This paper presents the results of a study on information extraction from unrestricted Turkish text using statistical language processing methods. In languages like English, there is a very small number of possible word forms with a given root word. However, languages like Turkish have very productive agglutinative morphology. Thus, it is an issue to build statistical models for specific tasks ...

Speech runs continuously, without pauses between individual words. As yet there is little firm evidence that the speech signal contains usable information as to the location of word boundaries, therefore current psycholinguistic models of lexical access are based upon this assumption and rely solely on phonemic information (that is, they consider speech as an uninterrupted string of phones). In...

Lexical chains have been successfully used in several previous applications, e.g. topic segmentation and summarization. In this paper, we address the problem of how to directly evaluate the quality of lexical chains, in comparison to a human gold standard. This is in contrast to previous work, where the formal evaluation either relied on a word sense disambiguation task or concentrated on the f...

This paper describes an unsupervised dynamic graphical model for morphological segmentation and bilingual morpheme alignment for statistical machine translation. The model extends Hidden Semi-Markov chain models by using factored output nodes and special structures for its conditional probability distributions. It relies on morpho-syntactic and lexical source-side information (part-of-speech, m...

This paper presents a novel unsupervised method for hierarchical topic segmentation. Lexical cohesion – the workhorse of unsupervised linear segmentation – is treated as a multi-scale phenomenon, and formalized in a Bayesian setting. Each word token is modeled as a draw from a pyramid of latent topic models, where the structure of the pyramid is constrained to induce a hierarchical segmentation...

In this study we present a novel set of discrimination-based indicators of language processing derived from Naive Discriminative Learning (ndl) theory. We compare the effectiveness of these new measures with classical lexical-distributional measures-in particular, frequency counts and form similarity measures-to predict lexical decision latencies when a complete morphological segmentation of ma...

We propose a method for segmentation of ex-pository texts based on hierarchical agglomera-tive clustering. The method uses paragraphs as the basic segments for identifying hierarchical discourse structure in the text, applying lexical similarity between them as the proximity test. Linear segmentation can be induced from the identified structure through application of two simple rules. However t...

Four experiments examined effects of lexical stress on lexical access for recently learned words. Participants learned artificial lexicons (48 words) containing phonologically similar items and were tested on their knowledge in a 4-alternative forced-choice (4AFC) referent-selection task. Lexical stress differences did not reduce confusions between cohort items: KAdazu and kaDAzeI were confused...