home.social

#mmnlg — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #mmnlg, aggregated by home.social.

  1. After some technical difficulties we will hear from Michela Lorandi on "Data-to-text Generation for Severely Under-Resourced Languages with GPT-3.5: A bit of Help Needed from Google Translate" at #WebNLG2023

    #MMNLG #SIGDIALxINLG2023

  2. After some technical difficulties we will hear from Michela Lorandi on "Data-to-text Generation for Severely Under-Resourced Languages with GPT-3.5: A bit of Help Needed from Google Translate" at #WebNLG2023

    #MMNLG #SIGDIALxINLG2023

  3. After some technical difficulties we will hear from Michela Lorandi on "Data-to-text Generation for Severely Under-Resourced Languages with GPT-3.5: A bit of Help Needed from Google Translate" at #WebNLG2023

    #MMNLG #SIGDIALxINLG2023

  4. Up next is Nalin Kumar presenting the Charles University Prague system for #WebNLG2023 "Better Translation + Split and Generate for Multilingual RDF-to-Text"

    #MMNLG #SIGDIALxINLG2023

    Lots of the "silver standard" training data was noisy, so the team used a state of the art MT system to retranslate some of the texts from English.

  5. Up next is Nalin Kumar presenting the Charles University Prague system for #WebNLG2023 "Better Translation + Split and Generate for Multilingual RDF-to-Text"

    #MMNLG #SIGDIALxINLG2023

    Lots of the "silver standard" training data was noisy, so the team used a state of the art MT system to retranslate some of the texts from English.

  6. Up next is Nalin Kumar presenting the Charles University Prague system for #WebNLG2023 "Better Translation + Split and Generate for Multilingual RDF-to-Text"

    #MMNLG #SIGDIALxINLG2023

    Lots of the "silver standard" training data was noisy, so the team used a state of the art MT system to retranslate some of the texts from English.

  7. Now Liam Cripwell presents an overview of the #WebNLG2023 challenge. The challenge began in 2017 with RDF->English generation, in 2020 added Russian and a #SemanticParsing track, and this year focused on #LowResourceLanguages looking at #Breton, #Welsh, #Irish, #Maltese, and #Russian.

    #MMNLG #SIGDIALxINLG2023

  8. Now Liam Cripwell presents an overview of the #WebNLG2023 challenge. The challenge began in 2017 with RDF->English generation, in 2020 added Russian and a #SemanticParsing track, and this year focused on #LowResourceLanguages looking at #Breton, #Welsh, #Irish, #Maltese, and #Russian.

    #MMNLG #SIGDIALxINLG2023

  9. Now Liam Cripwell presents an overview of the #WebNLG2023 challenge. The challenge began in 2017 with RDF->English generation, in 2020 added Russian and a #SemanticParsing track, and this year focused on #LowResourceLanguages looking at #Breton, #Welsh, #Irish, #Maltese, and #Russian.

    #MMNLG #SIGDIALxINLG2023

  10. The next keynote at #MMNLG is from Sandro Pezzele on "Adaptation in the Realm of Visually Grounded Language: Of Speakers, Models, and Tasks" here at #SIGDIALxINLG2023.

  11. At the #MMNLG workshop today at #SIGDIALxINLG2023, currently enjoying Dimitra Gkatzia's keynote about "Dealing with Data Challenges in Low-Resource NLG"

    She began by highlighting ways in which NLG can be low-resource: it's not just about languages, but domains can be low-resource as well, and even our "large" #DataToText datasets are small by modern #NLP standards.