Abstract
| Original language | English |
|---|---|
| Title of host publication | CoNLL 2018 - The 22nd Conference on Computational Natural Language Learning - Proceedings of the Conference |
| Subtitle of host publication | October 31 - November 1, 2018 Brussels, Belgium |
| Editors | Miikka Silfverberg |
| Place of Publication | Stroudsburg PA USA |
| Publisher | The Association for Computational Linguistics |
| Pages | 334-344 |
| Number of pages | 11 |
| ISBN (Electronic) | 9781948087728 |
| Publication status | Published - 2018 |
| Event | Conference on Natural Language Learning 2018 - Brussels, Belgium Duration: 31 Oct 2018 → 1 Nov 2018 https://www.conll.org/2018 |
Conference
| Conference | Conference on Natural Language Learning 2018 |
|---|---|
| Abbreviated title | CoNLL 2018 |
| Country | Belgium |
| City | Brussels |
| Period | 31/10/18 → 1/11/18 |
| Internet address |
Cite this
}
Learning to actively learn neural machine translation. / Liu, Ming; Buntine, Wray; Haffari, Gholamreza.
CoNLL 2018 - The 22nd Conference on Computational Natural Language Learning - Proceedings of the Conference: October 31 - November 1, 2018 Brussels, Belgium. ed. / Miikka Silfverberg. Stroudsburg PA USA : The Association for Computational Linguistics, 2018. p. 334-344.Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review
TY - GEN
T1 - Learning to actively learn neural machine translation
AU - Liu, Ming
AU - Buntine, Wray
AU - Haffari, Gholamreza
PY - 2018
Y1 - 2018
N2 - Traditional active learning (AL) methods for machine translation (MT) rely on heuristics. However, these heuristics are limited when the characteristics of the MT problem change due to e.g. the language pair or the amount of the initial bitext. In this paper, we present a framework to learn sentence selection strategies for neural MT. We train the AL query strategy using a high-resource language-pair based on AL simulations, and then transfer it to the lowresource language-pair of interest. The learned query strategy capitalizes on the shared characteristics between the language pairs to make an effective use of the AL budget. Our experiments on three language-pairs confirms that our method is more effective than strong heuristic-based methods in various conditions, including cold-start and warm-start as well as small and extremely small data conditions.
AB - Traditional active learning (AL) methods for machine translation (MT) rely on heuristics. However, these heuristics are limited when the characteristics of the MT problem change due to e.g. the language pair or the amount of the initial bitext. In this paper, we present a framework to learn sentence selection strategies for neural MT. We train the AL query strategy using a high-resource language-pair based on AL simulations, and then transfer it to the lowresource language-pair of interest. The learned query strategy capitalizes on the shared characteristics between the language pairs to make an effective use of the AL budget. Our experiments on three language-pairs confirms that our method is more effective than strong heuristic-based methods in various conditions, including cold-start and warm-start as well as small and extremely small data conditions.
M3 - Conference Paper
SP - 334
EP - 344
BT - CoNLL 2018 - The 22nd Conference on Computational Natural Language Learning - Proceedings of the Conference
A2 - Silfverberg, Miikka
PB - The Association for Computational Linguistics
CY - Stroudsburg PA USA
ER -