Corpus ID: 15776942

Learning to Order Natural Language Texts

  title={Learning to Order Natural Language Texts},
  author={Jiwei Tan and Xiaojun Wan and J. Xiao},
Ordering texts is an important task for many NLP applications. Most previous works on summary sentence ordering rely on the contextual information (e.g. adjacent sentences) of each sentence in the source document. In this paper, we investigate a more challenging task of ordering a set of unordered sentences without any contextual information. We introduce a set of features to characterize the order and coherence of natural language texts, and use the learning to rank technique to determine the… Expand
Learning Sentence Ordering for Opinion Generation of Debate
A sentence ordering method to help compose persuasive opinions for debating by developing a two-step method that improves the accuracy of first sentence selection by about 19 percentage points and had a superior performance over all metrics. Expand
End-to-end Argument Generation System in Debating
We introduce an argument generation system in debating, one that is based on sentence retrieval. Users can specify a motion such as This house should ban gambling, and a stance on whether the systemExpand


A Machine Learning Approach to Sentence Ordering for Multidocument Summarization and Its Evaluation
An algorithm that learns orderings from a set of human ordered texts and outperforms the existing methods in all evaluation metrics is proposed. Expand
Probabilistic Text Structuring: Experiments with Sentence Ordering
An approach to information ordering that is particularly suited for text-to-text generation and the appropriateness of such a model for multidocument summarization is assessed. Expand
An Adjacency Model for Sentence Ordering in Multi-document Summarization
A new method named adjacency based ordering to order sentences for summarization tasks, which distinctly outperforms other existing sentence ordering methods and its low input requirement makes it capable to most summarization and text generation tasks. Expand
A bottom-up approach to sentence ordering for multi-document summarization
The average continuity, an automatic evaluation measure of sentence ordering in a summary, is introduced and its appropriateness for this task is investigated. Expand
Measuring Variability in Sentence Ordering for News Summarization
It is concluded that evaluation of sentence ordering should use multiple reference orderings and whether a large enough test set would obviate the need for such independent means of quality assessment. Expand
Inferring Strategies for Sentence Ordering in Multidocument News Summarization
A strategy for ordering information that combines constraints from chronological order of events and topical relatedness is implemented and Evaluation of the augmented algorithm shows a significant improvement of the ordering over two baseline strategies. Expand
A Machine Learning Approach To Sentence Ordering For Multi-Document Summarization and its Evaluation
With the increasing popularity of the Internet,millions of texts available in electronic format. Availability of information is no longer a problem. Efficient searching techniques and search enginesExpand
A Hybrid Sentence Ordering Strategy in Multi-document Summarization
This paper uses 4 types of relationships between sentences to build a graph model where the vertices are sentences and edges are weighed relationships of the 4 types, and applies a variation of page rank to get the ordering of sentences for multi-document summaries. Expand
Improving Chronological Sentence Ordering by Precedence Relation
An approach to coherent sentence ordering for summarizing newspaper articles by combining the refinement algorithm with topical segmentation and chronological ordering and results reveal that the proposed method improves chronological sentence ordering. Expand
Domain-Independent Shallow Sentence Ordering
A shallow approach to the sentence ordering problem is presented, based on discourse entities, shallow syntactic analysis, and temporal precedence relations retrieved from VerbOcean, which shows that these relatively simple features perform well in a machine learning algorithm on datasets containing sequences of events. Expand