Large-Scale Hierarchical Alignment for Data-driven Text Rewriting

Nikola I. Nikolov, Richard Hahnloser


Abstract
We propose a simple unsupervised method for extracting pseudo-parallel monolingual sentence pairs from comparable corpora representative of two different text styles, such as news articles and scientific papers. Our approach does not require a seed parallel corpus, but instead relies solely on hierarchical search over pre-trained embeddings of documents and sentences. We demonstrate the effectiveness of our method through automatic and extrinsic evaluation on text simplification from the normal to the Simple Wikipedia. We show that pseudo-parallel sentences extracted with our method not only supplement existing parallel data, but can even lead to competitive performance on their own.
Anthology ID:
R19-1098
Volume:
Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)
Month:
September
Year:
2019
Address:
Varna, Bulgaria
Editors:
Ruslan Mitkov, Galia Angelova
Venue:
RANLP
SIG:
Publisher:
INCOMA Ltd.
Note:
Pages:
844–853
Language:
URL:
https://aclanthology.org/R19-1098
DOI:
10.26615/978-954-452-056-4_098
Bibkey:
Cite (ACL):
Nikola I. Nikolov and Richard Hahnloser. 2019. Large-Scale Hierarchical Alignment for Data-driven Text Rewriting. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019), pages 844–853, Varna, Bulgaria. INCOMA Ltd..
Cite (Informal):
Large-Scale Hierarchical Alignment for Data-driven Text Rewriting (Nikolov & Hahnloser, RANLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/R19-1098.pdf
Code
 ninikolov/lha