IIT(BHU)–IIITH at CoNLL–SIGMORPHON 2018 Shared Task on Universal Morphological Reinflection

This paper describes the systems submitted by IIT (BHU), Varanasi/IIIT Hyderabad (IITBHU–IIITH) for Task 1 of CoNLL– SIGMORPHON 2018 Shared Task on Universal Morphological Reinflection (Cotterell et al., 2018). The task is to generate the inflected form given a lemma and set of morphological features. The systems are evaluated on over 100 distinct languages and three different resource settings (low, medium and high). We formulate the task as a sequence to sequence learning problem. As most of the characters in inflected form are copied from the lemma, we use Pointer-Generator Network (See et al., 2017) which makes it easier for the system to copy characters from the lemma. PointerGenerator Network also helps in dealing with out-of-vocabulary characters during inference. Our best performing system stood 4th among 28 systems, 3rd among 23 systems and 4th among 23 systems for the low, medium and high resource setting respectively.

[1]  Grzegorz Kondrak,et al.  Inflection Generation as Discriminative String Transduction , 2015, HLT-NAACL.

[2]  Katharina Kann,et al.  MED: The LMU System for the SIGMORPHON 2016 Shared Task on Morphological Reinflection , 2016, SIGMORPHON.

[3]  Grzegorz Kondrak,et al.  If you can't beat them, join them: the University of Alberta system description , 2017, CoNLL Shared Task.

[4]  Yoav Goldberg,et al.  Morphological Inflection Generation with Hard Monotonic Attention , 2016, ACL.

[5]  Alexander J. Smola,et al.  Deep Sets , 2017, 1703.06114.

[6]  Jindrich Libovický,et al.  Attention Strategies for Multi-Source Sequence-to-Sequence Learning , 2017, ACL.

[7]  Christopher D. Manning,et al.  Get To The Point: Summarization with Pointer-Generator Networks , 2017, ACL.

[8]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[9]  Markus Forsberg,et al.  Semi-supervised learning of morphological paradigms and lexicons , 2014, EACL.

[10]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[11]  Yulia Tsvetkov,et al.  Morphological Inflection Generation Using Character Sequence to Sequence Learning , 2015, NAACL.

[12]  Graham Neubig,et al.  Morphological Inflection Generation with Multi-space Variational Encoder-Decoders , 2017, CoNLL.

[13]  Ryan Cotterell,et al.  The CoNLL–SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection , 2018, CoNLL.

[14]  John DeNero,et al.  Supervised Learning of Complete Morphological Paradigms , 2013, NAACL.

[15]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[16]  Samy Bengio,et al.  Order Matters: Sequence to sequence for sets , 2015, ICLR.

[17]  Ling Liu,et al.  Data Augmentation for Morphological Reinflection , 2017, CoNLL.

[18]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[19]  Markus Forsberg,et al.  Paradigm classification in supervised learning of morphology , 2015, HLT-NAACL.

[20]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[21]  Kristina Toutanova,et al.  Generating Complex Morphology for Machine Translation , 2007, ACL.

[22]  Simon Clematide,et al.  Align and Copy: UZH at SIGMORPHON 2017 Shared Task for Morphological Reinflection , 2017, CoNLL.

[23]  Katharina Kann,et al.  The LMU System for the CoNLL-SIGMORPHON 2017 Shared Task on Universal Morphological Reinflection , 2017, CoNLL.

[24]  Katharina Kann,et al.  Training Data Augmentation for Low-Resource Morphological Inflection , 2017, CoNLL.