#lowresourcelanguages search results

Introducing maiBERT - the first BERT-based language model for Maithili! Despite being spoken by millions in Nepal & India,Maithili has been underserved in NLP. Our model achieves 87.02%accuracy on news classification, outperforming existing regional models. #LowResourceLanguages

Rocker_Ritesh's tweet image. Introducing maiBERT - the first BERT-based language model for Maithili! Despite being spoken by millions in Nepal & India,Maithili has been underserved in NLP. Our model achieves 87.02%accuracy on news classification, outperforming existing regional models. #LowResourceLanguages
Rocker_Ritesh's tweet image. Introducing maiBERT - the first BERT-based language model for Maithili! Despite being spoken by millions in Nepal & India,Maithili has been underserved in NLP. Our model achieves 87.02%accuracy on news classification, outperforming existing regional models. #LowResourceLanguages

The first issue of Computational Linguistics in Bulgaria is out! The issue features recent research on the application of NLP & LLMs for Bulgarian and other LR languages. Read & download: jclib.dcl.bas.bg/current-issue/. #ComputationalLinguistics #NLP #LowResourceLanguages

CLinBulgaria's tweet image. The first issue of Computational Linguistics in Bulgaria is out! The issue features recent research on the application of NLP & LLMs for Bulgarian and other LR languages. 
Read & download: jclib.dcl.bas.bg/current-issue/.
#ComputationalLinguistics #NLP #LowResourceLanguages

Poster session @DeepIndaba I’m thankful for the chance to share my work, receive feedback, and connect with amazing minds across Africa and beyond🌍 #NLP #Efik #lowresourcelanguages

mb_awak's tweet image. Poster session @DeepIndaba 

I’m thankful for the chance to share my work, receive feedback, and connect with amazing minds across Africa and beyond🌍

#NLP #Efik #lowresourcelanguages

This verse displayed at Trinity College Dublin felt like an inspiring reminder of what the speech and language technology community can aim for. Support inclusivity for under-represented languages. #NLP #lowResourceLanguages #LLMs

boldingbroke's tweet image. This verse displayed at Trinity College Dublin felt like an inspiring reminder of what the speech and language technology community can aim for. Support inclusivity for under-represented languages. #NLP #lowResourceLanguages #LLMs

@eamt2020 #MT as an assistant for comprehension in the Swahili - English combination!!! This is my case with Dutch and MT 😬 Great presentation by @MikelForcada #lowresourcelanguages Have a look at the proceedings of the conference. They are free!!!!

AnaGuerberof's tweet image. @eamt2020 #MT as an assistant for comprehension in the Swahili - English combination!!!
This is my case with Dutch and MT 😬
Great presentation by @MikelForcada #lowresourcelanguages 
Have a look at the proceedings of the conference. They are free!!!!

📢 Today, our colleagues @SaludJZ and @garciacumbreras presented the keynote "Corpus compilation for #NLP shared tasks: the Spanish case" at the first International Conference on Speech and Language Technologies for Low-resource Languages #SPELLL2022 #lowresourcelanguages

NLP_SINAI's tweet image. 📢 Today, our colleagues @SaludJZ and @garciacumbreras presented the keynote "Corpus compilation for #NLP shared tasks: the Spanish case" at the first International Conference on Speech and Language Technologies for Low-resource Languages  #SPELLL2022 #lowresourcelanguages

Investigating how Claude, a large language model, can enhance translation capabilities especially for languages with low resources. #MachineTranslation #SyntheticData #LowresourceLanguages

GoatstackAI's tweet image. Investigating how Claude, a large language model, can enhance translation capabilities especially for languages with low resources. #MachineTranslation #SyntheticData #LowresourceLanguages

Enhancing Reasoning Capabilities in Low-Resource Language Models through Efficient Model Merging #LowResourceLanguages #AIResearch #ModelMerging #LanguageModels #ReasoningCapabilities itinai.com/enhancing-reas…

vlruso's tweet image. Enhancing Reasoning Capabilities in Low-Resource Language Models through Efficient Model Merging

#LowResourceLanguages #AIResearch #ModelMerging #LanguageModels #ReasoningCapabilities

itinai.com/enhancing-reas…

We found scaling the self-supervised model not only boosts accuracy, but also helps with #sampleefficiency. We were able to achieve Whisper level WERs by training on 200x less supervised data than they used, which will help particularly with #lowresourcelanguages 🌏.


Our approach, detailed in arxiv.org/abs/2505.18383 focuses on creating rich datasets that deeply embed: 1️⃣ Local Languages & Dialects (e.g., Arabizi, specific scripts) 2️⃣ Unique Cultural Heritage 3️⃣ Core Cultural Values #LowResourceLanguages #NLP


💡 Open-source models showed strong performance overall, but struggled with simile interpretation in low-resource languages. This highlights the challenge of building truly multilingual and culturally aware AI. #MultilingualAI #LowResourceLanguages


In their latest work, Marivate et al. explore Setswana and Sepedi—two languages spoken in South Africa and Botswana—by creating news headline datasets. Read more: arxiv.org/pdf/2004.13842 #AfricanNLP #LowResourceLanguages #Leyu

Leyu_Ai's tweet image. In their latest work, Marivate et al. explore Setswana and Sepedi—two languages spoken in South Africa and Botswana—by creating news headline datasets.
Read more: arxiv.org/pdf/2004.13842 

#AfricanNLP #LowResourceLanguages #Leyu

This groundbreaking work has already improved translation accuracy, helping open up the Web for speakers of these languages. #LesanAI #LowResourceLanguages #Crowdsourcing #LanguageData #DataForGood


Here’s an AI moat: Collect data that’s never been collected. #lowresourcelanguages


📖Recommended Reading [Large Language Models as Kuwaiti Annotators] By @HanaaOstad This study addresses a critical challenge in #NLP for #LowResourceLanguages, particularly the scarcity of annotated datasets 👉 Read it here: mdpi.com/2504-2289/9/2/…

BDCC_MDPI's tweet image. 📖Recommended  Reading
[Large Language Models as Kuwaiti Annotators]
By @HanaaOstad 

This study addresses a critical challenge in #NLP for #LowResourceLanguages, particularly the scarcity of annotated datasets

👉 Read it here: 
mdpi.com/2504-2289/9/2/…
BDCC_MDPI's tweet image. 📖Recommended  Reading
[Large Language Models as Kuwaiti Annotators]
By @HanaaOstad 

This study addresses a critical challenge in #NLP for #LowResourceLanguages, particularly the scarcity of annotated datasets

👉 Read it here: 
mdpi.com/2504-2289/9/2/…

Third edition of the International Conference on Speech & Language Technology for #LowresourceLanguages (#SPELLL) #NLProc #NLP spelll.org

BharathirajaAkr's tweet image. Third edition of the International Conference on Speech & Language Technology for #LowresourceLanguages (#SPELLL) #NLProc
#NLP
spelll.org

The first issue of Computational Linguistics in Bulgaria is out! The issue features recent research on the application of NLP & LLMs for Bulgarian and other LR languages. Read & download: jclib.dcl.bas.bg/current-issue/. #ComputationalLinguistics #NLP #LowResourceLanguages

CLinBulgaria's tweet image. The first issue of Computational Linguistics in Bulgaria is out! The issue features recent research on the application of NLP & LLMs for Bulgarian and other LR languages. 
Read & download: jclib.dcl.bas.bg/current-issue/.
#ComputationalLinguistics #NLP #LowResourceLanguages

Introducing maiBERT - the first BERT-based language model for Maithili! Despite being spoken by millions in Nepal & India,Maithili has been underserved in NLP. Our model achieves 87.02%accuracy on news classification, outperforming existing regional models. #LowResourceLanguages

Rocker_Ritesh's tweet image. Introducing maiBERT - the first BERT-based language model for Maithili! Despite being spoken by millions in Nepal & India,Maithili has been underserved in NLP. Our model achieves 87.02%accuracy on news classification, outperforming existing regional models. #LowResourceLanguages
Rocker_Ritesh's tweet image. Introducing maiBERT - the first BERT-based language model for Maithili! Despite being spoken by millions in Nepal & India,Maithili has been underserved in NLP. Our model achieves 87.02%accuracy on news classification, outperforming existing regional models. #LowResourceLanguages

Poster session @DeepIndaba I’m thankful for the chance to share my work, receive feedback, and connect with amazing minds across Africa and beyond🌍 #NLP #Efik #lowresourcelanguages

mb_awak's tweet image. Poster session @DeepIndaba 

I’m thankful for the chance to share my work, receive feedback, and connect with amazing minds across Africa and beyond🌍

#NLP #Efik #lowresourcelanguages

Low-resource languages deserve more attention in translation tools. Supporting these languages can foster inclusion and cultural preservation. Which language do you think needs better representation? #LowResourceLanguages #TranslationInclusivity #CulturalPreservation


Our approach, detailed in arxiv.org/abs/2505.18383 focuses on creating rich datasets that deeply embed: 1️⃣ Local Languages & Dialects (e.g., Arabizi, specific scripts) 2️⃣ Unique Cultural Heritage 3️⃣ Core Cultural Values #LowResourceLanguages #NLP


We’re proud to keep pushing for open, ethical, and African-led AI. #AfricanNLP #LowResourceLanguages #OpenScience #NAACL2025 #DSFSI 4/4


In their latest work, Marivate et al. explore Setswana and Sepedi—two languages spoken in South Africa and Botswana—by creating news headline datasets. Read more: arxiv.org/pdf/2004.13842 #AfricanNLP #LowResourceLanguages #Leyu

Leyu_Ai's tweet image. In their latest work, Marivate et al. explore Setswana and Sepedi—two languages spoken in South Africa and Botswana—by creating news headline datasets.
Read more: arxiv.org/pdf/2004.13842 

#AfricanNLP #LowResourceLanguages #Leyu

- Frugal learning (learning resources, computational resources) - Explainability of machine learning approaches - Contributions and limitations of LLMs - Speech recognition and synthesis - Model evaluation and benchmarking #NLP #Africa #LowResourceLanguages


- Data collection and curation - Evaluation & impact of biases introduced during collection and annotation - Integration of multi-modal data (text and audio) - Learning in a context of noisy and low-resource data #NLP #Africa #LowResourceLanguages


No results for "#lowresourcelanguages"

The first issue of Computational Linguistics in Bulgaria is out! The issue features recent research on the application of NLP & LLMs for Bulgarian and other LR languages. Read & download: jclib.dcl.bas.bg/current-issue/. #ComputationalLinguistics #NLP #LowResourceLanguages

CLinBulgaria's tweet image. The first issue of Computational Linguistics in Bulgaria is out! The issue features recent research on the application of NLP & LLMs for Bulgarian and other LR languages. 
Read & download: jclib.dcl.bas.bg/current-issue/.
#ComputationalLinguistics #NLP #LowResourceLanguages

Introducing maiBERT - the first BERT-based language model for Maithili! Despite being spoken by millions in Nepal & India,Maithili has been underserved in NLP. Our model achieves 87.02%accuracy on news classification, outperforming existing regional models. #LowResourceLanguages

Rocker_Ritesh's tweet image. Introducing maiBERT - the first BERT-based language model for Maithili! Despite being spoken by millions in Nepal & India,Maithili has been underserved in NLP. Our model achieves 87.02%accuracy on news classification, outperforming existing regional models. #LowResourceLanguages
Rocker_Ritesh's tweet image. Introducing maiBERT - the first BERT-based language model for Maithili! Despite being spoken by millions in Nepal & India,Maithili has been underserved in NLP. Our model achieves 87.02%accuracy on news classification, outperforming existing regional models. #LowResourceLanguages

Poster session @DeepIndaba I’m thankful for the chance to share my work, receive feedback, and connect with amazing minds across Africa and beyond🌍 #NLP #Efik #lowresourcelanguages

mb_awak's tweet image. Poster session @DeepIndaba 

I’m thankful for the chance to share my work, receive feedback, and connect with amazing minds across Africa and beyond🌍

#NLP #Efik #lowresourcelanguages

📢 Today, our colleagues @SaludJZ and @garciacumbreras presented the keynote "Corpus compilation for #NLP shared tasks: the Spanish case" at the first International Conference on Speech and Language Technologies for Low-resource Languages #SPELLL2022 #lowresourcelanguages

NLP_SINAI's tweet image. 📢 Today, our colleagues @SaludJZ and @garciacumbreras presented the keynote "Corpus compilation for #NLP shared tasks: the Spanish case" at the first International Conference on Speech and Language Technologies for Low-resource Languages  #SPELLL2022 #lowresourcelanguages

This verse displayed at Trinity College Dublin felt like an inspiring reminder of what the speech and language technology community can aim for. Support inclusivity for under-represented languages. #NLP #lowResourceLanguages #LLMs

boldingbroke's tweet image. This verse displayed at Trinity College Dublin felt like an inspiring reminder of what the speech and language technology community can aim for. Support inclusivity for under-represented languages. #NLP #lowResourceLanguages #LLMs

Enhancing Reasoning Capabilities in Low-Resource Language Models through Efficient Model Merging #LowResourceLanguages #AIResearch #ModelMerging #LanguageModels #ReasoningCapabilities itinai.com/enhancing-reas…

vlruso's tweet image. Enhancing Reasoning Capabilities in Low-Resource Language Models through Efficient Model Merging

#LowResourceLanguages #AIResearch #ModelMerging #LanguageModels #ReasoningCapabilities

itinai.com/enhancing-reas…

Investigating how Claude, a large language model, can enhance translation capabilities especially for languages with low resources. #MachineTranslation #SyntheticData #LowresourceLanguages

GoatstackAI's tweet image. Investigating how Claude, a large language model, can enhance translation capabilities especially for languages with low resources. #MachineTranslation #SyntheticData #LowresourceLanguages

In their latest work, Marivate et al. explore Setswana and Sepedi—two languages spoken in South Africa and Botswana—by creating news headline datasets. Read more: arxiv.org/pdf/2004.13842 #AfricanNLP #LowResourceLanguages #Leyu

Leyu_Ai's tweet image. In their latest work, Marivate et al. explore Setswana and Sepedi—two languages spoken in South Africa and Botswana—by creating news headline datasets.
Read more: arxiv.org/pdf/2004.13842 

#AfricanNLP #LowResourceLanguages #Leyu

📖Recommended Reading [Large Language Models as Kuwaiti Annotators] By @HanaaOstad This study addresses a critical challenge in #NLP for #LowResourceLanguages, particularly the scarcity of annotated datasets 👉 Read it here: mdpi.com/2504-2289/9/2/…

BDCC_MDPI's tweet image. 📖Recommended  Reading
[Large Language Models as Kuwaiti Annotators]
By @HanaaOstad 

This study addresses a critical challenge in #NLP for #LowResourceLanguages, particularly the scarcity of annotated datasets

👉 Read it here: 
mdpi.com/2504-2289/9/2/…
BDCC_MDPI's tweet image. 📖Recommended  Reading
[Large Language Models as Kuwaiti Annotators]
By @HanaaOstad 

This study addresses a critical challenge in #NLP for #LowResourceLanguages, particularly the scarcity of annotated datasets

👉 Read it here: 
mdpi.com/2504-2289/9/2/…

Third edition of the International Conference on Speech & Language Technology for #LowresourceLanguages (#SPELLL) #NLProc #NLP spelll.org

BharathirajaAkr's tweet image. Third edition of the International Conference on Speech & Language Technology for #LowresourceLanguages (#SPELLL) #NLProc
#NLP
spelll.org

We launch our Soundcloud page, checkout the first Podcast: Izindaba-Tindzaba: Machine learning news categorization for isiZulu and Siswati #NotebookLM soundcloud.com/dsfsi/podcast-… #AfricanNLP #LowResourceLanguages @UPTuks

DSFSI_Research's tweet image. We launch our Soundcloud page, checkout the first Podcast:  

Izindaba-Tindzaba: Machine learning news categorization for isiZulu and Siswati  #NotebookLM soundcloud.com/dsfsi/podcast-… #AfricanNLP #LowResourceLanguages @UPTuks

@eamt2020 #MT as an assistant for comprehension in the Swahili - English combination!!! This is my case with Dutch and MT 😬 Great presentation by @MikelForcada #lowresourcelanguages Have a look at the proceedings of the conference. They are free!!!!

AnaGuerberof's tweet image. @eamt2020 #MT as an assistant for comprehension in the Swahili - English combination!!!
This is my case with Dutch and MT 😬
Great presentation by @MikelForcada #lowresourcelanguages 
Have a look at the proceedings of the conference. They are free!!!!

Loading...

Something went wrong.


Something went wrong.


United States Trends