Ordering Sentences According to Topicality
نویسنده
چکیده
This paper addresses the problem of finding or producing the best ordering of the sentences in a text. I focus on using semantic properties of the words, as well as the high-level structure of each of the texts, to produce or choose the best ordering. In choosing an original sentence ordering from a group of sentential permutations of the same text, information about the topic of the text is helpful when added to information about coherence. A term distribution method of determining the semantic properties of words is successfully used to locate the most topical sentence in each text.
منابع مشابه
Using Context Inference to Improve Sentence Ordering for Multi-document Summarization
In this paper, we propose a novel context inference-based approach for sentences ordering in mult i-document summarization application. Our method first detects whether or not two summarizat ion sentences should be adjacent according to the similarity between one summarizat ion sentence and the context of the other one, and then it computes the reliability of the adjacent summarization sentence...
متن کاملA Novel Method of Sentence Ordering Based on Support Vector Machine
In this paper, we present a practical method of sentence ordering in extractive multi-document summarization tasks of Chinese language. By using Support Vector Machine (SVM), we classify the sentences of a summary into several groups in rough position according to the source documents. Then we adjust the sentence sequence of each group according to the estimation of directional relativity of ad...
متن کاملThematic roles, markedness alignment and processing complexity.
Two experiments used eye-tracking during reading to investigate the role of the consistency of the relative markedness alignment of noun phrases (NPs) in the processing of complex sentences in Korean. To do so, the animacy of the first NP was varied in both experiments to manipulate the relative markedness of NPs. In addition, case markings of the second NP (nominative vs. accusative) were mani...
متن کاملDo Heavy-NP Shift Phenomenon and Constituent Ordering in English Cause Sentence Processing Difficulty for EFL Learners?
Heavy-NP shift occurs when speakers prefer placing lengthy or “heavy” noun phrase direct objects in the clause-final position within a sentence rather than in the post-verbal position. Two experiments were conducted in this study, and their results suggested that having a long noun phrase affected the ordering of constituents (the noun phrase and prepositional phrase) by advanced Iranian EFL le...
متن کاملSelecting on-topic sentences from natural language corpora
We describe a system that examines input sentences with respect to arbitrary topics formulated as natural language expressions. It extracts predicate-argument structures from text intervals and links them into semantically organized proposition trees. By instantiating trees constructed for topic descriptions in trees representing input sentences or parts thereof, we are able to assess degree of...
متن کامل