: The performance of a statistical machine translation (SMT) system heavily depends on the quantity and quality of the bilingual language resource. However, the pervious work mainl...
In recent work, we proposed an alternative to parallel text as translation model (TM) training data: audio recordings of parallel speech (pSp), as it occurs in any communication s...
Automated grammar correction techniques have seen improvement over the years, but there is still much room for increased performance. Current correction techniques mainly focus on...
Based on simple methods such as observing word and part of speech tag co-occurrence and clustering, we generate syntactic parses of sentences in an entirely unsupervised and self-...
Traditional learning-based coreference resolvers operate by training a mentionpair classifier for determining whether two mentions are coreferent or not. Two independent lines of ...