Dynamic Faceted Search for Technical Support Exploiting Induced Knowledge
| Autor: | Shu Tao, Yu Deng, Ruchi Mahindru, Nandana Mihindukulasooriya, Sarthak Dash, Nicolas Rodolfo Fauceglia, Gaetano Rossiello, Alfio Gliozzo, Faisal Mahbub Chowdhury |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Computer science
010401 analytical chemistry 020207 software engineering 02 engineering and technology Service provider 01 natural sciences Remote assistance 0104 chemical sciences Domain (software engineering) Technical support Human–computer interaction 0202 electrical engineering electronic engineering information engineering Faceted search Leverage (statistics) Distributed File System Semantic Web |
| Zdroj: | Lecture Notes in Computer Science ISBN: 9783030624651 ISWC (2) |
| Popis: | IT support is a vital and integral part of technology adoption. Conventionally, IT support service providers heavily rely on human effort and expertise to respond to user queries. Given the cost-benefit and 24 \(\times \) 7 availability for answering user questions, Virtual Assistants (VA) are highly applicable in the technical support domain. In this paper, we describe a novel methodology for building interactive virtual assistants for IT support using Dynamic Faceted Search (DFS). Given a question, dynamic facets are generated automatically, enabling the user to refine and narrow down their intent. To do so we leverage knowledge automatically induced from textual content and existing Semantic Web resources such as Wikidata. Such knowledge is then used to dynamically generate facets interactively based on the user’s responses as shown in the demo video (https://ibm.box.com/v/iswc2020-dfs). The experiments on two real-world datasets in the IT support domain show the effectiveness of DFS in refining the user’s queries and efficiently identifying possible solutions to their technical problems. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|