Enriching Phrase-Based Statistical Machine Translation with POS Information

This work presents an extension to phrasebased statistical machine translation models which incorporates linguistic knowledge, namely part-of-speech information. Scores are added to the standard phrase table which represent how the phrases correspond to their translations on the partof-speech level. We suggest two different kinds of scores. They are learned from a POS-tagged version of the parallel training corpus. The decoding strategy does not have to be modified. Our experiments show that our extended models achieve similar BLEU and NIST scores compared to the standard model. Additional manual investigation reveals local improvements in the translation quality.