A Bottom-Up Approach to Sentence Ordering for Multi-Document Summarization

By Danushka Bollegala, Naoaki Okazaki, Mitsuru Ishizuka. 2006

118 citations recorded by the source corpus.

Ordering information is a difficult but important task for applications generating natural language texts such as multi-document summarization, question answering, and concept-to-text generation. In multi-document summarization, information is selected from a set of source documents. However, improper ordering of information in a summary can confuse the reader and deteriorate the readability of the summary. Therefore, it is vital to properly order the information in multi-document summarization. We present a bottom-up approach to arrange sentences extracted for multi-document summarization. To capture the association and order of two textual segments (e.g. sentences), we define four criteria: chronology, topical-closeness, precedence, and succession. These criteria are integrated into a criterion by a supervised learning approach. We repeatedly concatenate two textual segments into one segment based on the criterion, until we obtain the overall segment with all sentences arranged. We evaluate the sentence orderings produced by the proposed method and numerous baselines using subjective gradings as well as automatic evaluation measures. We introduce the average continuity, an automatic evaluation measure of sentence ordering in a summary, and investigate its appropriateness for this task.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Bin Bi
2. Wei Wang
3. Emiel Krahmer
4. Ming Yan
5. Albert Gatt
6. Nijat R. Isazade
7. Rasim M. Alguliyev
8. Luo Si

In Natural Language Processing

1. Emiel Krahmer
2. Albert Gatt
3. Nijat R. Isazade
4. Ming Yan
5. Zuyi Bao
6. Luo Si
7. Liwei Peng
8. Bin Bi

Citations in the corpus

• StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding (2019, background): “Most of previous researches of sentence ordering were integrated into the study of downstream task, such as multi-document summarization [19], we revisit this problem in our language modeling task as a new sentence prediction.”
• Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation (2017, background): “These approaches can be applied to text structuring, where the items to be ordered are typically preverbal messages; however, they can also be applied in (multidocument) summarisation, where the items to be ordered are sentences from the input documents which are judged to be summary-worthy enough t”
• Multiple documents summarization based on evolutionary optimization algorithm (2013, background): “Bollegala, Okazaki, and Ishizuka (2010) presented a bottom-up approach to arrange”
• Neural Sentence Ordering (2016, unknown): “Most of previous researches of sentence ordering were integrated into an external and downstream task, such as multi-document summarization (Barzilay and Elhadad, 2002; Lapata, 2003; Bollegala et al., 2010).”