Exploring Neural Architectures And Techniques For Typologically Diverse Morphological Inflection

Morphological inflection in low resource languages is critical to augment existing corpora in Low Resource Languages, which can help develop several applications in these languages with very good social impact. We describe our attention-based encoder-decoder approach that we implement using LSTMs and Transformers as the base units. We also describe the ancillary techniques that we experimented with, such as hallucination, language vector injection, sparsemax loss and adversarial language network alongside our approach to select the related language(s) for training. We present the results we generated on the constrained as well as unconstrained SIGMORPHON 2020 dataset (CITATION). One of the primary goals of our paper was to study the contribution varied components described above towards the performance of our system and perform an analysis on the same.

[1]  Ryan Cotterell,et al.  CoNLL-SIGMORPHON 2017 Shared Task: Universal Morphological Reinflection in 52 Languages , 2017, CoNLL.

[2]  Andreas Scherbakov.  The UniMelb Submission to the SIGMORPHON 2020 Shared Task 0: Typologically Diverse Morphological Inflection , 2020, SIGMORPHON.

[3]  Claire Cardie,et al.  Multi-Source Cross-Lingual Model Transfer: Learning What to Share , 2018, ACL.

[4]  Graham Neubig,et al.  Pushing the Limits of Low-Resource Morphological Inflection , 2019, EMNLP.

[5]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

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

[7]  Ryan Cotterell,et al.  SIGMORPHON 2020 Shared Task 0: Typologically Diverse Morphological Inflection , 2020, SIGMORPHON.

[8]  Guillaume Lample,et al.  Polyglot Neural Language Models: A Case Study in Cross-Lingual Phonetic Representation Learning , 2016, NAACL.

[9]  Patrick Littell,et al.  URIEL and lang2vec: Representing languages as typological, geographical, and phylogenetic vectors , 2017, EACL.

[10]  André F. T. Martins,et al.  IT–IST at the SIGMORPHON 2019 Shared Task: Sparse Two-headed Models for Inflection , 2019, Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology.

[11]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[12]  Ryan Cotterell,et al.  Exact Hard Monotonic Attention for Character-Level Transduction , 2019, ACL.

[13]  Çağrı Çöltekin,et al.  Cross-lingual morphological inflection with explicit alignment , 2019, Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology.