Resorting Relevance Evidences to Cumulative Citation Recommendation for Knowledge Base Acceleration

  • Jingang Wang
  • Lejian LiaoEmail author
  • Dandan Song
  • Lerong Ma
  • Chin-Yew Lin
  • Yong Rui
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9098)


Most knowledge bases (KBs) can hardly be kept up-to-date due to time-consuming manual maintenance. Cumulative Citation Recommendation (CCR) is a task to address this problem, whose objective is to filter relevant documents from a chronological stream corpus and then recommend them as candidate citations with certain relevance estimation to target entities in KBs. The challenge of CCR is how to accurately category the candidate documents into different relevance levels, since the boundaries between them are vague under the current definitions. To figure out the boundaries more precisely, we explore three types of relevance evidences including entities’ profiles, existing citations in KBs, and temporal signals, to supplement the definitions of relevance levels. Under the guidance of the refined definitions, we incorporate these evidences into classification and learning to rank approaches and evaluate their performance on TREC-KBA-2013 dataset. The experimental results show that all these approaches outperform the corresponding baselines. Our analysis also reveals various significances of these evidences in estimating relevance levels.


Cumulative citation recommendation Knowledge base acceleration Information filtering 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Balog, K., Ramampiaro, H.: Cumulative citation recommendation: classification vs. ranking. In: SIGIR 2013, pp. 941–944. ACM (2013)Google Scholar
  2. 2.
    Balog, K., Ramampiaro, H., Takhirov, N., Nørvåg, K.: Multi-step classification approaches to cumulative citation recommendation. In: OAIR 2013, pp. 121–128 (2013)Google Scholar
  3. 3.
    Berendsen, R., Meij, E., Odijk, D., Rijke, M.d., Weerkamp, W.: The university of amsterdam at trec 2012. In: TREC (2012)Google Scholar
  4. 4.
    Bonnefoy, L., Bouvier, V., Bellot, P.: A weakly-supervised detection of entity central documents in a stream. In: SIGIR 2013, pp. 769–772 (2013)Google Scholar
  5. 5.
    Bunescu, R., Pasca, M.: Using encyclopedic knowledge for named entity disambiguation. In: EACL 2006, pp. 9–16 (2006)Google Scholar
  6. 6.
    Cucerzan, S.: Large-scale named entity disambiguation based on Wikipedia data. In: EMNLP-CoNLL. pp. 708–716. Association for Computational Linguistics, Prague, June 2007Google Scholar
  7. 7.
    Dietz, L., Dalton, J., Balog, K.: Umass at trec 2013 knowledge base acceleration track. In: TREC (2013)Google Scholar
  8. 8.
    Frank, J.R., Kleiman-Weiner, M., Roberts, D.A., Niu, F., Zhang, C., Re, C., Soboroff, I.: Building an Entity-Centric Stream Filtering Test Collection for TREC 2012. In: TREC 2012 (2012)Google Scholar
  9. 9.
    Frank, J., Bauer, S.J., Kleiman-Weiner, M., Roberts, D.A., Triouraneni, N., Zhang, C., Rè, C.: Evaluating stream filtering for entity profile updates for trec 2013. In: TREC (2013)Google Scholar
  10. 10.
    Gross, O., Doucet, A., Toivonen, H.: Named entity filtering based on concept association graphs. CICLing (2013)Google Scholar
  11. 11.
    Han, X., Zhao, J.: Named entity disambiguation by leveraging wikipedia semantic knowledge. In: CIKM 2009, pp. 215–224 (2009)Google Scholar
  12. 12.
    Kjersten, B., McNamee, P.: The hltcoe approach to the trec 2012 kba track. In: TREC 2012 (2012)Google Scholar
  13. 13.
    Liu, X., Darko, J., Fang, H.: A related entity based approach for knowledge base acceleration. In: TREC (2013)Google Scholar
  14. 14.
    Mihalcea, R., Csomai, A.: Wikify!: linking documents to encyclopedic knowledge. In: CIKM, pp. 233–242. ACM (2007)Google Scholar
  15. 15.
    Robertson, S., Soboroff, I.: The trec 2002 filtering track report. In: TREC (2002)Google Scholar
  16. 16.
    Vlachos, M., Meek, C., Vagena, Z., Gunopulos, D.: Identifying similarities, periodicities and bursts for online search queries. In: SIGMOD, pp. 131–142. ACM (2004)Google Scholar
  17. 17.
    Wang, J., Song, D., Lin, C.Y., Liao, L.: Bit and msra at trec kba ccr track 2013. In: TREC (2013)Google Scholar
  18. 18.
    Zhou, M., Chang, K.C.C.: Entity-centric document filtering: boosting feature mapping through meta-features. In: CIKM, pp. 119–128. ACM (2013)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Jingang Wang
    • 1
  • Lejian Liao
    • 1
    Email author
  • Dandan Song
    • 1
  • Lerong Ma
    • 1
    • 2
  • Chin-Yew Lin
    • 3
  • Yong Rui
    • 3
  1. 1.School of Computer ScienceBeijing Institute of TechnologyBeijingChina
  2. 2.College of Mathematics and Computer ScienceYan’an UniversityShaanxiChina
  3. 3.Knowledge Mining GroupMicrosoft ResearchBeijingChina

Personalised recommendations