We present in this paper a formal approach for the representation of multimodal information. This approach, thanks to the to use of typed feature structures and hypergraphs, gener...
This paper presents a methodology for a quantitative and qualitative evaluation of Textual Entailment systems. We take advantage of the decomposition of Text Hypothesis pairs into...
We compare the performance of three statistical parsing architectures on the problem of deriving typed dependency structures for French. The architectures are based on PCFGs with ...
Marie Candito, Joakim Nivre, Pascal Denis, Enrique...
There has been relatively little work focused on determining the formality level of individual lexical items. This study applies information from large mixedgenre corpora, demonst...
As one of the important tasks of SemEval Evaluation, Frame Semantic Structure Extraction based on the FrameNet has received much more attention in NLP field. This task is often di...
In this paper, we present a two-stage approach to acquire Japanese unknown morphemes from text with full POS tags assigned to them. We first acquire unknown morphemes only making ...
We present a library of implemented HPSG analyses for argument optionality based on typological studies of this phenomenon in the world's languages, developed in the context ...
We investigate a series of targeted modifications to a data-driven dependency parser of German and show that these can be highly effective even for a relatively well studied langu...
Hierarchical phrase-based models provide a powerful mechanism to capture non-local phrase reorderings for statistical machine translation (SMT). However, many phrase reorderings a...