598 Hits in 2.1 sec

Experiments in Newswire Summarisation [chapter]

Stuart Mackie, Richard McCreadie, Craig Macdonald, Iadh Ounis
2016 Lecture Notes in Computer Science  
In this paper, we investigate extractive multi-document summarisation algorithms over newswire corpora.  ...  Following this verification of previous findings, we then reimplement various baseline and state-of-the-art summarisation algorithms, and make several observations from our experiments.  ...  Summarisation Datasets -In our summarisation experiments, we use newswire documents from the Document Understanding Conference (DUC) and the Text Analysis Conference (TAC).  ... 
doi:10.1007/978-3-319-30671-1_31 fatcat:uea7brhybvgm5eony2i4etmfiq

On choosing an effective automatic evaluation metric for microblog summarisation

Stuart Mackie, Richard McCreadie, Craig Macdonald, Iadh Ounis
2014 Proceedings of the 5th Information Interaction in Context Symposium on - IIiX '14  
Hence, in this paper, we aim to determine whether the traditional automatic newswire summarisation evaluation metrics generalise to the task of microblog summarisation.  ...  To help users obtain an overview of microblog content relating to topics and events that they are interested in, classical summarisation techniques from the newswire domain have been successfully applied  ...  Summarisation Algorithms In this section, we describe the algorithms for microblog summarisation used in our later experiments.  ... 
doi:10.1145/2637002.2637017 dblp:conf/iiix/MackieMMO14 fatcat:epg2iggerffahboo4ouyntzrzq

Automatic Labelling of Topic Models Learned from Twitter by Summarisation

Amparo Elizabeth Cano Basave, Yulan He, Ruifeng Xu
2014 Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)  
In this paper we propose to address the problem of automatic labelling of latent topics learned from Twitter as a summarisation problem.  ...  We compare the efficiency of existing state of the art summarisation algorithms.  ...  The generated labels with summarisation at x = 5 are presented in Table 2 , where GS represents the label generated from the Newswire headlines.  ... 
doi:10.3115/v1/p14-2101 dblp:conf/acl/BasaveHX14 fatcat:ldvhwv2x6varbjldtqpeksp5ea

News vertical search

Richard McCreadie, Craig Macdonald, Iadh Ounis
2013 Proceedings of the 36th international ACM SIGIR conference on Research and development in information retrieval - SIGIR '13  
In this paper, we investigate to what extent real-time content from newswire, blogs, Twitter and Wikipedia sources are useful to return to the user in the current fast-paced news search setting.  ...  Our results show that users exhibited a preference for rankings integrating newswire articles for only half of our queries, indicating that relying solely on newswire providers for news-related content  ...  Indeed, current events are now summarised and discussed in real-time [7, 27] using a variety of diverse media [21] , driven by user interaction and usergenerated content, e.g. news reporting in Twitter  ... 
doi:10.1145/2484028.2484080 dblp:conf/sigir/McCreadieMO13 fatcat:vnygrtoaovhkle24vu4iziwe4q

DIT: Summarisation and Semantic Expansion in Evaluating Semantic Similarity

Magdalena Kacmajor, John D. Kelleher
2014 Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014)  
In our experiments, text summarisation using a graph-based algorithm did not prove to be helpful.  ...  We investigated the potential benefits of (1) using text summarisation to narrow down the comparison to the most important concepts in both texts, and (2) leveraging WordNet information to increase usefulness  ...  The best performance has been observed in Newswire category.  ... 
doi:10.3115/v1/s14-2037 dblp:conf/semeval/KacmajorK14 fatcat:kfpow7hb5vg3hgezbxd7amlog4

COMPENDIUM: a text summarisation tool for generating summaries of multiple purposes, domains, and genres

2012 Natural Language Engineering  
In this paper, we present a Text Summarisation tool, compendium, capable of generating the most common types of summaries.  ...  The proposed architecture for compendium is divided in various stages, making a distinction between core and additional stages.  ...  Section 4.1 contains the description of the different corpora used, whereas Section 4.2 shows the experiments and the results obtained in a wide range of domains and types of texts, comprising newswire  ... 
doi:10.1017/s1351324912000198 fatcat:5nwndomjvzfe3kirymhwdwb2xy

Comparing Algorithms for Microblog Summarisation [chapter]

Stuart Mackie, Richard McCreadie, Craig Macdonald, Iadh Ounis
2014 Lecture Notes in Computer Science  
Current systems either directly apply, or build upon, classical summarisation approaches previously shown to be effective within the newswire domain.  ...  Hence, in this paper, we compare the performance of eleven summarisation approaches using four microblog summarisation datasets, with the aim of determining which are the most effective and therefore should  ...  We use this categorisation in our later experiments to characterise which types of algorithm are the most effective for microblog summarisation.  ... 
doi:10.1007/978-3-319-11382-1_15 fatcat:7dqlcuivnrbe7cb7zag2e7sxhu

Using query term order for result summarisation

Shao Fen Liang, Siobhan Devlin, John Tait
2005 Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '05  
We report on two experiments performed to test the importance of Term Order in automatic summarisation.  ...  Experiment one was undertaken as part of DUC 2004 to which three systems were submitted, each with a different summarisation approach.  ...  To prove our hypothesis we have done two experiments testing the importance of Term Order in documents summarisation and Query Term Order in search result summarisation.  ... 
doi:10.1145/1076034.1076162 dblp:conf/sigir/LiangDT05 fatcat:c5cs4uwm3bb6de3qrhezdwwyje

Generalisation in Named Entity Recognition: A Quantitative Analysis [article]

Isabelle Augenstein, Leon Derczynski, Kalina Bontcheva
2017 arXiv   pre-print
Unseen NEs, in particular, play an important role, which have a higher incidence in diverse genres such as social media than in more regular genres such as newswire.  ...  In particular, our findings indicate that NER approaches struggle to generalise in diverse genres with limited training data.  ...  This indicates that drift is lower in newswire than in tweets.  ... 
arXiv:1701.02877v2 fatcat:eandj36upfecrdtlurvfi2fw6m

A Testbed for Indonesian Text Retrieval

Jelita Asian, Hugh E. Williams, Seyed M. M. Tahaghoghi
2004 Australasian Document Computing Symposium  
However, despite media and intelligence interest in Indonesia, little work has been done on evaluating Information Retrieval techniques for Indonesian, and no standard testbed exists for such a purpose  ...  The Kompas newswire is different in topicality and timespan to the newswire collections used at TREC. Therefore, we defined our own topics following the TREC approach.  ...  We have defined 20 ad hoc queries for which known answers exist in a collection of 3,000 newswire documents.  ... 
dblp:conf/adcs/AsianWT04 fatcat:uggozoek2na6hpt5pgxb5x5t7i

Generalisation in named entity recognition: A quantitative analysis

Isabelle Augenstein, Leon Derczynski, Kalina Bontcheva
2017 Computer Speech and Language  
Unseen NEs, in particular, play an important role, which have a higher incidence in diverse genres such as social media than in more regular genres such as newswire.  ...  In particular, our findings indicate that NER approaches struggle to generalise in diverse genres with limited training data.  ...  T a g g e d P The seed domain for the experiments here is newswire, where we use the classifier trained on the biggest NW corpus investigated in this study, i.e. OntoNotes NW.  ... 
doi:10.1016/j.csl.2017.01.012 fatcat:xj3c5ng6bvfzfn5rtkwwycodoy

News vertical search using user-generated content

Richard McCreadie
2012 SIGIR Forum  
. • In Section 6.8, we summarise the findings of this chapter.  ...  In terms of the two experiments, 23 individual workers assessed the first experiment, while 57 workers assessed the second experiment. Both experiments were completed individually in under 36 hours.  ...  In this appendix, we provide a detailed description of all of the features that we use in our news query classification experiments in Chapter 7.  ... 
doi:10.1145/2492189.2492202 fatcat:wuha3gotmnffnbqhrdltooys5m

Coreference Resolution: To What Extent Does It Help NLP Applications? [chapter]

Ruslan Mitkov, Richard Evans, Constantin Orăsan, Iustin Dornescu, Miguel Rios
2012 Lecture Notes in Computer Science  
The study discusses experiments in which the aforementioned applications were implemented in two versions, one in which the BART coreference resolution system was integrated and one in which it was not  ...  coreference resolution, could improve the performance of three NLP applications: text summarisation, recognising textual entailment and text classification.  ...  Experiments on newswire texts show similar results [1] and lead to the conclusion that it may be possible to improve the results of the automatic summariser by using a coreference resolver instead of  ... 
doi:10.1007/978-3-642-32790-2_2 fatcat:7hcmnbcbdfcaplmsrwidlbsmpy

Analysis of named entity recognition and linking for tweets

Leon Derczynski, Diana Maynard, Giuseppe Rizzo, Marieke van Erp, Genevieve Gorrell, Raphaël Troncy, Johann Petrak, Kalina Bontcheva
2015 Information Processing & Management  
Information extraction from tweets is typically performed in a pipeline, comprising consecutive stages of language identification, tokenisation, part-of-speech tagging, named entity recognition and entity  ...  In this work, we describe a new Twitter entity disambiguation dataset, and conduct an empirical analysis of named entity recognition and disambiguation, investigating how robust a number of state-of-the-art  ...  Acknowledgments The authors thank Roland Roller and Sean McCorry of the University of Sheffield, and the CrowdFlower workers, for their help in annotating the entity-linked dataset; and the reviewers for  ... 
doi:10.1016/j.ipm.2014.10.006 fatcat:3ikmvocd75h7rljgxjszeku4gu

Techniques for Efficient Query Expansion [chapter]

Bodo Billerbeck, Justin Zobel
2004 Lecture Notes in Computer Science  
Query expansion is a well-known method for improving average effectiveness in information retrieval.  ...  We explore alternative methods for reducing queryevaluation costs, and propose a new method based on keeping a brief summary of each document in memory.  ...  A wide range of document summarisation techniques have been investigated (Goldstein et al., 1999) , and in particular Lam-Adesina and Jones (2001) have used summarisation for QE.  ... 
doi:10.1007/978-3-540-30213-1_4 fatcat:ubhkcjr2s5ajvl5rc6sksdzr34
« Previous Showing results 1 — 15 out of 598 results