Abstract
This chapter is divided into three parts. The first suggests some improvements to Bichitra as it stands, like direct access to particular images, synchronization of image and transcript, and provision of more links. The second suggests value additions in the form of new functions like topic modelling and more extensive multimedia components. It also points out the innovation involved in working these functions in non-Latin fonts. The last and longest section, ‘New Directions’, comprises the project director’s suggestions and speculations about using the Bichitra corpus for further development of textual computing generally. In particular, he argues for the special promise held out by large textual corpora in developing more precise ways of analyzing ‘big data’, paying more attention to their detailed contents. To achieve this, he suggests a series of progressively refined investigations of textual data in the light of its context: semantic and syntactical, literal and metaphoric.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Programs like ‘Knowledge Vault’ (Dong et al. 2014) parse big data semantically and/or syntactically to extract knowledge, but they chiefly extract the data automatically by measuring multiple occurrence. Google’s Knowledge Graph goes far in this direction. But all such programs extract knowledge out of the text, rather than probe more deeply into the verbal dimension per se. Their thrust is informational, not textual. Yet such in-depth textual analysis would be invaluable in creating a new generation of knowledge-extraction programs.
- 2.
In fact, infrequent items may be excluded on the grounds of small sample size (Mimno 2012, 5).
- 3.
See Mimno 2012 for an illustration of some basic possibilities in practice, especially the ‘broad areas’ indicated on page 17.
- 4.
- 5.
- 6.
Even the elaborate ontology of the ambitious ‘Read the Web’, designed to comb the resources of the entire Web, currently comprises factual or firmly denotative categories alone (Read the Web, http://rtw.ml.cmu.edu/rtw/kbbrowser/)—almost necessarily in view of the vast corpus involved.
- 7.
References
Das, Dipanjan et al., 2014. Frame-Semantic Parsing. Computational Linguistics 40:1, 10–56. http://www.mitpressjournals.org/doi/pdf/10.1162/COLI_a_00163. Accessed 12 January 2015.
Docuscope. http://www.cmu.edu/hss/english/research/docuscope.html. Accessed 24 December 2014.
Dong, Xin Luna et al. 2014. Knowledge Vault: A Web-Scale Approach to Probabilistic Knowledge Fusion. Proceedings on the Conference for Knowledge Discovery and Data-Mining. https://www.cs.cmu.edu/~nlao/publication/2014.kdd.pdf. Accessed 12 January 2015.
Hayles, N. Katherine. 2002. Writing Machines. Cambridge, Mass: MIT.
Hope, Jonathan and Michael Witmore. 2004. The Very Large Textual Object: A Prosthetic Reading of Shakespeare. Early Modern Literary Studies 9.3/Special Issue 12, January. http://extra.shu.ac.uk/emls/09-3/hopewhit.htm. Accessed 24 December 2014.
Kwiatkowski Tom et al. 2013. Scaling Semantic Parsers with On-the-Fly Ontology Matching. Proceedings of the Conference on Empirical Methods in Natural Language Processing, October: 1545–56. http://homes.cs.washington.edu/~lsz/papers/kcaz-emnlp13.pdf. Accessed 12 January 2015.
Mayer-Schönberger, Viktor and Kenneth Cukier. 2013. Big Data: A Revolution That Will Transform How We Live, Work and Think. London: John Murray.
Mimno, David. 2012. Computational Historiography: Data Mining in a Century of Classics Journals. Journal on Computing and Cultural Heritage, 5:1, 1–19.
Montaigne, Michel de. 1958. Complete Essays. Trans. Donald M. Frame, 1957. Stanford: Stanford University Press.
Moretti, Franco. 2005. Graphs, Maps, Trees: Abstract Models for Literary History. London: Verso.
Ogden, C.K. and I.A. Richards. 1923. The Meaning of Meaning. London: Kegan Paul.
Read the Web. http://rtw.ml.cmu.edu/rtw/. Accessed 12 January 2015.
Saussure, Ferdinand de. 1975. Course in General Linguistics. Trans. Wade Baskin, 1959. London: Fontana/Collins.
Stray, Jonathan. 2010. A Full-Text Visualization of the Iraq War Logs. http://jonathanstray.com/a-full-text-visualization-of-the-iraq-war-logs. Accessed 12 January 2015.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Chaudhuri, S. (2015). Beyond Bichitra. In: Chaudhuri, S. (eds) Bichitra: The Making of an Online Tagore Variorum. Quantitative Methods in the Humanities and Social Sciences. Springer, Cham. https://doi.org/10.1007/978-3-319-23678-0_10
Download citation
DOI: https://doi.org/10.1007/978-3-319-23678-0_10
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-23677-3
Online ISBN: 978-3-319-23678-0
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)