Don't 'have a clue'? Unsupervised co-learning of downward-entailing operators

Details Don't 'have a clue'? Unsupervised co-learning of downward-entailing operators Don't 'have a clue'? Unsupervised co-learning of downward-entailing operators

2010-08-18

arxiv.org/abs/1008.3169v2

Proceedings of the ACL Short Papers, pp. 247-252, 2010

Computer Science

Computation and Language

pp 1-6 are identical to the ACL 2010 published version; pp. 7-8 are the "externally-available appendices". Revision contains a

Scientific paper

Researchers in textual entailment have begun to consider inferences involving 'downward-entailing operators', an interesting and important class of lexical items that change the way inferences are made. Recent work proposed a method for learning English downward-entailing operators that requires access to a high-quality collection of 'negative polarity items' (NPIs). However, English is one of the very few languages for which such a list exists. We propose the first approach that can be applied to the many languages for which there is no pre-existing high-precision database of NPIs. As a case study, we apply our method to Romanian and show that our method yields good results. Also, we perform a cross-linguistic analysis that suggests interesting connections to some findings in linguistic typology.

Affiliated with

Also associated with

No associations

Rating

Don't 'have a clue'? Unsupervised co-learning of downward-entailing operators does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Don't 'have a clue'? Unsupervised co-learning of downward-entailing operators, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Don't 'have a clue'? Unsupervised co-learning of downward-entailing operators will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-134338