1 |
What transfers in morphological inflection? Experiments with analogical models ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Formalizing Inflectional Paradigm Shape with Information Theory
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2021)
|
|
BASE
|
|
Show details
|
|
6 |
The Paradigm Discovery Problem
|
|
|
|
In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (2020)
|
|
BASE
|
|
Show details
|
|
7 |
Interpreting Sequence-to-Sequence Models for Russian Inflectional Morphology
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2020)
|
|
Abstract:
Morphological inflection, as an engineering task in NLP, has seen a rise in the use of neural sequence-to-sequence models (Kann et al. 2016, Cotterell et al. 2018, Aharoni et al. 2017). While these outperform traditional systems based on edit rule induction, it is hard to interpret what they are learning in linguistic terms. We propose a new method of analyzing morphological sequence-to-sequence models which groups errors into linguistically meaningful classes, making what the model learns more transparent. As a case study, we analyze a seq2seq model on Russian, finding that semantic and lexically conditioned allomorphy (e.g. inanimate nouns like zavod `factory' and animates like otec `father' have different, animacy-conditioned accusative forms) are responsible for its relatively low accuracy. Augmenting the model with word embeddings as a proxy for lexical semantics leads to significant improvements in predicted wordform accuracy.
|
|
Keyword:
Computational Linguistics; error analysis; interpretability; morphology; sequence-to-sequence
|
|
URL: https://scholarworks.umass.edu/cgi/viewcontent.cgi?article=1156&context=scil https://scholarworks.umass.edu/scil/vol3/iss1/39
|
|
BASE
|
|
Hide details
|
|
8 |
Stop the Morphological Cycle, I Want to Get Off: Modeling the Development of Fusion
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2020)
|
|
BASE
|
|
Show details
|
|
9 |
Normalization may be ineffective for phonetic category learning ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Normalization may be ineffective for phonetic category learning
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2019)
|
|
BASE
|
|
Show details
|
|
13 |
Giving Good Directions: Order of Mention Reflects Visual Salience
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Giving Good Directions: Order of Mention Reflects Visual Salience
|
|
|
|
BASE
|
|
Show details
|
|
15 |
POS induction with distributional and morphological information using a distance-dependent Chinese Restaurant Process
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Where's Wally: the influence of visual salience on referring expression generation
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Structured generative models for unsupervised named-entity clustering
|
|
|
|
BASE
|
|
Show details
|
|
|
|