ISOFT at QALD-5: Hybrid Question Answering System over Linked Data and Text Data
نویسندگان
چکیده
We develop a question answering system over linked data and text data. We combine knowledgebase-based question answering (KBQA) approach and information retrieval based question answering (IRQA) approach to solve complex questions. To solve this kind of complex question using only knowledgebase and SPARQL query, we use various methods to translate natural language (NL) phrases in question to entities and properties in knowledgebase (KB). However, converting NL phrases to entities and properties in KB many times usually has low accuracy in most KBQA. To reduce the number of converting NL phrases to words in KB, we extract clues of answers using IRQA and generate one SPARQL based on the extracted clues and analyses of the question and the semantic answer type.
منابع مشابه
ISOFT at QALD-4: Semantic Similarity-based Question Answering System over Linked Data
We present a question answering system over linked data. We use natural language processing tools to extract slots and SPARQL templates from the question. Then, we use semantic similarity to map a natural language question to a SPARQL query. We combine important words to avoid loss of meaning, and compare combined words with uniform resource identifiers (URIs) from a knowledgebase (KB). This pr...
متن کاملAnswering Boolean Hybrid Questions with HAWK
The decentral architecture behind the Web has led to pieces of information being distributed across data sources with varying structure. Hence, answering complex questions often requires combining information from structured and unstructured data sources. We present an extension for HAWK, a novel search approach for Hybrid Question Answering based on combining Linked Data and textual data. Espe...
متن کاملHAWK - Hybrid Question Answering Using Linked Data
The decentral architecture behind the Web has led to pieces of information being distributed across data sources with varying structure. Hence, answering complex questions often required combining information from structured and unstructured data sources. We present HAWK, a novel entity search approach for Hybrid Question Answering based on combining Linked Data and textual data. The approach u...
متن کاملHAWK@QALD5 - Trying to Answer Hybrid Questions with Various Simple Ranking Techniques
The growing amount of data available in the Document Web as well as in the Linked Data Web has lead to an information gap. Information needed to answer complex questions might often require full-text data as well as Linked Data. Thus, HAWK combines unstructured and structured data sources. In this article, we introduce HAWK, a novel entity search approach for hybrid question answering based on ...
متن کاملQALD-3: Multilingual Question Answering over Linked Data
The third edition of the open challenge on Question Answering over Linked Data (QALD-3) has put a strong emphasis on multilinguality. This paper provides an overview of the first task, focusing on multilingual question answering, which attracted six teams to submit results.
متن کامل