November 16, 2021
Despite their failure to solve the compositional SCAN dataset, seq2seq architectures still achieve astonishing success on more practical tasks. This observation pushes us to question the usefulness of SCAN-style compositional generalization in realistic NLP tasks. In this work, we study the benefit that such compositionality brings about to several machine translation tasks. We present several focused modifications of Transformer that greatly improve generalization capabilities on SCAN and select one that remains on par with a vanilla Transformer on a standard machine translation (MT) task. Next, we study its performance in low-resource settings and on a newly introduced distribution-shifted English-French translation task. Overall, we find that improvements of a SCAN-capable model do not directly transfer to the resource-rich MT setup. In contrast, in the low-resource setup, general modifications lead to an improvement of up to 13.1% BLEU score w.r.t. a vanilla Transformer. Similarly, an improvement of 14% in an accuracy-based metric is achieved in the introduced compositional English-French translation task. This provides experimental evidence that the compositional generalization assessed in SCAN is particularly useful in resource-starved and distribution-shifted scenarios.
Written by
Rahma Chaabouni
Roberto Dessì
Evgeny Kharitonov
Publisher
BlackBox Workshop
Research Topics
December 06, 2021
Hongyu Gong, Yun Tang, Juan Miguel Pino, Xian Li
December 06, 2021
November 08, 2021
Baptiste Rozière, Marie-Anne Lachaux, Marc Szafraniec, Guillaume Lample
November 08, 2021
October 26, 2021
Xuezhe Ma, Xiang Kong, Sinong Wang, Chunting Zhou, Jonathan May, Hao Ma, Luke Zettlemoyer
October 26, 2021
October 25, 2021
October 25, 2021