The present research studies the impact of decompounding and two different word normalization methods, stemming and lemmatization, on monolingual and bilingual retrieval. The langu...
Abstract. The last decade has seen an increase in the number of available corpus query systems. These systems generally implement a query language as well as a database model. We r...
Topic models are a useful tool for analyzing large text collections, but have previously been applied in only monolingual, or at most bilingual, contexts. Meanwhile, massive colle...
David M. Mimno, Hanna M. Wallach, Jason Naradowsky...
This paper proposes a method for dealing with repairs in action control dialogue to resolve participants' misunderstanding. The proposed method identifies the repair target b...
Building NLG systems, in particular statistical ones, requires parallel data (paired inputs and outputs) which do not generally occur naturally. In this paper, we investigate the ...