| 4 |
Comparing Feature-Engineering and Feature-Learning Approaches for Multilingual Translationese Classification ...
|
|
|
|
Abstract:
Traditional hand-crafted linguistically-informed features have often been used for distinguishing between translated and original non-translated texts. By contrast, to date, neural architectures without manual feature engineering have been less explored for this task. In this work, we (i) compare the traditional feature-engineering-based approach to the feature-learning-based one and (ii) analyse the neural architectures in order to investigate how well the hand-crafted features explain the variance in the neural models' predictions. We use pre-trained neural word embeddings, as well as several end-to-end neural architectures in both monolingual and multilingual settings and compare them to feature-engineering-based SVM classifiers. We show that (i) neural architectures outperform other approaches by more than 20 accuracy points, with the BERT-based model performing the best in both the monolingual and multilingual settings; (ii) while many individual hand-crafted translationese features correlate with ... : 9 pages, 5 pages appendix, 2 figures, 7 tables. The first 3 authors contributed equally. Accepted to EMNLP 2021, Main Conference ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/2109.07604
https://dx.doi.org/10.48550/arxiv.2109.07604
|
|
BASE
|
|
Hide details
|
|
|
| 5 |
Comparing Feature-Engineering and Feature-Learning Approaches for Multilingual Translationese Classification ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 6 |
Massive vs. Curated Word Embeddings for Low-Resourced Languages. The Case of Yorùbá and Twi ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|
|
