@article {13708, title = {A modality lexicon and its use in automatic tagging}, journal = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC{\textquoteright}10)}, year = {2010}, month = {2010///}, pages = {1402 - 1407}, abstract = {This paper describes our resource-building results for an eight-week JHU Human Language Technology Center of Excellence SummerCamp for Applied Language Exploration (SCALE-2009) on Semantically-Informed Machine Translation. Specifically, we describe the construction of a modality annotation scheme, a modality lexicon, and two automated modality taggers that were built using the lexicon and annotation scheme. Our annotation scheme is based on identifying three components of modality: a trigger, a target and a holder. We describe how our modality lexicon was produced semi-automatically, expanding from an initial hand-selected list of modality trigger words and phrases. The resulting expanded modality lexicon is being made publicly available. We demonstrate that one tagger{\textemdash}a structure-based tagger{\textemdash}results in precision around 86\% (depending on genre) for tagging of a standard LDC data set. In a machine translation application, using the structure-based tagger to annotate English modalities on an English-Urdu training corpus improved the translation quality score for Urdu by 0.3 Bleu points in the face of sparse training data. }, author = {Baker,K. and Bloodgood,M. and Dorr, Bonnie J and Filardo,N.W. and Levin,L. and Piatko,C.} }