Abstract. We introduce LTAG-spinal, a novel variant of traditional Lexicalized Tree Adjoining Grammar (LTAG) with desirable linguistic, computational and statistical properties. Un...
This paper describes an empirical study of high-performance dependency parsers based on a semi-supervised learning approach. We describe an extension of semisupervised structured ...
Jun Suzuki, Hideki Isozaki, Xavier Carreras, Micha...
This paper presents a new dependence language modeling approach to information retrieval. The approach extends the basic language modeling approach based on unigram by relaxing th...
Jianfeng Gao, Jian-Yun Nie, Guangyuan Wu, Guihong ...
In this paper we propose a rule-based approach to extract dependency and grammatical relations from the Venice Italian Treebank (VIT) (Delmonte et al., 2007) with bracketed tree s...
The paper describes the treatment of some specific syntactic constructions in two treebanks of Latin according to a common set of annotation guidelines. Both projects work within ...
David Bamman, Marco Passarotti, Roberto Busa, Greg...