State-of-the-art generalisation research in NLP: a taxonomy and review
The ability to generalise well is one of the primary desiderata of natural language
processing (NLP). Yet, what'good generalisation'entails and how it should be evaluated is …
processing (NLP). Yet, what'good generalisation'entails and how it should be evaluated is …
Generative linguistics and neural networks at 60: Foundation, friction, and fusion
J Pater - Language, 2019 - muse.jhu.edu
The birthdate of both generative linguistics and neural networks can be taken as 1957, the
year of the publication of foundational work by both Noam Chomsky and Frank Rosenblatt …
year of the publication of foundational work by both Noam Chomsky and Frank Rosenblatt …
[HTML][HTML] Modeling morphology with linear discriminative learning: Considerations and design choices
This study addresses a series of methodological questions that arise when modeling
inflectional morphology with Linear Discriminative Learning. Taking the semi-productive …
inflectional morphology with Linear Discriminative Learning. Taking the semi-productive …
Generalising to German plural noun classes, from the perspective of a recurrent neural network
Inflectional morphology has since long been a useful testing ground for broader questions
about generalisation in language and the viability of neural network models as cognitive …
about generalisation in language and the viability of neural network models as cognitive …
From form (s) to meaning: Probing the semantic depths of language models using multisense consistency
The staggering pace with which the capabilities of large language models (LLMs) are
increasing, as measured by a range of commonly used natural language understanding …
increasing, as measured by a range of commonly used natural language understanding …
(Un) solving Morphological Inflection: Lemma Overlap Artificially Inflates Models' Performance
O Goldman, D Guriel, R Tsarfaty - arXiv preprint arXiv:2108.05682, 2021 - arxiv.org
In the domain of Morphology, Inflection is a fundamental and important task that gained a lot
of traction in recent years, mostly via SIGMORPHON's shared-tasks. With average accuracy …
of traction in recent years, mostly via SIGMORPHON's shared-tasks. With average accuracy …
Less is more: why all paradigms are defective, and why that is a good thing
AL Janda, MF Tyers - Corpus linguistics and linguistic theory, 2021 - degruyter.com
Only a fraction of lexemes are encountered in all their paradigm forms in any corpus or even
in the lifetime of any speaker. This raises a question as to how it is that native speakers …
in the lifetime of any speaker. This raises a question as to how it is that native speakers …
An encoder-decoder approach to the paradigm cell filling problem
M Silfverberg, M Hulden - Proceedings of the 2018 Conference on …, 2018 - aclanthology.org
Abstract The Paradigm Cell Filling Problem in morphology asks to complete word inflection
tables from partial ones. We implement novel neural models for this task, evaluating them on …
tables from partial ones. We implement novel neural models for this task, evaluating them on …
Classifications flexionnelles. Étude quantitative des structures de paradigmes
S Beniamine - 2018 - theses.hal.science
Dans les systèmes flexionnels, il arrive que des propriétés morphosyntaxiques soient
exprimées différemment d'un lexème à l'autre. Pour décrire ces systèmes, il est usuel …
exprimées différemment d'un lexème à l'autre. Pour décrire ces systèmes, il est usuel …
[HTML][HTML] VeLeRo: an inflected verbal lexicon of standard Romanian and a quantitative analysis of morphological predictability
This paper presents VeLeRo, an inflected lexicon of Standard Romanian which contains the
full paradigm of 7297 verbs in phonological form. We explain the process by which the …
full paradigm of 7297 verbs in phonological form. We explain the process by which the …