Towards Evaluating the Impact of Anaphora Resolution on Text Summarisation from a Human Perspective
Automatic Text Summarisation (TS) is the process of abstracting key content from information sources. Previous research attempted to combine diverse NLP techniques to improve the quality of the produced summaries. The study reported in this paper seeks to
- PDF / 230,556 Bytes
- 13 Pages / 439.37 x 666.142 pts Page_size
- 96 Downloads / 208 Views
ADAPT Centre, Knowledge and Data Engineering Group, School of Computer Science and Statistics, Trinity College Dublin, Dublin, Ireland {bayomim,killian.levacher,peter.lavin, seamus.lawless}@scss.tcd.ie ADAPT Centre, School of Computing, Dublin City University, Dublin, Ireland [email protected] 3 IBM Analytics, IBM Technology Campus, Dublin, Ireland [email protected]
Abstract. Automatic Text Summarisation (TS) is the process of abstracting key content from information sources. Previous research attempted to combine diverse NLP techniques to improve the quality of the produced summaries. The study reported in this paper seeks to establish whether Anaphora Resolution (AR) can improve the quality of generated summaries, and to assess whether AR has the same impact on text from different subject domains. Summarisation evaluation is critical to the development of automatic summarisation systems. Previous studies have evaluated their summaries using automatic techniques. However, automatic techniques lack the ability to evaluate certain factors which are better quantified by human beings. In this paper the summaries are evaluated via human judgment, where the following factors are taken into consideration: informativeness, readability and understandability, conciseness, and the overall quality of the summary. Overall, the results of this study depict a pattern of slight but not significant increases in the quality of summaries produced using AR. At a subject domain level, however, the results demonstrate that the contribution of AR towards TS is domain dependent and for some domains it has a statistically significant impact on TS. Keywords: Text summarisation
Anaphora resolution TextRank
1 Introduction Natural Language Processing (NLP) has different tasks [1, 2]. One of these tasks is Automatic Text Summarisation (TS) that has been the subject of a lot of interest in the NLP community in recent years [2]. The goal of automatic summarisation is to process M.R. Ghorab—Postdoctoral Researcher at Trinity College Dublin at the time of conducting this research. © Springer International Publishing Switzerland 2016 E. Métais et al. (Eds.): NLDB 2016, LNCS 9612, pp. 187–199, 2016. DOI: 10.1007/978-3-319-41754-7_16
188
M. Bayomi et al.
the source text to produce a shorter version of the information contained in it then present this version in a way that suits the needs of a particular user or application. Text summaries attempt to provide concise overviews of content, and can allow a reader to make a quick and informed decision regarding whether a document contains the information they seek, and thus whether it would be worth the time and effort required to read the entire document. The rapid growth of the Web has resulted in a massive increase in the amount of information available online, which in turn has increased the importance of text summarisation. Various techniques have been proposed in the literature for the automatic summarisation of text, some of which are supervised, while others are unsupervised. S
Data Loading...
