Saeed Najafi


pdf bib
Weakly-Supervised Questions for Zero-Shot Relation Extraction
Saeed Najafi | Alona Fyshe
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics

Zero-Shot Relation Extraction (ZRE) is the task of Relation Extraction where the training and test sets have no shared relation types. This very challenging domain is a good test of a model’s ability to generalize. Previous approaches to ZRE reframed relation extraction as Question Answering (QA), allowing for the use of pre-trained QA models. However, this method required manually creating gold question templates for each new relation. Here, we do away with these gold templates and instead learn a model that can generate questions for unseen relations. Our technique can successfully translate relation descriptions into relevant questions, which are then leveraged to generate the correct tail entity. On tail entity extraction, we outperform the previous state-of-the-art by more than 16 F1 points without using gold question templates. On the RE-QA dataset where no previous baseline for relation extraction exists, our proposed algorithm comes within 0.7 F1 points of a system that uses gold question templates. Our model also outperforms the state-of-the-art ZRE baselines on the FewRel and WikiZSL datasets, showing that QA models no longer need template questions to match the performance of models specifically tailored to the ZRE task. Our implementation is available at


pdf bib
Combining Neural and Non-Neural Methods for Low-Resource Morphological Reinflection
Saeed Najafi | Bradley Hauer | Rashed Rubby Riyadh | Leyuan Yu | Grzegorz Kondrak
Proceedings of the CoNLL–SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection

pdf bib
Comparison of Assorted Models for Transliteration
Saeed Najafi | Bradley Hauer | Rashed Rubby Riyadh | Leyuan Yu | Grzegorz Kondrak
Proceedings of the Seventh Named Entities Workshop

We report the results of our experiments in the context of the NEWS 2018 Shared Task on Transliteration. We focus on the comparison of several diverse systems, including three neural MT models. A combination of discriminative, generative, and neural models obtains the best results on the development sets. We also put forward ideas for improving the shared task.

pdf bib
String Transduction with Target Language Models and Insertion Handling
Garrett Nicolai | Saeed Najafi | Grzegorz Kondrak
Proceedings of the Fifteenth Workshop on Computational Research in Phonetics, Phonology, and Morphology

Many character-level tasks can be framed as sequence-to-sequence transduction, where the target is a word from a natural language. We show that leveraging target language models derived from unannotated target corpora, combined with a precise alignment of the training data, yields state-of-the art results on cognate projection, inflection generation, and phoneme-to-grapheme conversion.


pdf bib
If you can’t beat them, join them: the University of Alberta system description
Garrett Nicolai | Bradley Hauer | Mohammad Motallebi | Saeed Najafi | Grzegorz Kondrak
Proceedings of the CoNLL SIGMORPHON 2017 Shared Task: Universal Morphological Reinflection