This paper proposes a corpus-based language model for topic identification. We analyze the association of noun-noun and noun-verb pairs in LOB Corpus. The word association norms are based on three factors: 1) word importance, 2) pair co-occurrence, and 3) distance. They are trained on the paragraph and sentence levels for noun-noun and nounverb pairs, respectively. Under the topic coherence pos...

This paper describes a supervised algorithm for word sense disambigua-tion based on hierarchies of decision lists. This algorithm supports a useful degree of conditional branching while minimizing the training data fragmentation typical of decision trees. Classiications are based on a rich set of collocational, morphological and syntactic contextual features, extracted automatically from traini...

This paper presents a contrastive analysis of adpositions in English, Nepali and Russian corpora. Two sets of highly frequent adpositions, those with broadly locative and broadly ablative meaning, are contrasted. The ‘quantitative-distributional’ analysis is based on identifying patterns across the most statistically significant collocations of the words in question; it is undertaken using 1 mi...

Automatically-derived grammars, such as the split-and-merge model, have proven helpful in parsing (Petrov et al., 2006). As such grammars are refined, latent information is recovered which may be usable for linguistic tasks besides parsing. In this paper, we present and examine a new method of semantic relation classification: using automaticallyderived grammar rule clusters as a robust knowled...

This paper analyses the efficiency of the EWC semantic relatedness measure in an ad-hoc retrieval task. This measure combines the Wikipedia-based Explicit Semantic Analysis (ESA) measure, the WordNet path measure and the mixed collocation index. EWC considers encyclopaedic, ontological, and collocational knowledge about terms. This advantage of EWC is a key factor to find precise terms for auto...

We investigate the identification and, to some extent, the classification of collocational word groups that consist of an adjectival modifier (A), an accusative object noun (N), and a verb (V) by means of parsing a newspaper corpus with a lexicalized probabilistic grammar.1 Data triples are extracted from the resulting Viterbi parses and subsequently evaluated by means of a statistical associat...

The current research investigates the use of collocations in students’ academic writings to obtain information about popular types they use, collocational errors, and sources errors. design study is a qualitative which employed document analysis as instrument collect data. 50 students were population samples well. results show that have tendency using Type 1 (Verb-Noun) 2 (Adjective-Noun) more ...

In this paper, we report about some preliminary experiments in which we tried to improve the performance of a state-of-the-art Predictive Typing system for the German language by adding a collocation-based prediction component. This component tries to exploit the fact that texts have a topic and are semantically coherent. Thus, the appearance in a text of a certain word can be a cue that other,...

dimension seep : drip Emphasis enemy : foe Denotational, indirect error : mistake Denotational, fuzzy woods : forest Stylistic, formality pissed : drunk : inebriated Stylistic, force ruin : annihilate Expressed attitude skinny : thin : slim, slender Emotive daddy : dad : father Collocational task : job Selectional pass away : die Subcategorization give : donate 2.3 Dimensions of variation The p...