Assistant Professor and the Director of Computational Linguistics in the Department of Linguistics at Indiana University

Multilingual NLP: Parsing German & Multilingual Coreference Resolution

In the last two decades, Natural Language Processing (NLP) has almost exclusively worked on English. However, when we apply the methods developed for English to other languages, at best, the performance is significantly below the results for English, but in many cases, the methods cannot be applied at all. This talk will concentrate on two problems, syntactic parsing and coreference resolution. For parsing, we will look at results for two German treebanks, which have a similar textual basis but different annotations schemes as well as strikingly different results. In the second part of the talk, I will present first results in multilingual coreference resolution, with a focus on markable extraction