Popularity Prediction for Social Media over Arbitrary Time Horizons
Daniel Haimovich, Dima Karamshuk, Thomas J. Leeper, Evgeniy Riabenko, Milan Vojnovic
Filtering and Mining Parallel Data in a Joint Multilingual Space
Association for Computational Linguistics (ACL)
Abstract
We learn a joint multilingual sentence embedding and use the distance between sentences in different languages to filter noisy parallel data and to mine for parallel data in large news collections. We are able to improve a competitive baseline on the WMT’14 English to German task by 0.3 BLEU by filtering out 25% of the training data. The same approach is used to mine additional bitexts for the WMT’14 system and to obtain competitive results on the BUCC shared task to identify parallel sentences in comparable corpora.
The approach is generic, it can be applied to many language pairs and it is independent of the architecture of the machine translation system.
Latest Publications
VLDB
A-Muze-Net: Music Generation by Composing the Harmony based on the Generated Melody
Or Goren, Eliya Nachmani, Lior Wolf
Log-structured Protocols in Delos
Mahesh Balakrishnan, Mihir Dharamshi, David Geraghty, Santosh Ghosh, Filip Gruszczynski, Jun Li, Jingming Liu, Suyog Mapara, Rajeev Nagar, Ivailo Nedelchev, Francois Richard, Chen Shen, Yee Jiun Song, Rounak Tibrewal, Vidhya Venkat, Ahmed Yossef, Ali Zaveri