Brian Roark

Spelling convention sensitivity in neural language models

Mar 06, 2023
Elizabeth Nielsen, Christo Kirov, Brian Roark

Figure 2 for Spelling convention sensitivity in neural language models

Figure 3 for Spelling convention sensitivity in neural language models

Figure 4 for Spelling convention sensitivity in neural language models

* EACL Findings 2023

Access Paper or Ask Questions

Beyond Arabic: Software for Perso-Arabic Script Manipulation

Jan 26, 2023
Alexander Gutkin, Cibu Johny, Raiomond Doctor, Brian Roark, Richard Sproat

Figure 2 for Beyond Arabic: Software for Perso-Arabic Script Manipulation

Figure 3 for Beyond Arabic: Software for Perso-Arabic Script Manipulation

Figure 4 for Beyond Arabic: Software for Perso-Arabic Script Manipulation

* Preprint to appear in the Proceedings of the 7th Arabic Natural Language Processing Workshop (WANLP 2022) at EMNLP, Abu Dhabi, United Arab Emirates, December 7-11, 2022. 7 pages

Access Paper or Ask Questions

Structured abbreviation expansion in context

Oct 04, 2021
Kyle Gorman, Christo Kirov, Brian Roark, Richard Sproat

Figure 2 for Structured abbreviation expansion in context

Figure 3 for Structured abbreviation expansion in context

Figure 4 for Structured abbreviation expansion in context

* Accepted to Findings of EMNLP 2021

Access Paper or Ask Questions

Finding Concept-specific Biases in Form--Meaning Associations

Apr 29, 2021
Tiago Pimentel, Brian Roark, Søren Wichmann, Ryan Cotterell, Damián Blasi

Figure 2 for Finding Concept-specific Biases in Form--Meaning Associations

Figure 3 for Finding Concept-specific Biases in Form--Meaning Associations

Figure 4 for Finding Concept-specific Biases in Form--Meaning Associations

* Accepted at NAACL 2021. This is the camera ready version. Code is available in https://github.com/rycolab/form-meaning-associations

Access Paper or Ask Questions

Disambiguatory Signals are Stronger in Word-initial Positions

Feb 03, 2021
Tiago Pimentel, Ryan Cotterell, Brian Roark

* Accepted at EACL 2021. Code is available in https://github.com/tpimentelms/frontload-disambiguation

Access Paper or Ask Questions

Processing South Asian Languages Written in the Latin Script: the Dakshina Dataset

Jul 02, 2020
Brian Roark, Lawrence Wolf-Sonkin, Christo Kirov, Sabrina J. Mielke, Cibu Johny, Isin Demirsahin, Keith Hall

Figure 2 for Processing South Asian Languages Written in the Latin Script: the Dakshina Dataset

Figure 3 for Processing South Asian Languages Written in the Latin Script: the Dakshina Dataset

Figure 4 for Processing South Asian Languages Written in the Latin Script: the Dakshina Dataset

* Published at LREC 2020

Access Paper or Ask Questions

Phonotactic Complexity and its Trade-offs

May 07, 2020
Tiago Pimentel, Brian Roark, Ryan Cotterell

* Transactions of the Association for Computational Linguistics, Vol. 8, 1-18
* Published in TACL: https://doi.org/10.1162/tacl_a_00296

Access Paper or Ask Questions

Language-agnostic Multilingual Modeling

Apr 20, 2020
Arindrima Datta, Bhuvana Ramabhadran, Jesse Emond, Anjuli Kannan, Brian Roark

Figure 2 for Language-agnostic Multilingual Modeling

Figure 3 for Language-agnostic Multilingual Modeling

Figure 4 for Language-agnostic Multilingual Modeling

Access Paper or Ask Questions

Meaning to Form: Measuring Systematicity as Information

Jul 26, 2019
Tiago Pimentel, Arya D. McCarthy, Damián E. Blasi, Brian Roark, Ryan Cotterell

Figure 2 for Meaning to Form: Measuring Systematicity as Information

Figure 3 for Meaning to Form: Measuring Systematicity as Information

Figure 4 for Meaning to Form: Measuring Systematicity as Information

* Accepted for publication at ACL 2019

Access Paper or Ask Questions

1

2

>>