Geigle, Gregor ; Reimers, Nils ; Rücklé, Andreas ; Gurevych, Iryna (2021)
TWEAC: Transformer with Extendable QA Agent Classifiers.
doi: 10.48550/arXiv.2104.07081
Report, Bibliographie
Kurzbeschreibung (Abstract)
Question answering systems should help users to access knowledge on a broad range of topics and to answer a wide array of different questions. Most systems fall short of this expectation as they are only specialized in one particular setting, e.g., answering factual questions with Wikipedia data. To overcome this limitation, we propose composing multiple QA agents within a meta-QA system. We argue that there exist a wide range of specialized QA agents in literature. Thus, we address the central research question of how to effectively and efficiently identify suitable QA agents for any given question. We study both supervised and unsupervised approaches to address this challenge, showing that TWEAC -- Transformer with Extendable Agent Classifiers -- achieves the best performance overall with 94% accuracy. We provide extensive insights on the scalability of TWEAC, demonstrating that it scales robustly to over 100 QA agents with each providing just 1000 examples of questions they can answer.
| Typ des Eintrags: | Report |
|---|---|
| Erschienen: | 2021 |
| Autor(en): | Geigle, Gregor ; Reimers, Nils ; Rücklé, Andreas ; Gurevych, Iryna |
| Art des Eintrags: | Bibliographie |
| Titel: | TWEAC: Transformer with Extendable QA Agent Classifiers |
| Sprache: | Englisch |
| Publikationsjahr: | 14 April 2021 |
| Verlag: | arXiv |
| Reihe: | Computation and Language |
| Auflage: | 1. Version |
| DOI: | 10.48550/arXiv.2104.07081 |
| URL / URN: | https://arxiv.org/abs/2104.07081 |
| Zugehörige Links: | |
| Kurzbeschreibung (Abstract): | Question answering systems should help users to access knowledge on a broad range of topics and to answer a wide array of different questions. Most systems fall short of this expectation as they are only specialized in one particular setting, e.g., answering factual questions with Wikipedia data. To overcome this limitation, we propose composing multiple QA agents within a meta-QA system. We argue that there exist a wide range of specialized QA agents in literature. Thus, we address the central research question of how to effectively and efficiently identify suitable QA agents for any given question. We study both supervised and unsupervised approaches to address this challenge, showing that TWEAC -- Transformer with Extendable Agent Classifiers -- achieves the best performance overall with 94% accuracy. We provide extensive insights on the scalability of TWEAC, demonstrating that it scales robustly to over 100 QA agents with each providing just 1000 examples of questions they can answer. |
| Freie Schlagworte: | UKP_p_DIP, UKP_p_square, UKP_p_texprax, UKP_p_seditrah_factcheck |
| Zusätzliche Informationen: | Preprint |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Ubiquitäre Wissensverarbeitung |
| Hinterlegungsdatum: | 07 Sep 2021 14:23 |
| Letzte Änderung: | 11 Jul 2024 10:21 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum