TY - GEN
T1 - Learning to learn morphological inflection for resource-poor languages
AU - Kann, Katharina
AU - Bowman, Samuel R.
AU - Cho, Kyunghyun
N1 - Funding Information:
This work has received support from Samsung Advanced Institute of Technology (Next Generation Deep Learning: from Pattern Recognition to AI) and Samsung Electronics (Improving Deep Learning using Latent Structure). It further benefited from the donation of a Titan V GPU by NVIDIA Corporation.
Publisher Copyright:
Copyright © 2020, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
PY - 2020
Y1 - 2020
N2 - We propose to cast the task of morphological inflection—mapping a lemma to an indicated inflected form—for resource-poor languages as a meta-learning problem. Treating each language as a separate task, we use data from high-resource source languages to learn a set of model parameters that can serve as a strong initialization point for fine-tuning on a resource-poor target language. Experiments with two model architectures on 29 target languages from 3 families show that our suggested approach outperforms all baselines. In particular, it obtains a 31.7% higher absolute accuracy than a previously proposed cross-lingual transfer model and outperforms the previous state of the art by 1.7% absolute accuracy on average over languages.
AB - We propose to cast the task of morphological inflection—mapping a lemma to an indicated inflected form—for resource-poor languages as a meta-learning problem. Treating each language as a separate task, we use data from high-resource source languages to learn a set of model parameters that can serve as a strong initialization point for fine-tuning on a resource-poor target language. Experiments with two model architectures on 29 target languages from 3 families show that our suggested approach outperforms all baselines. In particular, it obtains a 31.7% higher absolute accuracy than a previously proposed cross-lingual transfer model and outperforms the previous state of the art by 1.7% absolute accuracy on average over languages.
UR - http://www.scopus.com/inward/record.url?scp=85095226449&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85095226449&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85095226449
T3 - AAAI 2020 - 34th AAAI Conference on Artificial Intelligence
SP - 8058
EP - 8065
BT - AAAI 2020 - 34th AAAI Conference on Artificial Intelligence
PB - AAAI press
T2 - 34th AAAI Conference on Artificial Intelligence, AAAI 2020
Y2 - 7 February 2020 through 12 February 2020
ER -