This paper proposes a dictionary-based method of recognizing and paraphrasing Japanese periphrastic and overlapping verb phrases. Periphrastic VP is a phrase in which the verb or the noun functions as an adverb, voice or aspect. Overlapping VP is a phrase in which there is an overlapping meaning between the verb and the noun. The result of our experiment showed that the method can deal with tho...

We present an implicit tensor factorization method for learning the embeddings of transitive verb phrases. Unlike the implicit matrix factorization methods recently proposed for learning word embeddings, our method directly models the interaction between predicates and their two arguments, and learns verb phrase embeddings. By representing transitive verbs as matrices, our method captures multi...

Position changes in Chinese phrase are explained with light verb assumption in Generative Grammar. With regards to the idea that light verb is a hypothetical element, this study attempted to find the brain neural correlates in positions changes of Chinese phrases and whether this processing is launched by light verb or not. The results show that these phrases which can change the positions acti...

Verbs (in lemma form) and syntactic frames are automatically extracted from the ATB.! In order to acquire an argument structure for the verbs,!I only considered structure that is internal to the maximal Verb Phrase (VP) projection of the verb. However, within the VP, all sisters of the verb are excluded except for those in a close semantic relationship to the verb.! This is facilitated by the f...

In Mwotlap (north Vanuatu), most verb phrases consist of two or more verb roots chained together 〈V1-V2...〉, acting like a single verb. Although a clear case of verb serialization, such phrases reveal a strong asymmetry between their free verb head (V1), and what appears to be little more than a post-head modifier (V2). Because the resulting “macro-verb” can only refer to a single action, its i...

Parsing is a process of building structure onto a sentence or other string of characters so that the meaning of the sentence or string can be derived. Consider a simple English sentence: ”the boy hit the ball.” Thinking back to elementary school English class, the sentence can be broken into parts of speech as per Figure 1: an article followed by a noun, then a verb, then an article, then a nou...

In addressing a verb bias in syntactic analysis we present the beginnings of a noun-driven analysis paradigm. Such a paradigm may complement and compensate for some weaknesses in the existing verb-driven paradigm (in which the noun is subordinated) as applied to information sources or contexts in which the data is structured in objects and more than in events. The Current Paradigm In analysis o...

The phrase based systems for machine translation are limited by the phrases that they see during the training. For highly inflected languages, it is uncommon to see all the forms of a word in the parallel corpora used during training. This problem is amplified for verbs in highly inflected languages where the correct form of the word depends on factors like gender, number and tense aspect. We p...

The most important problems of dependency analysis are separated into three kinds of dependencies: noun to verb dependency, verb to verb dependency and noun to noun dependency. Recently, efficient methods have been developed for the first two problems. However, the third problem, namely noun phrase analysis, has not yet been solved. One of the most typical and important noun phrases in the Japa...