Marc Canby


2023

pdf bib
A Framework for Bidirectional Decoding: Case Study in Morphological Inflection
Marc Canby | Julia Hockenmaier
Findings of the Association for Computational Linguistics: EMNLP 2023

Transformer-based encoder-decoder models that generate outputs in a left-to-right fashion have become standard for sequence-to-sequence tasks. In this paper, we propose a framework for decoding that produces sequences from the “outside-in”: at each step, the model chooses to generate a token on the left, on the right, or join the left and right sequences. We argue that this is more principled than prior bidirectional decoders. Our proposal supports a variety of model architectures and includes several training methods, such as a dynamic programming algorithm that marginalizes out the latent ordering variable. Our model sets state-of-the-art (SOTA) on the 2022 and 2023 shared tasks, beating the next best systems by over 4.7 and 2.7 points in average accuracy respectively. The model performs particularly well on long sequences, can implicitly learn the split point of words composed of stem and affix, and performs better relative to the baseline on datasets that have fewer unique lemmas.

2020

pdf bib
University of Illinois Submission to the SIGMORPHON 2020 Shared Task 0: Typologically Diverse Morphological Inflection
Marc Canby | Aidana Karipbayeva | Bryan Lunt | Sahand Mozaffari | Charlotte Yoder | Julia Hockenmaier
Proceedings of the 17th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology

The objective of this shared task is to produce an inflected form of a word, given its lemma and a set of tags describing the attributes of the desired form. In this paper, we describe a transformer-based model that uses a bidirectional decoder to perform this task, and evaluate its performance on the 90 languages and 18 language families used in this task.