We present experiments in using discourse structure for improving machine translation evaluation. We first design two discourse-aware similarity measures, which use all-subtree kernels to compare discourse parse trees in accordance with the Rhetorical Structure Theory. Then, we show that these measures can help improve a number of existing machine translation evaluation metrics both at the segmentand at the system-level. Rather than proposing a single new metric, we show that discourse information is complementary to the state-of-the-art evaluation metrics, and thus should be taken into account in the development of future richer evaluation metrics.

@inproceedings{guzman-EtAl:2014:P14-1, abstract = {We present experiments in using discourse structure for improving machine translation evaluation. We first design two discourse-aware similarity measures, which use all-subtree kernels to compare discourse parse trees in accordance with the Rhetorical Structure Theory. Then, we show that these measures can help improve a number of existing machine translation evaluation metrics both at the segmentand at the system-level. Rather than proposing a single new metric, we show that discourse information is complementary to the state-of-the-art evaluation metrics, and thus should be taken into account in the development of future richer evaluation metrics.}, address = {Baltimore, Maryland, USA}, author = {Guzm\'{a}n, Francisco and Joty, Shafiq and M\`{a}rquez, Llu\'{i}s and Nakov, Preslav}, booktitle = {Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics ({ACL}'14)}, link = {http://www.aclweb.org/anthology/P/P14/P14-1065}, month = {June}, pages = {687--698}, publisher = {Association for Computational Linguistics}, title = {Using Discourse Structure Improves Machine Translation Evaluation}, year = {2014} }