Handling Anaphoras in multiple languages in the framework of Geometry Constructions

-- Pankaj Prateek and Jeetesh Mangwani

Abstract

In this project, we take up the problem of handling anaphoras in multiple languages in the context of a language-independent interpreter for drawing geometric diagrams. We focus on ruler and compass based construction problems. We start with use cases and motivations on why such a system would be useful and where deploying it would be fruitful. We give a brief tabulated review summary of related research work done on geometry related problems and point out the common trait that they lack the ability to decipher any problem/constraint expressed in a natural language. We, then, move to describe the design of the interpreter and the usage of cross-lingual alignment technique to provide the ability of language-independent interpretation. We briefly mention how the alignment model is utilised to realize the powerful translation feature. This is followed by a detailed account on handling anaphoras while extracting semantics from the translated sentences. We conclude with comprehensive results, difficulties faced and future work.

Report
Corpus + Code*(Updated: April 27, 2014)
Presentation
Bibliography

References:

  1. Umair Z Ahmed, Arpit Kumar, Monojit Choudhury, and Kalika Bali. Can modern statistical parsers lead to better natural language understanding for education? In Computational Linguistics and Intelligent Text Processing, pages 415–427. Springer, 2012.
  2. Sumit Gulwani, Vijay Anand Korthikanti, and Ashish Tiwari. Synthesizing geometry constructions. In ACM SIGPLAN Notices, volume 46, pages 50–61. ACM, 2011.
  3. Shachar Itzhaky, Sumit Gulwani, Neil Immerman, and Mooly Sagiv. Solving geometry problems using a combination of symbolic and numerical reasoning. Technical report, Technical report, Tel Aviv University, 2012.
  4. Dan Jurafsky and James H Martin. Speech & Language Processing. Pearson Education India, 2000.
  5. Hans Kamp, Josef Van Genabith, and Uwe Reyle. Discourse representation theory. In Handbook of philosophical logic, pages 125–394. Springer, 2011.
  6. Ruslan Mitkov. Anaphora resolution, volume 134. Longman London, 2002.
  7. Truc-Vien T. Nguyen and Massimo Poesio. Relational structures and models for coreference resolution. In Proceedings of the 24rd International Conference on Computational Linguistics, COLING ’12, December 2012.
  8. Franz Josef Och and Hermann Ney. A systematic comparison of various statistical alignment models. Computational linguistics, 29(1):19–51, 2003.
  9. Altaf Rahman and Vincent Ng. Ensemble-based coreference resolution. In Proceedings of the 22nd IJCAI Volume Three, pages 1884–1889, 2011.
  10. Rebecca Louise Root. The semantics of anaphora in discourse. PhD thesis, University of Texas at Austin, 1986.
  11. Pascal Schreck, Pascal Mathis, and Julien Narboux. Geometric construction problem solving in computer-aided learning. In Tools with Artificial Intelligence (ICTAI), 2012 IEEE 24th International Conference on, volume 1, pages 1139–1144. IEEE, 2012.
  12. Veselin Stoyanov and Jason Eisneree. Easy-first coreference resolution. In Proceedings 24rd COLING ’12, Dec 2012.
  13. Luke S Zettlemoyer and Michael Collins. Learning to map sentences to logical form: Structured classification with probabilistic categorial grammars. arXiv preprint arXiv:1207.1420, 2012.
* The code might have been updated after the mentioned date. The recent version can be found at https://bitbucket.org/pankajprateek/cs499_interpretinggeometryconstructions (This is a private repository. To get access, mail your bitbucket username to pratikkr@cse.iitk.ac.in)