Abstract / Description of output
Neural machine translation systems have been shown to achieve state-of-the-art translation performance for many language pairs. In order to produce a correct translation, MT systems must learn how to disambiguate words with multiple senses and pick the correct translation. We explore the extent to which the word embeddings for ambiguous words are able to disambiguate senses at deeper layers of the NMT encoder, which are thought to represent words with surrounding context. Consistent with previous research, we find that the NMT system fails to translate many ambiguous words correctly. We provide an evaluation framework to use for proposed improvements to word sense disambiguation abilities of NMT systems.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the 13th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Papers) |
| Place of Publication | Boston, MA, USA |
| Publisher | Association for Machine Translation in the Americas, AMTA |
| Pages | 125-131 |
| Number of pages | 7 |
| Publication status | Published - 21 Mar 2018 |
| Event | 13th Conference of the Association for Machine Translation in the Americas - Boston, United States Duration: 17 Mar 2018 → 21 Mar 2018 https://amtaweb.org/ |
Conference
| Conference | 13th Conference of the Association for Machine Translation in the Americas |
|---|---|
| Abbreviated title | AMTA 2018 |
| Country/Territory | United States |
| City | Boston |
| Period | 17/03/18 → 21/03/18 |
| Internet address |