We present a probabilistic model that uses both prosodic and lexical cues for the automatic segmentation of speech into topic units. The approach combines hidden Markov models, statistical language models, and prosody-based decision trees. Lexical information is obtained from a speech recognizer, and prosodic features are extracted automatically from speech waveforms. We evaluate our approach o...

We propose OntoGain, a system for unsupervised ontology acquisition from unstructured text which relies on multi-word term extraction. For the acquisition of taxonomic relations, we exploit inherent multi-word terms’ lexical information in a comparative implementation of agglomerative hierarchical clustering and formal concept analysis methods. For the detection of non-taxonomic relations, we c...

AntConc is a freeware, multi-platform, multi-purpose corpus analysis toolkit, designed specifically for use in the classroom. It hosts a comprehensive set of tools including a powerful concordancer, word and keyword frequency generators, tools for cluster and lexical bundle analysis, and a word distribution plot. In this paper, I will describe each of these tools, and explain their value to lea...

The research was conducted in order to show the dominant models of thinking related word for ?cat? Serbian language community. conceptualization cat examined based on meaning lexical units: lexeme and its semantic structure; derivational network this lexeme; terminological expressions with phraseologisms component. It can be stated that analysis linguistic data successfully reveals results both...

This paper presents a tool for extracting multi-word expressions from corpora in Modern Greek, which is used together with a parallel concordancer to augment the lexicon of a rule-based machinetranslation system. The tool is part of a larger extraction system that relies, in turn, on a multilingual parser developed over the past decade in our laboratory. The paper reviews the various NLP module...

A large vocabulary isolated word recognition system based on the hypothesize-and-test paradigm is described. The system has been, however, devised as a word hypothesizer for a continuous speech understanding system able to answer to queries put to a geographical database. Word preselection is achieved by segmenting and classifying the input signal in terms of broad phonetic classes. Due to low ...

It is commonly said that adjectives are a kind of word that people use for emitting their opinion. This is because this lexical category designates the qualities of an entity. However, there are different ways to express an explicit opinion besides the use of adjectives. People also can choose verbs, nouns, adverbs and even groups of words that have complex meaning, like idioms or other multi-w...

We present novel methods for analysing the activation patterns of RNNs and identifying the types of linguistic structure they learn. As a case study, we use a multi-task gated recurrent network model consisting of two parallel pathways with shared word embeddings trained on predicting the representations of the visual scene corresponding to an input sentence, and predicting the next word in the...

Many systems for tasks such as question answering, multi-document summarization, and information retrieval need robust numerical measures of lexical relatedness. Standard thesaurus-based measures of word pair similarity are based on only a single path between those words in the thesaurus graph. By contrast, we propose a new model of lexical semantic relatedness that incorporates information fro...