Towards Multi-paper Summarization Using Reference Information

Nanba, Hidetsugu; Okumura, Manabu

doi:10.5715/jnlp.6.5_43

Cited by 67 publications

(56 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The area of that curve is the probability that a randomly drawn positive example has a higher decision function value than a random negative example. We define a baseline method based on the method proposed by Nanba and Okumura (Nanba and Okumura 1999). Specifically, we used the words appearing in the citation context as the features and defined the feature values by the number of occurrences.…”

Section: Evaluation Measures and Baseline Methodsmentioning

confidence: 99%

Topic level expertise search over heterogeneous networks

et al. 2010

View full text Add to dashboard Cite

In this paper, we present a topic level expertise search framework for heterogeneous networks. Different from the traditional Web search engines that perform retrieval and ranking at document level (or at object level), we investigate the problem of expertise search at topic level over heterogeneous networks. In particular, we study this problem in an academic search and mining system, which extracts and integrates the academic data from the distributed Web. We present a unified topic model to simultaneously model topical aspects of different objects in the academic network. Based on the learned topic models, we investigate the expertise search problem from three dimensions: ranking, citation tracing analysis, and topical graph search. Specifically, we propose a topic level random walk method for ranking the different objects. In citation tracing analysis, we aim to uncover how a piece of Learn (2011) 82: 211-237 work influences its follow-up work. Finally, we have developed a topical graph search function, based on the topic modeling and citation tracing analysis. Experimental results show that various expertise search and mining tasks can indeed benefit from the proposed topic level analysis approach.

show abstract

Section: Evaluation Measures and Baseline Methodsmentioning

confidence: 99%

Topic level expertise search over heterogeneous networks

et al. 2010

View full text Add to dashboard Cite

show abstract

“…References [44], [45] present a similar task of finding "related sentences" to a citation anchor; they use a set of 90 cue-phrases extracted from a set of 100 citation blocks with a simple-matching * 18 Even this one is likely coincidental, as it ("meanwhile") had only a single positive example and no negative examples in the data.…”

Section: Related Workmentioning

confidence: 99%

“…They are interested in building summaries, such as with Ref. [45], and is shown by their use of the F 3 score for evaluation, so finding related content for maximising recall seems to be a priority. Our work has the advantage that it is generalised, i.e., a single trained model is used for evaluation of all citing/cited work pairs.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Citation Block Determination Using Textual Coherence

Kaplan

Tokunaga

Teufel

2016

Journal of Information Processing

View full text Add to dashboard Cite

Detecting the boundaries of citations in the running text of research papers is an important task for research paper summarisation, idea attribution, sentiment analysis, and other citation-based analysis research. Recently, detecting non-explicit citing sentences has garnered some attention, but can still be seen as in its infancy. We define this task as citation block determination (CBD). In this paper we propose and investigate the effects of various types of textual coherence on CBD, positing that it is a crucial aspect of identifying citation blocks, as it is fundamental to the composition of citations themselves. We demonstrate promising results, with our method outperforming previous state-of-the-art on F 1 by a large margin, with an improvement in both precision and recall, and further provide an in-depth error analysis and discussion of why this is the case.

show abstract

“…Three types of extractive summaries based on citation link analysis have been proposed: overview of a research area (multi-document scientific paper summary) [145], impact summary (single document summary of a paper using sentences from the paper itself) [134] and citation summary (a mix of multi-and single document summarization, in which a single paper is summarized but the input to the summarizer are the sentences from other papers in which that paper is cited) [169].…”

Section: Exploiting Citation Links Between Papersmentioning

confidence: 99%