Firstly we briefly review the three conceptual domains of Sweetser (1990/2002), “content domain”, “epistemic domain”, and “speech-act domain” (Sweetserian trichotomy), and Shen (2003), the corresponding A(cting), K(nowing), U(ttering) (Shenian trichotomy)—our KAU, finding that they and their followers ignored largely the necessity to distinguish between these three domains in terms of the speak...

Hypernym classification is the task of deciding whether, given two words, one word “is a kind of” the other. We present a classifier that learns the noun hypernym relation based on automatically-discovered lexico-syntactic patterns between a set of provided hyponym/hypernym noun pairs. This classifier is shown to outperform two previous methods for automatically identifying hypernym pairs (usin...

The human turn-taking system regulates the smooth and precise exchange of speaking turns during face-to-face interaction. Recent studies investigated the processing of ongoing turns during conversation by measuring the eye movements of noninvolved observers. The findings suggest that humans shift their gaze in anticipation to the next speaker before the start of the next turn. Moreover, there i...

In this paper we present the principles of lexico-semantic annotation of Składnica Treebank using Polish WordNet lexical units. We describe different means of annotation, depending on the structure of a sentence in Składnica on the one hand and the availability of adequate lexical unit in PLWN on the other. Apart from “standard” annotation involving lexical units with the same lemma as the toke...

This paper describes a novel approach to inducing lexico-structural transfer rules from parsed bi-texts using syntactic pattern matching, statistical cooccurrence and error-driven filtering. We present initial evaluation results and discuss future directions.