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...

Many studies have examined the differences between speech that is produced spontaneously as opposed to read from a prepared script. Most of these studies have focused on prosodic measures taken from clauses, sentences, or connected discourse. Furthermore, studies have shown that listeners are able to identify the context of production when presented with sentence-length utterances. The current ...

The article deals with the characteristics of noun phrases functioning in pre-position. Pre-noun modifiers, or attributive modifiers, are among the high-capacity structures in the contemporary English language, as they enable to devoid of prepositions and to describe objects in a laconic way. The goal of this research was to analyze the way scholars interpret this linguistic structure today, as...

This paper offers a method for the noun phrase recognition of Hungarian natural language texts based on machine learning methods. The approach learns noun phrase tree patterns described by regular expressions from an annotated corpus. The tree patterns are completed with probability values using error statistics. The noun phrase recognition parser tries to find the best-fitting trees for a sent...

Such genericity is a feature of entire sentences (or at least of entire clauses), and is not attributable to any subpart of the sentence, such as to the subject noun phrase or to the verb phrase. It is instead somehow an interaction between the two. This sets it apart from another type of genericity, which is attributed to the noun phrase’s referring to an abstract genus (or kind) and not as ma...

An important challenge for the automatic analysis of English written text is the abundance of noun compounds: sequences of nouns acting as a single noun. In our view, their semantics is best characterized by the set of all possible paraphrasing verbs, with associated weights, e.g., malaria mosquito is carry (23), spread (16), cause (12), transmit (9), etc. Using Amazon’s Mechanical Turk, we col...

In one sense, the goals of QA and Novelty tasks are the same: extracting small document parts which are relevant to users’ queries. Additionally, the unit of extraction is almost always fixed in both tasks. For QA, an answer is a noun phrase in most cases, and for Novelty, a sentence is recognized as the basic information unit. This observation leads us to the following unified approach to both...

As children hear a novel verb in a NOUN-VERB-NOUN (i.e., NVN) structure, they generally infer that the verb is transitive, like the verb “hit” (Naigles, 1990; Yuan, Fisher, & Snedeker, 2012). However, the relationship between sentence structure and a verb’s transitivity status is not straightforward. Particularly, in typologically pro-drop languages, such as Mandarin Chinese, the object in a se...

This paper proposes a novel method that extracts semantic relations from social data in order to acquire ontologies that are used for mining social data. A set of nouns are iteratively extracted from documents in a bootstrapping manner, and then a semantic relation between a noun pair is identified by a clustering procedure. The main feature is exploitation of the co-occurrence of a verb and a ...