We present a simple and effective way to perform out-of-domain statistical parsing by drastically reducing lexical data sparseness in a PCFG-LA architecture. We replace terminal symbols with unsupervised word clusters acquired from a large newspaper corpus augmented with biomedical targetdomain data. The resulting clusters are effective in bridging the lexical gap between source-domain and targ...

Query expansion consists in extending user queries with related terms in order to solve the lexical gap problem in Information Retrieval and Question Answering. The main difficulty lies in identifying relevant expansion terms in order to prevent query drift. We propose to use definition clusters built from a combination of English lexical resources for query expansion. We apply the technique of...

Joint morphological and syntactic analysis has been proposed as a way of improving parsing accuracy for richly inflected languages. Starting from a transition-based model for joint part-of-speech tagging and dependency parsing, we explore different ways of integrating morphological features into the model. We also investigate the use of rule-based morphological analyzers to provide hard or soft...

We are interested in understanding speech overlaps and their function in human conversations. Previous studies on speech overlaps have relied on supervised methods, small corpora and controlled conversations. The characterization of overlaps based on timing, semantic and discourse function requires an analysis over a very large feature space. In this study, the corpus of overlapped speech segme...

Query clustering helps users frame an optimum query to obtain relevant documents. The contentbased approach to query clustering has been criticized since queries are usually very short and consist of a wide variety of keywords, making this method ineffective in finding clusters. Clustering based on similar search results URLs has also performed inadequately due to the large number of distinct U...

O presente artigo teve como finalidade apresentar uma revisão bibliográfica sistemática sobre o empreendedorismo e inovação a partir dos trabalhos científicos publicados em periódicos brasileiros internacionais entre período de 2015 2019 sob perspectiva da análise lexical. Em termos metodológicos, realizou-se, primeiramente, catalogação estudos âmbitos nacional internacional para os anos propos...

formulaic sequence (fs) is a general term often used to refer to various types of recurrent clusters. one particular type of fss common in different registers is lexical bundles (lbs). this study investigated whether lbs are stored and processed as a whole in the mind of language users and whether their functional discourse type has any effect on their processing. to serve these objectives, thr...