The SIGMORPHON 2020 Shared Task on Multilingual Grapheme-to-Phoneme Conversion

Gorman, Kyle; Ashby, Lucas F.E.; Goyzueta, Aaron; McCarthy, Arya D.; Wu, Shijie; You, Daniel

doi:10.18653/v1/2020.sigmorphon-1.2

Cited by 31 publications

(19 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The SIGMORPHON 2020 Shared Task is composed of three tasks: Task 0 on typologically diverse morphological inflection (Vylomova et al, 2020), Task 1 on multilingual grapheme-tophoneme conversion (Gorman et al, 2020), and Task 2 on unsupervised morphological paradigm completion . We submit systems to Tasks 0 and 2.…”

Section: Sigmorphon 2020 Shared Taskmentioning

confidence: 99%

The NYU-CUBoulder Systems for SIGMORPHON 2020 Task 0 and Task 2

Singer¹,

Kann²

2020

Proceedings of the 17th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology

View full text Add to dashboard Cite

We describe the NYU-CUBoulder systems for the SIGMORPHON 2020 Task 0 on typologically diverse morphological inflection and Task 2 on unsupervised morphological paradigm completion. The former consists of generating morphological inflections from a lemma and a set of morphosyntactic features describing the target form. The latter requires generating entire paradigms for a set of given lemmas from raw text alone. We model morphological inflection as a sequenceto-sequence problem, where the input is the sequence of the lemma's characters with morphological tags, and the output is the sequence of the inflected form's characters. First, we apply a transformer model to the task. Second, as inflected forms share most characters with the lemma, we further propose a pointer-generator transformer model to allow easy copying of input characters. Our best performing system for Task 0 is placed 6th out of 23 systems. We further use our inflection systems as subcomponents of approaches for Task 2. Our best performing system for Task 2 is the 2nd best out of 7 submissions.

show abstract

Section: Sigmorphon 2020 Shared Taskmentioning

confidence: 99%

The NYU-CUBoulder Systems for SIGMORPHON 2020 Task 0 and Task 2

Singer¹,

Kann²

2020

Proceedings of the 17th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology

View full text Add to dashboard Cite

show abstract

“…It features fifteen languages from various phylogenetic families and written in different scripts. We refer the reader to Gorman et al (2020) for an overview of the language data. Each language comes with 3,600 training and 450 development set examples.…”

Section: Introductionmentioning

confidence: 99%

CLUZH at SIGMORPHON 2020 Shared Task on Multilingual Grapheme-to-Phoneme Conversion

Makarov¹,

Clematide²

2020

Proceedings of the 17th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology

View full text Add to dashboard Cite

This paper describes the submission by the team from the Institute of Computational Linguistics, Zurich University, to the Multilingual Grapheme-to-Phoneme Conversion (G2P) Task of the SIGMORPHON 2020 challenge. The submission adapts our system from the 2018 edition of the SIGMORPHON shared task. Our system is a neural transducer that operates over explicit edit actions and is trained with imitation learning. It is well-suited for morphological string transduction partly because it exploits the fact that the input and output character alphabets overlap. The challenge posed by G2P has been to adapt the model and the training procedure to work with disjoint alphabets. We adapt the model to use substitution edits and train it with a weighted finitestate transducer acting as the expert policy. An ensemble of such models produces competitive results on G2P. Our submission ranks second out of 23 submissions by a total of nine teams.

show abstract

“…• We show that sparse seq2seq techniques, previously used for morphological inflection and machine translation , are also effective for multilingual g2p. We make four submissions to Task 1 (Gorman et al, 2020), which differ based on their choice of softmax replacement (1.5-entmax or sparsemax) and their architecture (RNN or transformer). Our strongest models finish third in word error rate (WER) and second in phoneme error rate (PER).…”

Section: Introductionmentioning

confidence: 99%

One-Size-Fits-All Multilingual Models

Peters¹,

Martins²

2020

Proceedings of the 17th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology

View full text Add to dashboard Cite

This paper presents DeepSPIN's submissions to Tasks 0 and 1 of the SIGMORPHON 2020 Shared Task. For both tasks, we present multilingual models, training jointly on data in all languages. We perform no languagespecific hyperparameter tuning -each of our submissions uses the same model for all languages. Our basic architecture is the sparse sequence-to-sequence model with entmax attention and loss, which allows our models to learn sparse, local alignments while still being trainable with gradient-based techniques. For Task 1, we achieve strong performance with both RNN-and transformer-based sparse models. For Task 0, we extend our RNN-based model to a multi-encoder set-up in which separate modules encode the lemma and inflection sequences. Despite our models' lack of language-specific tuning, they tie for first in Task 0 and place third in Task 1.

show abstract

The SIGMORPHON 2020 Shared Task on Multilingual Grapheme-to-Phoneme Conversion

Cited by 31 publications

References 35 publications

The NYU-CUBoulder Systems for SIGMORPHON 2020 Task 0 and Task 2

The NYU-CUBoulder Systems for SIGMORPHON 2020 Task 0 and Task 2

CLUZH at SIGMORPHON 2020 Shared Task on Multilingual Grapheme-to-Phoneme Conversion

One-Size-Fits-All Multilingual Models

Contact Info

Product

Resources

About