The SIGMORPHON 2019 Shared Task: Morphological Analysis in Context and Cross-Lingual Transfer for Inflection

@article{McCarthy2019TheS2,
  title={The SIGMORPHON 2019 Shared Task: Morphological Analysis in Context and Cross-Lingual Transfer for Inflection},
  author={Arya D. McCarthy and Ekaterina Vylomova and Shijie Wu and Chaitanya Malaviya and Lawrence Wolf-Sonkin and Garrett Nicolai and Christo Kirov and Miikka Silfverberg and Sabrina J. Mielke and Jeffrey Heinz and Ryan Cotterell and Mans Hulden},
  journal={ArXiv},
  year={2019},
  volume={abs/1910.11493}
}
The SIGMORPHON 2019 shared task on cross-lingual transfer and contextual analysis in morphology examined transfer learning of inflection between 100 language pairs, as well as contextual lemmatization and morphosyntactic description in 66 languages. The first task evolves past years’ inflection tasks by examining transfer of morphological inflection knowledge from a high-resource language to a low-resource language. This year also presents a new second challenge on lemmatization and… 

Tables from this paper

SIGMORPHON–UniMorph 2022 Shared Task 0: Modeling Inflection in Language Acquisition
This year’s iteration of the SIGMORPHONUniMorph shared task on “human-like” morphological inflection generation focuses on generalization and errors in language acquisition. Systems are trained on
Leveraging Principal Parts for Morphological Inflection
TLDR
The overall average performance of the CU Ling team's submission ranks the first in both average accuracy and Levenshtein distance from the gold inflection among all submissions including those using external resources.
The Effect of Linguistic Typology on Transfer Learning of Morphology
In the SIGMORPHON 2019 shared task 1, multiple teams attempted for the first time to leverage transfer learning to build more accurate models of natural language morphology with small amounts of
What transfers in morphological inflection? Experiments with analogical models
We investigate how abstract processes like suffixation can be learned from morphological inflection task data using an analogical memory-based framework. In this framework, the inflection target form
(Un)solving Morphological Inflection: Lemma Overlap Artificially Inflates Models’ Performance
TLDR
This work proposes to re-evaluate morphological inflection models by employing harder train-test splits that will challenge the generalization capacity of the models, and proposes a split-by-lemma method to challenge the performance on existing benchmarks.
Well-Defined Morphology is Sentence-Level Morphology
TLDR
This work defines a morphological annotation scheme by a fixed set of inflectional features to allow annotation for sentence-inflection, and shows that the task of reinflection gets substantially more difficult but that the change of scope from words to well-defined sentences allows interface with contextualized language models.
The SIGMORPHON 2020 Shared Task on Unsupervised Morphological Paradigm Completion
TLDR
This shared task on unsupervised morphological paradigm completion (SIGMORPHON 2020 Task 2) is described, a novel task in the field of inflectional morphology, where none of the submitted systems was able to improve over the baseline on average over all 9 test languages.
Findings of the SIGMORPHON 2021 Shared Task on Unsupervised Morphological Paradigm Clustering
TLDR
The goal of the SIGMORPHON 2021 Shared Task on Unsupervised Morphological Paradigm Clustering is to cluster word types from a raw text corpus into paradigms, which receives 14 submissions from 4 teams that follow different strategies, and the best performing system is based on adaptor grammars.
Morphology is not just a naive Bayes – UniMelb Submission to SIGMORPHON 2022 ST on Morphological Inflection
TLDR
A nonneural system that extracted transformation patterns from alignments between a lemma and inflected forms and chose a pattern based on its abstractness score discovered that such score that does not account for all possible combinations of string segments as well as morphosyntactic features is not sufficient for a certain proportion of inflection cases.
Pushing the Limits of Low-Resource Morphological Inflection
TLDR
A novel two-step attention architecture for the inflection decoder is presented and the crucial factors for success with cross-lingual transfer for morphological inflection: typological similarity and a common representation across languages are identified.
...
...

References

SHOWING 1-10 OF 36 REFERENCES
The CoNLL–SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection
TLDR
The CoNLL--SIGMORPHON 2018 shared task on supervised learning of morphological generation featured data sets from 103 typologically diverse languages and featured a new second task which asked participants to inflect words in sentential context, similar to a cloze task.
Neural Factor Graph Models for Cross-lingual Morphological Tagging
TLDR
This paper proposes a method for cross-lingual morphological tagging that aims to improve information sharing between languages by relaxing the assumption that tag sets exactly overlap between the HRL and LRL.
A Universal Feature Schema for Rich Morphological Annotation and Fine-Grained Cross-Lingual Part-of-Speech Tagging
TLDR
A universal morphological feature schema is presented, which is a set of features that represent the finest distinctions in meaning that are expressed by inflectional morphology across languages, and is used to assess the effectiveness of cross-linguistic projection of a multilingual consensus of these fine-grained morphological features.
Exploring Cross-Lingual Transfer of Morphological Knowledge In Sequence-to-Sequence Models
TLDR
This work proposes a set of data-dependent experiments using an existing encoder-decoder recurrent neural network for the paradigm completion task and shows that indeed the performance gains surpass a pure regularization effect and that knowledge about language and morphology can be transferred.
Language Modeling for Morphologically Rich Languages: Character-Aware Modeling for Word-Level Prediction
TLDR
The main technical contribution of this work is a novel method for injecting subword-level information into semantic word vectors, integrated into the neural language modeling training, to facilitate word-level prediction.
Modeling Language Variation and Universals: A Survey on Typological Linguistics for Natural Language Processing
TLDR
It is shown that to date, the use of information in existing typological databases has resulted in consistent but modest improvements in system performance, due to both intrinsic limitations of databases and under-employment of the typological features included in them.
Context Sensitive Neural Lemmatization with Lematus
TLDR
Lematus, a lemmatizer based on a standard encoder-decoder architecture, which incorporates character-level sentence context, is introduced, and it is shown that including context significantly improves results against a context-free version of the model.
MED: The LMU System for the SIGMORPHON 2016 Shared Task on Morphological Reinflection
This paper presents MED, the main system of the LMU team for the SIGMORPHON 2016 Shared Task on Morphological Reinflection as well as an extended analysis of how different design choices contribute
Marrying Universal Dependencies and Universal Morphology
TLDR
A deterministic mapping from Universal Dependencies v2 features into the UniMorph schema is presented to ease interoperability and a critical evaluation of the foundations, strengths, and weaknesses of the two annotation projects is presented.
A Simple Joint Model for Improved Contextual Neural Lemmatization
TLDR
A simple joint neural model for lemmatization and morphological tagging that achieves state-of-the-art results on 20 languages from the Universal Dependencies corpora is presented.
...
...