Learning to Organize a Bag of Words into Sentences with Neural Networks: An Empirical Study

Chongyang Tao, Shen Gao, Juntao Li, Yansong Feng, Dongyan Zhao, Rui Yan


Abstract
Sequential information, a.k.a., orders, is assumed to be essential for processing a sequence with recurrent neural network or convolutional neural network based encoders. However, is it possible to encode natural languages without orders? Given a bag of words from a disordered sentence, humans may still be able to understand what those words mean by reordering or reconstructing them. Inspired by such an intuition, in this paper, we perform a study to investigate how “order” information takes effects in natural language learning. By running comprehensive comparisons, we quantitatively compare the ability of several representative neural models to organize sentences from a bag of words under three typical scenarios, and summarize some empirical findings and challenges, which can shed light on future research on this line of work.
Anthology ID:
2021.naacl-main.134
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1682–1691
Language:
URL:
https://aclanthology.org/2021.naacl-main.134
DOI:
10.18653/v1/2021.naacl-main.134
Bibkey:
Cite (ACL):
Chongyang Tao, Shen Gao, Juntao Li, Yansong Feng, Dongyan Zhao, and Rui Yan. 2021. Learning to Organize a Bag of Words into Sentences with Neural Networks: An Empirical Study. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1682–1691, Online. Association for Computational Linguistics.
Cite (Informal):
Learning to Organize a Bag of Words into Sentences with Neural Networks: An Empirical Study (Tao et al., NAACL 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/2021.naacl-main.134.pdf
Data
Penn Treebank