We explore the use of Power Iteration Clustering for large-scale clustering of nouns and verbs, using subject-verb-object triple relations. We have implemented a parallelized version of PIC, which can efficiently handle clustering of hundreds of thousands of sparse “documents.” We tested our implementation on clustering of over 1 million noun phrases, and over 650K verb phrases. We also evaluat...

It has been claimed that verb processing (as opposed to noun processing) is subserved by specific neural circuits in the left prefrontal cortex. In this study, we took advantage of the unusual grammatical characteristics of clitic pronouns in Italian (e.g., lo and la in portalo and portala 'bring it [masculine]/[feminine]', respectively)-the fact that clitics have both nominal and verbal charac...

We present in this paper recent progress in Sanskrit computational linguistics. We propose a solution to the tagging of verb phrases which correctly handles the non-associativity of external sandhi arising from the treatment of preverb ā. This involves a notion of phantom phoneme. We give exemples of execution of a computer tagger designed accordingly, which handles verb phrases as well as noun...

Chinese verb phrases classification is to determine boundaries of verb phrases and divide them exactly, using brackets, by automatically analyzing and processing by computer after the sentences have been decollated and marked the characteristic or property of a certain word. SVM classification model is a common and powerful for classification tasks. In this paper, the SVM classification model i...

This study examines French-learning infants' sensitivity to grammatical non-adjacent dependencies involving subject-verb agreement (e.g., le/les garçons lit/lisent 'the boy(s) read(s)') where number is audible on both the determiner of the subject DP and the agreeing verb, and the dependency is spanning across two syntactic phrases. A further particularity of this subsystem of French subject-ve...

Collections of relational paraphrases have been automatically constructed from large text corpora, as a WordNet counterpart for the realm of binary predicates and their surface forms. However, these resources fall short in their coverage of hypernymy links (subsumptions) among the synsets of phrases. This paper closes this gap by computing a high-quality alignment between the relational phrases...

This paper examines three subtypes of the verb copying construction in Chinese. We begin by looking at Cheng’s (2007) analysis of the resultative verb copying construction, according to which both standard movement and sideward movement are required to account for the verb copying construction (VCC). Cheng suggests that the same analysis can be applied to verb copying with nonresultative phrase...

This paper proposes a statistical method of acquiring knowledge about the abbreviation possibility of some of multiple phrases modifying the same verb/noun. Our method calculates weight values of multiple phrases by mutual information based on the strength of relation between the phrases among the multiple phrases and modified verbs/nouns. Among phrases modifying the same verb/noun, those havin...

Annotated corpora are essential resources for natural language processing. This paper describes our approach for building a corpus annotated with predicateargument structure on research abstracts in molecular biology domain. Observation of the records in a database of cell signaling events and corresponding research abstracts showed that extracting predicateargument structure is a useful interm...