1 |
Literacy and Access to the Opportunities of Democracy
|
|
|
|
In: Internship Reflection Papers (2021)
|
|
BASE
|
|
Show details
|
|
2 |
Humor, creativity and lexical creation ; Humour, créativité et création lexicale
|
|
|
|
In: ISSN: 1951-6215 ; EISSN: 1951-6215 ; Lexis. Journal in English Lexicology ; https://hal.archives-ouvertes.fr/hal-02994959 ; Centre d’Études Linguistiques (Linguistics Research Center) University of Lyon. Lexis. Journal in English Lexicology, 2021, Humor, creativity and lexical creation, 1951-6215. ⟨10.4000/lexis.5585⟩ ; https://journals.openedition.org/lexis/3602 (2021)
|
|
BASE
|
|
Show details
|
|
3 |
Automatic Language Identification in Code-Switched Hindi-English Social Media Text
|
|
|
|
In: Journal of Open Humanities Data; Vol 7 (2021); 7 ; 2059-481X (2021)
|
|
Abstract:
Natural Language Processing (NLP) tools typically struggle to process code-switched data and so linguists are commonly forced to annotate such data manually. As this data becomes more readily available, automatic tools are increasingly needed to help speed up the annotation process and improve consistency. Last year, such a toolkit was developed to semi-automatically annotate transcribed bilingual code-switched Vietnamese-English speech data with token-based language information and POS tags (hereafter the CanVEC toolkit, L. Nguyen & Bryant, 2020). In this work, we extend this methodology to another language pair, Hindi-English, to explore the extent to which we can standardise the automation process. Specifically, we applied the principles behind the CanVEC toolkit to data from the International Conference on Natural Language Processing (ICON) 2016 shared task, which consists of social media posts (Facebook, Twitter and WhatsApp) that have been annotated with language and POS tags (Molina et al., 2016). We used the ICON-2016 annotations as the gold-standard labels in the language identification task. Ultimately, our tool achieved an F1 score of 87.99% on the ICON-2016 data. We then evaluated the first 500 tokens of each social media subset manually, and found almost 40% of all errors were caused entirely by problems with the gold-standard, i.e., our system was correct. It is thus likely that the overall accuracy of our system is higher than reported. This shows great potential for effectively automating the annotation of code-switched corpora, on different language combinations, and in different genres. We finally discuss some limitations of our approach and release our code and human evaluation together with this paper.
|
|
Keyword:
automatic annotation; code-switching; Computational Linguistics; English; Hindi; language identification; Linguistics; Vietnamese
|
|
URL: https://openhumanitiesdata.metajnl.com/jms/article/view/44 https://doi.org/10.5334/johd.44
|
|
BASE
|
|
Hide details
|
|
4 |
Vowel duration and consonant voicing: A production study ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Mental simulation of the illusory and the factual in negation processing ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Does the language you speak shape the way you think about the world? ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Investigating the processing of question types in contexts with different prior beliefs ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Social Factors in the Production, Perception and Processing of Contact Varieties: Evidence from Bilingual Corpora, Nativeness Evaluations, and Real-time Processing (EEG) of Spanish-accented English
|
|
|
|
BASE
|
|
Show details
|
|
9 |
A contrastive study of the EFL vowel system in native Spanish, French, German and Russian learners
|
|
|
|
In: TDX (Tesis Doctorals en Xarxa) (2021)
|
|
BASE
|
|
Show details
|
|
10 |
The French-English Bilingual Mind
|
|
|
|
In: The Journal of Purdue Undergraduate Research (2021)
|
|
BASE
|
|
Show details
|
|
11 |
Transliteracy Sponsorscapes: Potential for Attunement and Diffraction in Literacy Learning
|
|
|
|
BASE
|
|
Show details
|
|
|
|