We present an extensive empirical evaluation of collocation extraction methods based on
lexical association measures and their combination. The experiments are performed on …

In the present paper we describe TectoMT, a multi-purpose open-source NLP framework. It
allows for fast and efficient development of NLP applications by exploiting a wide range of …

* Colorless green ideas sleep furiously (N. Chomsky)► must be adhered to in order to
produce correct, meaningful, fluent utterances► ranges from almost free word combinations …

In this paper we introduce a generic XML-based data format called PML (Prague Markup
Language), which was specifically designed for the needs of representing rich multi-layered …

Tato kniha je opravenou a doplněnou verzí mé disertační práce, která vznikla během
doktorského studia oboru i-3 matematická lingvistika na Matematicko-fyzikální fakultě …

Tato technická zpráva shrnuje výsledky práce na tématu pojmenovaných entit v Ústavu
formální a aplikované lingvistiky Matematicko-fyzikální fakulty Univerzity Karlovy v Praze v …

In this paper we deal with a new rule-based approach to the Natural Language Generation
problem. The presented system synthesizes Czech sentences from Czech tectogrammatical …

The thesis presents tools for analysis at analytical and tectogrammatical layers that the
Prague Dependency Treebank is based on. The tools for analytical annotation consist of two …

TectoMT je nynı experimentálnı systém, který je prekonán state-of-the-art MT systémy
otevrených zdrojových Mojzıšu. TectoMT, 20091 Machine translation (MT) is gaining more …

The annotation experience we have acquired while participating in the Prague treebanking
projects provides us with a strong evidence to conclude that the linguistic data annotation by …