natural Language Processing, RASLAN 2018
Fakulta / Pracoviště MU

Fakulta informatiky

Citace
www https://nlp.fi.muni.cz/raslan/2018/paper07-Neverilova_Kvassay.pdf
Klíčová slova search intent; search query parsing
Popis This work is part of a project aiming to provide one single search endpoint for all company data. We present a search query parser that takes a speech-to-text output, i.e. a sentence. The output is a structured representation of the search query from which a SPARQL query is generated. The SPARQL is then applied to an ontology with the company data. The parsing procedure consists of two steps. First, the search intent is detected, second, the query is parsed based on the search intent. For the intent classification, we use word embeddings with boosting of top 5 words, and support vector machines. For the parsing, we use semantic role labeling, named entity recognition, and external resources such as ConceptNet and DBPedia. The final parsing step is rule-based and related to the ontology structure. The intent classifier accuracy is 94%. In the subsequent manual evaluation,the resulting structures were complete and correct in 51% cases, in 34.57% of cases it was complete and correct but it also contained irrelevant information.
Související projekty:

Používáte starou verzi internetového prohlížeče. Doporučujeme aktualizovat Váš prohlížeč na nejnovější verzi.