In this paper, we propose a linear model-based general framework to combine k-best parse outputs from multiple parsers. The proposed framework leverages on the strengths of previo...
In this paper, we propose two different language modeling approaches, namely skip trigram and across sentence boundary, to capture the long range dependencies. The skip trigram mo...
Saeedeh Momtazi, Friedrich Faubel, Dietrich Klakow
Traditional Active Learning (AL) techniques assume that the annotation of each datum costs the same. This is not the case when annotating sequences; some sequences will take longe...
Robbie Haertel, Eric K. Ringger, Kevin D. Seppi, J...
Subcategorization is a kind of knowledge which can be considered as crucial in several NLP tasks, such as Information Extraction or parsing, but the collection of very large resou...
This paper proposes a novel method to refine the grammars in parsing by utilizing semantic knowledge from HowNet. Based on the hierarchical state-split approach, which can refine ...
Xiaojun Lin, Yang Fan, Meng Zhang, Xihong Wu, Huis...