We report on a series of experiments addressing the fact that German is less suited than English for word-based n-gram language models. Several systems were trained at different vocabulary sizes using various sets of lexical units. They were evaluated against a newly created corpus of German and Austrian broadcast news.

Abstract: Lexical bundles, as building blocks of coherent discourse, have been the subject of much research in the last two decades. While many of such studies have been mainly concerned with  exploring  variations  in  the  use  of  these  word  sequences  across  different  registers  and disciplines, very few have addressed the use of some particular groups of lexical bundles within some gen...

This Master's Thesis concerns research in the automatic analysis of the sub-lexical structure of English words. Sub-lexical structure includes linguistic categories such as syllabification, stress, phonemic representation, phonetics, and spelling. This information could be very useful in all sorts of speech applications, including duration modeling and speech recognition. ANGIE is a system that...

Numerous studies have been carried out to find the relation between neighborhood effect and retention of lexical items. This study was an attempt to find such a relationship among Iranian EFL learners. Participants, advanced second English learners, were chosen based on the Oxford Placement Test. Participants completed a lexical decision task that was designed and performed by a computer softwa...

This paper investigates conceptually and empirically the novel sense matching task, which requires to recognize whether the senses of two synonymous words match in context. We suggest direct approaches to the problem, which avoid the intermediate step of explicit word sense disambiguation, and demonstrate their appealing advantages and stimulating potential for future research.

Current breakthroughs in natural language processing have benefited dramatically from neural models, through which distributional semantics can leverage data representations to facilitate downstream applications. Since embeddings use context prediction on word co-occurrences yield dense vectors, they are inevitably prone capture more semantic association than similarity. To improve vector space...

We explore the relation between word sense subjectivity and cross-lingual lexical substitution, following the intuition that good substitutions will transfer a word’s (contextual) sentiment from the source language into the target language. Experiments on English-Chinese lexical substitution show that taking a word’s subjectivity into account can indeed improve performance. We also show that ju...

This paper analyzes the use of hybrid language models for automatic speech transcription. The goal is to later use such an approach as a support for helping communication with deaf people, and to run it on an embedded decoder on a portable device, which introduces constraints on the model size. The main linguistic units considered for this task are the words and the syllables. Various lexicon s...