We present a probabilistic framework to automatically learn models of recurring signs from multiple sign language video sequences containing the vocabulary of interest. We extract the parts of the signs that are present in most occurrences of the sign in context and are robust to the variations produced by adjacent signs. Each sentence video is first transformed into a multidimensional time ser...

We describe the natural language processing component of a new serious gaming project, deLearyous, which aims at developing an environment in which users can improve their communication skills by interacting with a virtual character in (Dutch) written natural language. The virtual characters’ possible dialogue paths are defined by Leary’s Rose, a framework for interpersonal communication. In or...

This paper presents a CRF (Conditional Random Field) model for Semantic Chunk Annotation in a Chinese Question and Answering System (SCACQA). The model was derived from a corpus of real world questions, which are collected from some discussion groups on the Internet. The questions are supposed to be answered by other people, so some of the questions are very complex. Mutual information was adop...

Our goal is to extract answers from preretrieved sentences for Question Answering (QA). We construct a linear-chain Conditional Random Field based on pairs of questions and their possible answer sentences, learning the association between questions and answer types. This casts answer extraction as an answer sequence tagging problem for the first time, where knowledge of shared structure between...

This paper deals with the truth conditions of conditional sentences. It focuses on a particular class of problematic examples for semantic theories for these sentences. I will argue that the examples show the need to refer to dynamic, in particular causal laws in an approach to their truth conditions. More particularly, I will claim that we need a causal notion of consequence. The proposal subs...

Most theoretical as well as empirical work regarding the scalar implicature not all of the quantifier some has focused on the controversy of whether this implicature is generated by default or based on context. Independently of this question, it can be also asked whether this scalar implicature contributes to the truth-conditional content of sentences. We present results of an ERP study which t...

A highly pervasive phenomenon in natural languages is ellipsis. It is commonly believed that the presence of ellipsis is one of the main reasons why natural language is as ambiguous as it is. If lexical material is left unpronounced, a hearer must rely on other parts of the sentence, on contextual information and on intonation to recover the unpronounced material. Because there may be different...

Discriminative feature-based methods are widely used in natural language processing, but sentence parsing is still dominated by generative methods. While prior feature-based dynamic programming parsers have restricted training and evaluation to artificially short sentences, we present the first general, featurerich discriminative parser, based on a conditional random field model, which has been...

Word Ordering Errors (WOEs) are the most frequent type of grammatical errors at sentence level for non-native Chinese language learners. Learners taking Chinese as a foreign language often place character(s) in the wrong places in sentences, and that results in wrong word(s) or ungrammatical sentences. Besides, there are no clear word boundaries in Chinese sentences. That makes WOEs detection a...

Although figures in scientific articles have high information content and concisely communicate many key research findings, they are currently under utilized by literature search and retrieval systems. Many systems ignore figures, and those that do not typically only consider caption text. This study describes and evaluates a fully automated approach for associating figures in the body of a bio...