Mention Detection for Improving Coreference Resolution in Russian Texts: A Machine Learning Approach

Autores/as

  • Svetlana Toldova National Research Institute “Higher School of Economics”
  • Max Ionov Moscow State University

DOI:

https://doi.org/10.13053/cys-20-4-2480

Palabras clave:

Coreference resolution, discourse-new detection, singleton detection, discourse processing, natural language processing, machine learning.

Resumen

Coreference resolution task is a well-known NLP application that was proven helpful for all high-level NLP applications: machine translation, summarization, and others. Mention detection is the sub-task of detecting the discourse status of each noun phrase, classifying it as a discourse-new, singleton (mentioned only once) or discourse-old occurrence. It has been shown that this task applied to a coreference resolution system may in crease its overall performance. So, we decided to adapt current approaches for English language in to Russian. We present some quality results of experiments regarding classifiers for mention detection and their application in to the coreference resolution task in Russian languages.

Biografía del autor/a

Svetlana Toldova, National Research Institute “Higher School of Economics”

Holds PhD in computational linguistics from Moscow State University. She is currently research professor at National Research Institute “Higher School of Economics”, Moscow, Russia. Her research areas are natural language processing (anaphora resolution, parsing, etc.).

Max Ionov, Moscow State University

Is Graduate Student at Moscow State University, Department of Theoretical and Applied Linguistics, Moscow, Russia. His research areas are natural language processing (anaphora resolution, parsing, etc.).

Descargas

Publicado

2016-12-18