Towards fast natural language parsing: FASTPARSE ERC Starting Grant

• Autores: Carlos Gómez Rodríguez
• Localización: Procesamiento del lenguaje natural, ISSN 1135-5948, Nº. 59, 2017, págs. 121-124
• Idioma: inglés
• Títulos paralelos:
  • Hacia el análisis sintáctico rápido de lenguaje natural: la ERC Starting Grant FASTPARSE
• Enlaces
  • Texto completo
• Resumen
  • español

    El proyecto FASTPARSE (Fast Natural Language Parsing for Large-Scale NLP), financiado por el Consejo Europeo de Investigación (ERC), tiene como objetivo lograr un salto cualitativo en la velocidad de los analizadores sintácticos de lenguaje natural, desarrollando analizadores lo suficientemente rápidos para facilitar el procesado de textos a escala web. Para ello, el proyecto propone distintas líneas de investigación que combinan técnicas de optimización informática, algoritmia, análisis estadístico de propiedades del lenguaje y modelos cognitivos inspirados en el procesado humano del mismo.

  • English

    The goal of the FASTPARSE project (Fast Natural Language Parsing for Large-Scale NLP), funded by the European Research Council (ERC), is to achieve a breakthrough in the speed of natural language syntactic parsers, developing fast parsers that are suitable for web-scale processing. For this purpose, the project proposes several research lines involving computational optimization, algorithmics, statistical analysis of language and cognitive models inspired in human language processing.

• Referencias bibliográficas
  • Baroni, M. 2009. Distributions in text. In Corpus Linguistics: An International Handbook. M. de Gruyter, pages 803-821.
  • Bohnet, B. 2010. Top accuracy and fast dependency parsing is not a contradiction. In Proceedings of the 23rd International Conference on Computational...
  • Choi, J. D. and A. McCallum. 2013. Transition-based dependency parsing with selectional branching. In Proceedings of the 51st Annual Meeting...
  • Christiansen, M. H. and N. Chater. 2016. The now-or-never bottleneck: a fundamental constraint on language. Behavioral and Brain Sciences,...
  • Crabbé, B. 2015. Multilingual discriminative lexicalized phrase structure parsing. In Proceedings of the 2015 Conference on Empirical Methods...
  • Deacon, T. W. 1997. The Symbolic Species: The Co-evolution of Language and the Brain. W.W. Norton.
  • Ferrer-i-Cancho, R. and C. Gómez-Rodríguez. 2016. Crossings as a side effect of dependency lengths. Complexity, 21(S2):320-328.
  • Futrell, R., K. Mahowald, and E. Gibson. 2015. Large-scale evidence of dependency length minimization in 37 languages. Proceedings of the...
  • Goldberg, Y. and J. Orwant. 2013. A dataset of syntactic-ngrams over time from a very large corpus of english books. In Second Joint Conference...
  • Gómez-Rodríguez, C. 2016a. Natural language processing and the Now-or-Never bottleneck. Behavioral and Brain Sci- ences, 39:e74, 1.
  • Gómez-Rodríguez, C. 2016b. Restricted non-projectivity: Coverage vs. efficiency. Comput. Linguist., 42(4):809-817.
  • Gulordava, K. and P. Merlo. 2015. Diachronic trends in word order freedom and dependency length in dependencyannotated corpora of Latin and...
  • Ha, L. Q., E. I. Sicilia-Garcia, J. Ming, and F. J. Smith. 2002. Extension of Zipf's law to words and phrases. In COLING 2002: The 19th...
  • Kummerfeld, K. J., D. Hall, R. J. Curran, and D. Klein. 2012. Parser showdown at the wall street corral: An empirical investigation of error...
  • Rasooli, M. S. and J. R. Tetreault. 2015. Yara parser: A fast and accurate dependency parser. CoRR, abs/1503.06733.