We present three approaches to lexical chaining based on the LDA topic model and evaluate them intrinsically on a manually annotated set of German documents. After motivating the choice of statistical methods for lexical chaining with their adaptability to different languages and subject domains, we describe our new two-level chain annotation scheme, which rooted in the concept of cohesive harm...

School-age children acquire hundreds of new words each year, many of which are acquired incidentally, from uses in discourse contexts. Although children are adept word learners, lexical acquisition from oral language is not necessarily inevitable. Children have particular difficulties in the acquisition of terms that involve complex semantic representations, such as science terms (Braisby, Dock...

The lack of adequate bases of commonsense or even lexical knowledge is perhaps the main obstacle to the development of highperformance, robust tools for semantic interpretation. It is also generally accepted that, notwithstanding the increasing availability in recent years of substantial hand-coded lexical resources such as WordNet and EuroWordNet, addressing the commonsense knowledge bottlenec...

I)br practical research in natnral language processing, it is indisl)ensM)le to develop a large scale semantic dictionary for computers. It is cspeciany important to improve thc tcclmiqucs tbr compiling semantic dictionaries ti'orn natural language texts such as those in existing human dictionaries or in large corpora, llowever, there are at least two ditlicultics in analyzing existing texts: t...