Now showing items 1-4 of 4

    • Artificial Error Generation with Machine Translation and Syntactic Patterns 

      Rei, Marek; Felice, M; Yuan, Z; Briscoe, Edward John (Association for Computational Linguistics, 2017-09-08)
      Shortage of available training data is holding back progress in the area of automated error detection. This paper investigates two alternative methods for artificially generating writing errors, in order to create additional ...
    • Attending to characters in neural sequence labeling models 

      Rei, Marek; Crichton, Gamal; Pyysalo, Sampo
      Sequence labeling architectures use word embeddings for capturing similarity, but suffer when handling previously unseen or rare words. We investigate character-level extensions to such models and propose a novel architecture ...
    • Combining manual rules and supervised learning for hedge cue and scope detection 

      Rei, Marek; Briscoe, Edward John (Association for Computational Linguistics, 2010-12-01)
      Hedge cues were detected using a supervised Conditional Random Field (CRF) classifier exploiting features from the RASP parser. The CRF’s predictions were filtered using known cues and unseen instances were removed, ...
    • An Error-Oriented Approach to Word Embedding Pre-Training 

      Farag, Y; Rei, Marek; Briscoe, Edward John (Association for Computational Linguistics, 2017-09-08)
      We propose a novel word embedding pre-training approach that exploits writing errors in learners' scripts. We compare our method to previous models that tune the embeddings based on script scores and the discrimination ...