A Language Model for Parsing Very Long Chinese Sentences

B y corpus analyses, about seventy-five percent of Chinese sentences are composed of more than two sentence segments separated by commas or semicolons. A segment may be a sentence, a noun phrase, a verb phrase, an adjective phrase, an adverbial phrase, or a prepositional phrase. An N P segment may serve as a subject of the next segment or an object of the previous segment. The empty category pro may also appear in the VI' segment. The maximal freedom of the uses of pros, the large number of segments, the various segment types, and the associativity problem make sentence parsing difficult. Few parsing systems deal with these problems. This paper regards a segment as a basic parsing unit. And it uses characteristic words, subcategories of verbs, topic chain and some heuristic rules to link the segments into meaningful units. The pro resolution and the segment linking are useful for practical applications.