Mesgar, Mohsen ; Youssef, Paul ; Li, Lin ; Bierwirth, Dominik ; Meyer, Christian M. ; Gurevych, Iryna (2019)
When is ACL's Deadline? A Scientific Conversational Agent.
doi: 10.48550/arXiv.1911.10392
Report, Bibliographie
Kurzbeschreibung (Abstract)
Our conversational agent UKP-ATHENA assists NLP researchers in finding and exploring scientific literature, identifying relevant authors, planning or post-processing conference visits, and preparing paper submissions using a unified interface based on natural language inputs and responses. UKP-ATHENA enables new access paths to our swiftly evolving research area with its massive amounts of scientific information and high turnaround times. UKP-ATHENA's responses connect information from multiple heterogeneous sources which researchers currently have to explore manually one after another. Unlike a search engine, UKP-ATHENA maintains the context of a conversation to allow for efficient information access on papers, researchers, and conferences. Our architecture consists of multiple components with reference implementations that can be easily extended by new skills and domains. Our user-based evaluation shows that UKP-ATHENA already responds 45% of different formulations of defined intents with 37% information coverage rate.
| Typ des Eintrags: | Report |
|---|---|
| Erschienen: | 2019 |
| Autor(en): | Mesgar, Mohsen ; Youssef, Paul ; Li, Lin ; Bierwirth, Dominik ; Meyer, Christian M. ; Gurevych, Iryna |
| Art des Eintrags: | Bibliographie |
| Titel: | When is ACL's Deadline? A Scientific Conversational Agent |
| Sprache: | Englisch |
| Publikationsjahr: | 26 November 2019 |
| Verlag: | arXiv |
| Reihe: | Computation and Language |
| Kollation: | 7 Seiten |
| DOI: | 10.48550/arXiv.1911.10392 |
| Kurzbeschreibung (Abstract): | Our conversational agent UKP-ATHENA assists NLP researchers in finding and exploring scientific literature, identifying relevant authors, planning or post-processing conference visits, and preparing paper submissions using a unified interface based on natural language inputs and responses. UKP-ATHENA enables new access paths to our swiftly evolving research area with its massive amounts of scientific information and high turnaround times. UKP-ATHENA's responses connect information from multiple heterogeneous sources which researchers currently have to explore manually one after another. Unlike a search engine, UKP-ATHENA maintains the context of a conversation to allow for efficient information access on papers, researchers, and conferences. Our architecture consists of multiple components with reference implementations that can be easily extended by new skills and domains. Our user-based evaluation shows that UKP-ATHENA already responds 45% of different formulations of defined intents with 37% information coverage rate. |
| Freie Schlagworte: | KDSL,UKP_p_QAEduInf |
| Zusätzliche Informationen: | 1.Version |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Ubiquitäre Wissensverarbeitung |
| Hinterlegungsdatum: | 29 Nov 2019 05:46 |
| Letzte Änderung: | 19 Dez 2024 09:00 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum