Context and NLP

  • Victor Hung


Early Natural Language Processing (NLP) endeavors often employed contextual cues as supplemental assistive measures—secondary sources of data to help understand its users’ linguistic inputs. Context was used more as a tie-breaking tool rather than as a central component in conversational negotiation. Recent work in context-based reasoning has inspired a paradigm shift from these context-assisted techniques to context-centric NLP systems. This evolution of context’s role in NLP is necessary to support today’s sophisticated Human-Computer Interaction (HCI) applications, such as personal digital assistants, language tutors, and question answering systems. In these applications, there is a strong sense of utilitarian, purpose-driven conversation. Such an emphasis on goal-oriented behavior requires that the underlying NLP methods be capable of navigating through a conversation at the conceptual, or contextual level. This chapter explores the natural bond between NLP and context-based methods, as it manifests itself in the context-centric paradigm. Insights and examples are provided along the way to shed light on this evolved way of engineering natural language-based HCI.


Speech Recognition Natural Language Processing Automate Speech Recognition Contextual Awareness Automate Speech Recognition System 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. Angrosh, M.A., Cranefield, S., Stanger, N.: Context identification of sentences in related work sections using a conditional random field: towards intelligent digital libraries. Annual Joint Conference on Digital libraries, vol. 10, pp. 293–302 (2010)Google Scholar
  2. Anzalone, S.M., Yoshikawa, Y., Ishiguro, H., Menegatti, E., Pagello, E., Sorbello, R.: A topic recognition system for real world human-robot conversations. Intell. Auton. Syst. 194, 383–391 (2012)Google Scholar
  3. Baker, K.L., Franz, A.M., Jordan, P.W.: Coping with ambiguity in knowledge-based natural language analysis. FLAIRS-94 (1994)Google Scholar
  4. Breuing, A.: Improving human-agent conversations by accessing contextual knowledge from Wikipedia. WI-IAT Doctoral Workshop, in Conjunction with the 2010 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, vol. 3, pp. 428–431 (2010)Google Scholar
  5. Cambria, E., Olsher, D., Rajagopal, D.: SenticNet 3: A common and common-sense knowledge base for cognition-driven sentiment analysis. AAAI-14 (2014)Google Scholar
  6. Dethlefs, N.: Context-sensitive natural language generation: From knowledge-driven to data-driven techniques. Lang. Linguist. Compass 8(3), 99–115 (2014)CrossRefGoogle Scholar
  7. Dong, H., Hussain, F.K., Chang, E.: A context-aware semantic similarity model for ontology environments. Concurr. Comput.: Pract. Exp. 23(5), 505–524 (2011)CrossRefGoogle Scholar
  8. Eisman, E.M., López, V., Castro, J.L.: A framework for designing closed domain virtual assistants. Expert Syst. Appl. 39(3), 3135–3144 (2012)CrossRefGoogle Scholar
  9. Flycht-Eriksson, A., Jönsson, A.: Dialogue and domain knowledge management in dialogue systems. Proceedings of the 1st SIGdial Workshop on Discourse and Dialogue, vol. 10, pp. 121–130 (2000)Google Scholar
  10. Fügen, C., Holzapfel, H., Waibel, A.: Tight coupling of speech recognition and dialog management—dialog-context dependent grammar weighting for speech recognition. INTERSPEECH-2004, pp. 169–172 (2004)Google Scholar
  11. Gardent, C., Lorenzo, A., Nancy, L., Perez-Beltrachini, L., Rojas-Barahona, L.: Weakly and strongly constrained dialogues for language learning. SIGDIAL, pp. 357–359 (2013)Google Scholar
  12. Gonzalez, A.J., Myler, H.R., Towhidnejad, M., McKenzie, F.D., Kladke, R.R.: Automated knowledge generation from a CAD database. Knowledge Discovery in Databases, pp. 383–396. AAAI, Menlo (1991)Google Scholar
  13. Gonzalez, A., Stensrud, B., Barrett, G.: Formalizing context-based reasoning: A modeling paradigm for representing tactical human behavior. Int. J. Intell. Syst. 23(7), 822–847 (2008)CrossRefGoogle Scholar
  14. Griol, D., Molina, J.M., de Miguel, A.S.: Domain and subtask-adaptive conversational agents to provide an enhanced human agent interaction. Advances in practical applications of heterogeneous multi-agent systems. The PAAMS Collection Lecture Notes in Computer Science, vol. 8473, pp. 134–145. Springer International, Switzerland (2014)Google Scholar
  15. Hung, V., Gonzalez, A.: Context-centric speech-based human-computer interaction. Int. J. Intell. Syst. 28(10), 1010–1037 (2013)CrossRefGoogle Scholar
  16. Janarthanam, S., Lemon, O., Liu, X., Bartie, P., Mackaness, W., Dalmas, T., Goetze, J.: Conversational natural language interaction for place-related knowledge acquisition. Place-Related Knowledge Acquisition Research Workshop, Spatial Cognition Conference (2012)Google Scholar
  17. Kübler, S., Scheutz, M., Baucom, E., Israel, R.: Adding context information to part of speech tagging for dialogues. International Workshop on Treebanks and Linguistic Theories, vol. 9 (2010)Google Scholar
  18. Kunc, L., Mikovec, Z., Slavík, P.: Avatar and dialog turn-yielding phenomena. Int. J. Technol. Hum. Interact. 9(2), 66–88 (2013)CrossRefGoogle Scholar
  19. Latorre-Navarro, E.M., Harris, J.G.: A natural language conversational system for online academic advising. International Florida Artificial Intelligence Research Society Conference, vol. 27, pp. 186–189 (2014)Google Scholar
  20. Lee, S., Lee, C., Lee, J., Noh, H., Lee, G.G.: Intention-based corrective feedback generation using context-aware model. International Conference on Computer Supported Education, vol. 1, pp. 11–18 (2010)Google Scholar
  21. Lee, S., Noh, H., Lee, J., Lee, K., Lee, G.G.: Foreign language tutoring in oral conversations using spoken dialog systems. IEICE Trans. Inf. Syst. 95-D(5), 1216–1228 (2012)CrossRefGoogle Scholar
  22. Levin, L., Glickman, O., Qu, Y., Gates, D., Lavie, A., Rose, C.P., Van Ess-Dykema, C., Waibel, A.: Using context in machine translation of spoken language. Proceedings of Theoretical and Methodological Issues in Machine Translation (TMI-95) (1995)Google Scholar
  23. Lieberman, H., Faaborg, A., Daher, W., Espinosa, J.: How to wreck a nice beach you sing calm incense. International Conference on Intelligent User Interfaces (2005)Google Scholar
  24. Mahmoudi, M.T., Taghiyareh, F., Rajavi, K., Pirouzi, M.S.: A context-aware framework for semantic indexing of research papers. International Conference on Information, Process, and Knowledge Management, vol. 4 (2012)Google Scholar
  25. Mehra, P.: Context-aware computing: Beyond search and location-based services. IEEE Internet Comput. 16(2), 12–16 (2012)CrossRefGoogle Scholar
  26. Miller, G., Beckwith, R., Fellbaum, C., Gross, D., Miller, K.: Introduction to WordNet: An on-line lexical database. Int. J. Lexicogr. 3(4), 234–244 (1990)Google Scholar
  27. Mooney, R.J.: Learning language from perceptual context: A challenge problem for AI. Proceedings of the 2006 AAAI Fellows Symposium (2006)Google Scholar
  28. Nie, X., Feng, W., Wan, L., Xie, L.: Measuring semantic similarity by contextualword connections in Chinese news story segmentation. IEEE ICASSP, pp. 8312–8316 (2013)Google Scholar
  29. Porzel, R., Strube, M.: Towards context-dependent natural language processing in computational linguistics for the new millennium: Divergence or synergy. Proceedings of the International Symposium, pp. 21–22 (2002)Google Scholar
  30. Porzel, R., Zorn, H., Loos, B., Malaka, R.: Towards a separation of pragmatic knowledge and contextual information. ECAI-06 Workshop on Contexts and Ontologies (2006)Google Scholar
  31. Røssvoll, T.H.: The European MobileSage project—situated adaptive guidance for the mobile elderly: Overview, status, and preliminary results. International Conference on Advances in Computer-Human Interactions, vol. 6 (2013)Google Scholar
  32. Roth, D.: Learning to resolve natural language ambiguities: A unified approach. AAAI-98, vol. 15, pp. 806–813 (1998)Google Scholar
  33. Sakirulai, O., Osman, I.T., Peytchev, E.: Managing contextual information in semantically-driven temporal information systems. IEEE SUKSim, pp. 451–456 (2011)Google Scholar
  34. Sammut, C.: Managing context in a conversational agent. Electron. Trans. Artif. Intell. 5(B), 189–202 (2001)Google Scholar
  35. Serridge, B.: Context-dependent modeling in a segment-based speech recognition system. M. Eng. thesis, MIT Department of Electrical Engineering and Computer Science (1997, Aug)Google Scholar
  36. Shinozaki, T., Yamamoto, Y., Tsuruta, S.: Context-based counselor agent for software development ecosystem. Computing pp. 1–26, Springer, Vienna (2013)Google Scholar
  37. Skillen, K. L., Chen, L., Nugent, C. D., Donnelly, M. P., Burns, W., & Solheim, I.: Ontological user profile modeling for context-aware application personalization. In Ubiquitous Computing and Ambient Intelligence (pp. 261–268). Springer Berlin Heidelberg. (2012)Google Scholar
  38. Towhidnejad, M., Myler, H.R., Gonzalez, A.J.: Constraint mechanisms in automated knowledge generation. Appl. Artif. Intell. 7(2), 113–134 (1993)CrossRefGoogle Scholar
  39. Varges, S., Riccardi, G., Quarteroni, S., Ivanov, A.V.: POMDP concept policies and task structures for hybrid dialog management. IEEE ICASSP, pp. 5592–5595 (2011)Google Scholar
  40. Waltinger, U., Breuing, A., Wachsmuth, I.: Connecting question answering and conversational agents: Contextualizing German questions for interactive question answering systems. Künstl. Intell. 26(4), 381–390 (2012)CrossRefGoogle Scholar
  41. Weichselbraun, A., Gindl, S., Scharl, A.: Enriching semantic knowledge bases for opinion mining in big data applications. Knowledge-Based Systems. Elsevier, Amsterdam (2014)Google Scholar
  42. Wilks, Y.: The history of natural language processing and machine translation. Encyclopedia of Language and Linguistics, Kluwer, Amsterdam (2005)Google Scholar
  43. Yan, P., Zheng, F.: Context directed speech recognition in dialogue systems. International Symposium on Tonal Aspects of Languages with Emphasis on Tone Languages, pp. 225–228 (2004)Google Scholar
  44. Young S.: The MINDS system: Using context and dialog to enhance speech. Human Language Technology Conference Workshop on Speech and Natural Language, pp. 131–136 (1989)Google Scholar

Copyright information

© Springer Science+Business Media New York 2014

Authors and Affiliations

  1. 1.Intelligent Systems LaboratoryUniversity of Central FloridaOrlandoUSA

Personalised recommendations