Generating comparative summaries from reviews

Sipoš, Ruben; Joachims, Thorsten

doi:10.1145/2505515.2507879

Cited by 21 publications

(11 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Comparative summarization has been studied for several years . One strategy of comparative summarization only considers the notable differences between the two documents rather than considering their commonality .…”

Section: Related Workmentioning

confidence: 99%

Automatic generation of related work through summarizing citations

Chen

Zhuge

2017

Concurrency and Computation

View full text Add to dashboard Cite

Summary Related work is a component of a scientific paper, which introduces other researchers' relevant works and makes comparisons with the current author's work. Automatically generating the related work section of a writing paper provides a tool for researchers to accomplish the related work section efficiently without missing related works. This paper proposes an approach to automatically generating a related work section by comparing the main text of the paper being written with the citations of other papers that cite the same references. Our approach first collects the papers that cite the reference papers of the paper being written and extracts the corresponding citation sentences to form a citation document. It then extracts keywords from the citation document and the paper being written and constructs a graph of the keywords. Once the keywords that discriminate the two documents are determined, the minimum Steiner tree that covers the discriminative keywords and the topic keywords is generated. The summary is generated by extracting the sentences covering the Steiner tree. According to ROUGE evaluations, the experiments show that the citations are suitable for related work generation and our approach outperforms the three baseline methods of MEAD, LexRank, and ReWoS. This work verifies the general summarization method based on connotation and extension through citation.

show abstract

Section: Related Workmentioning

confidence: 99%

Automatic generation of related work through summarizing citations

Chen

Zhuge

2017

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…Furthermore, it is difficult to apply statistical topic modeling in comparative document analysis as the data statistic between two documents is insufficient, in particular when the documents are about emergent topics (e.g., Academia, News). Finally, our work is also related to comparing reviews in opinion mining [26,23,14,12] and contrastive summarization for entities [15]-they also aim to find similarities and differences between two objects. However, these works are restricted to sentiment analysis.…”

Section: Related Workmentioning

confidence: 99%

Comparative Document Analysis for Large Text Corpora

Ren

Wang

2017

Proceedings of the Tenth ACM International Conference on Web Search and Data Mining

View full text Add to dashboard Cite

show abstract

“…Contrastive opinion mining extracts contrasting view points about a single entity or event instead of comparing multiple ones. A recent preliminary study extends this for comparing reviews of two products (Sipos and Joachims, 2013). It uses a supervised method for learning sentence alignments per product-type, and does not organize various opinions for an entity via clustering.…”

Section: Related Workmentioning

confidence: 99%

Entity-balanced Gaussian pLSA for Automated Comparison

Contractor

Singla

2016

Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

Community created content (e.g., product descriptions, reviews) typically discusses one entity at a time and it can be hard as well as time consuming for a user to compare two or more entities. In response, we define a novel task of automatically generating entity comparisons from text. Our output is a table that semantically clusters descriptive phrases about entities. Our clustering algorithm is a Gaussian extension of probabilistic latent semantic analysis (pLSA), in which each phrase is represented in word vector embedding space. In addition, our algorithm attempts to balance information about entities in each cluster to generate meaningful comparison tables, where possible. We test our system's effectiveness on two domains, travel articles and movie reviews, and find that entitybalanced clusters are strongly preferred by users.

show abstract

Generating comparative summaries from reviews

Cited by 21 publications

References 14 publications

Automatic generation of related work through summarizing citations

Automatic generation of related work through summarizing citations

Comparative Document Analysis for Large Text Corpora

Entity-balanced Gaussian pLSA for Automated Comparison

Contact Info

Product

Resources

About