DE eng

Search in the Catalogues and Directories

Hits 1 – 18 of 18

1
What transfers in morphological inflection? Experiments with analogical models ...
BASE
Show details
2
Quantifying Paradigm Shape in Spanish Verbs
LeFevre, Grace. - : The Ohio State University, 2021
BASE
Show details
3
Formalizing Inflectional Paradigm Shape with Information Theory
In: Proceedings of the Society for Computation in Linguistics (2021)
BASE
Show details
4
When context is and isn’t helpful: A corpus study of naturalistic speech [<Journal>]
Hitczenko, Kasia [Verfasser]; Mazuka, Reiko [Verfasser]; Elsner, Micha [Verfasser].
DNB Subject Category Language
Show details
5
The Paradigm Discovery Problem ...
Erdmann, Alexander; Elsner, Micha; Wu, Shijie. - : ETH Zurich, 2020
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 ...
Hitczenko, Kasia; Mazuka, Reiko; Elsner, Micha. - : University of Massachusetts Amherst, 2019
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
11
Lexical Networks in !Xung and Ju
Hussain, Syed-Amad. - : The Ohio State University, 2018
BASE
Show details
12
Proceedings of the 41th Annual Boston University Conference on Language Development [held November 4-6, 2016, in Boston] 1. 1
In: 1 (2017), S. 32-45
Leibniz-Zentrum Allgemeine Sprachwissenschaft
Show details
13
Giving Good Directions: Order of Mention Reflects Visual Salience
Clarke, Alasdair D. F.; Elsner, Micha; Rohde, Hannah. - : Frontiers Media S.A., 2015
BASE
Show details
14
Giving Good Directions: Order of Mention Reflects Visual Salience
Clarke, Alasdair DF; Elsner, Micha; Rohde, Hannah. - : Frontiers Media, 2015
BASE
Show details
15
POS induction with distributional and morphological information using a distance-dependent Chinese Restaurant Process
Sirts, Kairit; Eisenstein, Jacob; Elsner, Micha. - : Stroudsburg, PA : Association for Computational Linguistics, 2014
BASE
Show details
16
Where's Wally: the influence of visual salience on referring expression generation
Clarke, Alasdair D. F.; Elsner, Micha; Rohde, Hannah. - : Frontiers Media S.A., 2013
BASE
Show details
17
EM works for pronoun anaphora resolution
In: Association for Computational Linguistics / European Chapter. Conference of the European Chapter of the Association for Computational Linguistics. - Menlo Park, Calif. : ACL 12 (2009), 148-156
BLLDB
Show details
18
Structured generative models for unsupervised named-entity clustering
Elsner, Micha; Charniak, Eugene; Johnson, Mark. - : East Stroudsburg, PA : Association for Computational Linguistics, 2009
BASE
Show details

Catalogues
0
0
0
0
1
0
1
Bibliographies
1
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
15
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern