In Pollard and Sag (1994) and Ginzburg and Sag (2000) phrases are either headed or non-headed, and if they are headed, there is a relation of selection between the daughters: either the head daughter selects its non-head sister(s), as in the phrases of type head-complements, or the non-head daughter selects its head sister, as in the phrases of type head-adjunct. In the non-headed phrases, by c...

It is a fundamental and important task to extract key phrases from documents. Generally, phrases in a document are not independent in delivering the content of the document. In order to capture and make better use of their relationships in key phrase extraction, we suggest exploring the Wikipedia knowledge to model a document as a semantic network, where both n-ary and binary relationships amon...

Coreference resolution involves nding antecedents for anaphoric discourse entities, such as deenite noun phrases. But many deenite noun phrases are not anaphoric because their meaning can be understood from general world knowledge (e.g., \the White House" or \the news media"). We have developed a corpus-based algorithm for automatically identifying deenite noun phrases that are non-anaphoric, w...

We describe an interface that uses the phrases occurring in a document collection as a basis for browsing the collection and accessing its contents. Phrases are automatically extracted from the document text to represent the subject matter of the collection. Clearly, the interface’s utility depends on how good these phrases are. We evaluate the system by comparing the phrases extracted from a l...

We propose a novel framework for topic labeling that assigns the most representative phrases for a given set of sentences covering the same topic. We build an entailment graph over phrases that are extracted from the sentences, and use the entailment relations to identify and select the most relevant phrases. We then aggregate those selected phrases by means of phrase generalization and merging...

A weakly-supervised method is applied to anonymized queries to extract lexical interpretations of compound noun phrases (e.g., “fortune 500 companies”). The interpretations explain the subsuming role (“listed in”) that modifiers (fortune 500) play relative to heads (companies) within the noun phrases. Experimental results over evaluation sets of noun phrases from multiple sources demonstrate th...

The problem of manual ly modifying the lexicon appears with any na tura l language processing program. Ideally, a program should be able to acquire new lexieal entries from context, the way people learn. We address the problem of acquiring entire phrases, specifically Jigurative phr~es, through augment ing a phr~al lezico~ Facilitating such a self-extending lexicon involves (a) disambiguation~s...

This paper presents a syntactic analysis of a fragment of Amharic noun phrases. Amharic noun phrases possess some peculiar characteristics especially relating to the syntax of the definite article. The definite article shows some morphological and distributional characteristics distinct from languages such as English and German, which makes it difficult to directly apply the methods proposed fo...

In machine translation and man-machine dialogue, it is important to clarify' referents of noun phrases. We present a method for determining the referents of noun phrases in Japanese sentences by using the referential properties, modifiers, and possessors 1 of noun phrases. Since the Japanese language has no articles, it is difficult to decide whether a noun phrase has an antecedent or not. We h...