In this paper, we determine the maximum number of distinct Lyndon factors that a word of length n can contain. We also derive formulas for the expected total number of Lyndon factors in a word of length n on an alphabet of size σ, as well as the expected number of distinct Lyndon factors in such a word. The minimum number of distinct Lyndon factors in a word of length n is 1 and the minimum tot...

This paper presents a corrective model for speech recognition of inflected languages. The model, based on a discriminative framework, incorporates word ngrams features as well as factored morphological features, providing error reduction over the model based solely on word n-gram features. Experiments on a large vocabulary task, namely the Czech portion of the MALACH corpus, demonstrate perform...

Most of existing work learn sentiment-specific word representation for improving Twitter sentiment classification, which encoded both n-gram and distant supervised tweet sentiment information in learning process. They assume all words within a tweet have the same sentiment polarity as the whole tweet, which ignores the word its own sentiment polarity. To address this problem, we propose to lear...

Recently, word representation has been increasingly focused on for its excellent properties in representing the word semantics. Previous works mainly suffer from the problem of polysemy phenomenon. To address this problem, most of previous models represent words as multiple distributed vectors. However, it cannot reflect the rich relations between words by representing words as points in the em...

We investigate the application of kernel methods to representing both structural and lexical knowledge for predicting polarity of opinions in consumer product review. We introduce anygram kernels which model lexical information in a significantly faster way than the traditional n-gram features, while capturing all possible orders of n-grams (n) in a sequence without the need to explicitly prese...

A technique for reducing a tagset used for n-gram part-of-speech disambiguation is introduced and evaluated in an experiment. The technique ensures that all information that is provided by the original tagset can be restored from the reduced one. This is crucial, since we are interested in the linguistically motivated tags for part-of-speech disambiguation. The reduced tagset needs fewer parame...

We propose a novel algorithm for English to Persian transliteration. Previous methods proposed for this language pair apply a word alignment tool for training. By contrast, we introduce an alignment algorithm particularly designed for transliteration. Our new model improves the English to Persian transliteration accuracy by 14% over an n-gram baseline. We also propose a novel back-transliterati...

This article describes a semantic system which is based on distributional models obtained from a chronologically structured language resource, namely Google Books Syntactic Ngrams. The models were created using dependency-based contexts and a strategy for reducing the vector space, which consists in selecting the more informative and relevant word contexts. The system allows linguists to analiz...

Any-gram kernels are a flexible and efficient way to employ bag-of-n-gram features when learning from textual data. They are also compatible with the use of word embeddings so that word similarities can be accounted for. While the original any-gram kernels are implemented on top of tree kernels, we propose a new approach which is independent of tree kernels and is more efficient. We also propos...

This paper describes a number of techniques for language verification based on acoustic processing and n-gram language modelling. A new technique is described which uses anti-models to model the general class of languages. These models are then used to normalise the acoustic score giving a 34% reduction in the error rate of the system. An approach to automatically generate discriminative subwor...