TY - GEN
T1 - A Unified Evaluation Framework for Novelty Detection and Accommodation in NLP with an Instantiation in Authorship Attribution
AU - Varshney, Neeraj
AU - Gupta, Himanshu
AU - Robertson, Eric
AU - Liu, Bing
AU - Baral, Chitta
N1 - Publisher Copyright:
© 2023 Association for Computational Linguistics.
PY - 2023
Y1 - 2023
N2 - State-of-the-art natural language processing models have been shown to achieve remarkable performance in 'closed-world' settings where all the labels in the evaluation set are known at training time. However, in real-world settings, 'novel' instances that do not belong to any known class are often observed. This renders the ability to deal with novelties crucial. To initiate a systematic research in this important area of 'dealing with novelties', we introduce NoveltyTask, a multi-stage task to evaluate a system's performance on pipelined novelty 'detection' and 'accommodation' tasks. We provide mathematical formulation of NoveltyTask and instantiate it with the authorship attribution task that pertains to identifying the correct author of a given text. We use Amazon reviews corpus and compile a large dataset (consisting of 250k instances across 200 authors/labels) for NoveltyTask. We conduct comprehensive experiments and explore several baseline methods for the task. Our results show that the methods achieve considerably low performance making the task challenging and leaving sufficient room for improvement. Finally, we believe our work will encourage research in this underexplored area of dealing with novelties, an important step en route to developing robust systems.
AB - State-of-the-art natural language processing models have been shown to achieve remarkable performance in 'closed-world' settings where all the labels in the evaluation set are known at training time. However, in real-world settings, 'novel' instances that do not belong to any known class are often observed. This renders the ability to deal with novelties crucial. To initiate a systematic research in this important area of 'dealing with novelties', we introduce NoveltyTask, a multi-stage task to evaluate a system's performance on pipelined novelty 'detection' and 'accommodation' tasks. We provide mathematical formulation of NoveltyTask and instantiate it with the authorship attribution task that pertains to identifying the correct author of a given text. We use Amazon reviews corpus and compile a large dataset (consisting of 250k instances across 200 authors/labels) for NoveltyTask. We conduct comprehensive experiments and explore several baseline methods for the task. Our results show that the methods achieve considerably low performance making the task challenging and leaving sufficient room for improvement. Finally, we believe our work will encourage research in this underexplored area of dealing with novelties, an important step en route to developing robust systems.
UR - http://www.scopus.com/inward/record.url?scp=85175447780&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85175447780&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85175447780
T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics
SP - 1794
EP - 1818
BT - Findings of the Association for Computational Linguistics, ACL 2023
PB - Association for Computational Linguistics (ACL)
T2 - 61st Annual Meeting of the Association for Computational Linguistics, ACL 2023
Y2 - 9 July 2023 through 14 July 2023
ER -