This Open Access Dissertation is brought to you for free and open access by DigitalCommons@WayneState. It has been accepted for inclusion in Wayne State University Dissertations by an authorized administrator of DigitalCommons@WayneState. Approved by: _____________________________________ Advisor Date _____________________________________ _____________________________________ __________________...

We assess the reliability and accuracy of (neural) word embeddings for both modern and historical English and German. Our research provides deeper insights into the empirically justified choice of optimal training methods and parameters. The overall low reliability we observe, nevertheless, casts doubt on the suitability of word neighborhoods in embedding spaces as a basis for qualitative concl...

The p a p e r i s d e v o t e d t o l i n g u i s t i c problems of defining the basic formalized representation of text in an automatic translation system within the frsmlework of the so-called integral formal model of tile tr~ulslation process, the primary requirement for tills representation considered to be a compromise between its semal~ticity, superficiality~ a/id exhaustiveness. A repres...

We present a novel approach to solving definite descriptions in unrestricted text based on searching the web for a particular type of lexico-syntactic patterns. Using statistics on these patterns, we intend to recover the antecedents for a predefined subset of definite descriptions occurring in two types of anaphoric relations: identity anaphora and associative anaphora. Preliminary results obt...

Much of the writing styles recognized in rhetorical and composition theories involve deep syntactic elements. However, most previous research for computational stylometric analysis has relied on shallow lexico-syntactic patterns. Some very recent work has shown that PCFG models can detect distributional difference in syntactic styles, but without offering much insights into exactly what constit...

RÉSUMÉ Nous présentons PatternSim, une nouvelle mesure de similarité sémantique qui repose d’une part sur des patrons lexico-syntaxiques appliqués à de très vastes corpus et d’autre part sur une formule de réordonnancement des candidats extraits. Le système, initialement développé pour l’anglais, a été adapté au français. Nous rendons compte de cette adaptation, nous en proposons une évaluation...

This paper describes and evaluates a linguistically based NER system for Portuguese, based on lexico-semantical information, pattern matching and morphosyntactic, context driven Constraint Grammar rules. Preliminary Fscores for cross-domain news texts, when distinguishing six different name types, were 91.85 (raw) and 93.6 (subtyping of ready-chunked proper nouns).

This paper describes a method for learning the countability preferences of English nouns from raw text corpora. The method maps the corpus-attested lexico-syntactic properties of each noun onto a feature vector, and uses a suite of memory-based classifiers to predict membership in 4 countability classes. We were able to assign countability to English nouns with a precision of 94.6%.

The paper presents a software system that embodies a lexico-syntactic approach to the task of Textual Entailment. Although the approach is based on a minimal set of resources it is highly confident. The architecture of the system is open and can be easily expanded with more and deeper processing modules. Results on a standard data set are presented.