Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · MilaNLProc

xlm-emo-t

xlm-emo-t is an XLM-RoBERTa text-classification model from MilaNLProc. Hub tags include emotion and multilingual, and the model card describes it as a fine-tuned version of the XLM-T model intended for research.

Publisher
MilaNLProc
Task
text-classification
Model type
xlm-roberta
License
Unknown
Library
transformers
Publication status
Approved for indexing

Model overview

MilaNLProc publishes xlm-emo-t as a text-classification model on the Transformers stack. Captured config identifies XLMRobertaForSequenceClassification with an xlm-roberta model type. Hub tags include emotion, emotion-analysis, and multilingual. According to the model card, this is a fine-tuned version of XLM-T, and the captured abstract discusses collecting emotion detection datasets across 19 languages.

Recorded capabilities

XLM-RoBERTa classification config

The captured configuration identifies XLMRobertaForSequenceClassification with an xlm-roberta model type.

Publisher XLM-T fine-tune note

The model card says this model is the fine-tuned version of the XLM-T model.

Research intended use

The model card states the model is intended as a research output for research communities, with AI researchers as primary intended users.

Use cases in the source record

  • Research-oriented emotion classification in text, as described on the model card.

Limitations and unknowns

  • No evaluation results were extracted from this record.
  • No parameter count was extracted from this record.
  • No license value was extracted from this record.
  • The hub multilingual tag and the card's 19-language dataset collection claim are not independently verified language-support inventories.
  • Provider state is historical snapshot data, not independently refreshed current availability.
  • XLM-T fine-tune wording, intended-use limits, and dataset-license referrals come from the publisher model card and have not been independently verified by Ethen.

Source and provenance

Source: MilaNLProc/xlm-emo-t

Captured: Unknown. Processed: 2026-09-07T19:34:34.161989+00:00.

Federico Bianchi • Debora Nozza • Dirk Hovy Abstract Detecting emotion in text allows social and computational scientists to study how people behave and react to online events. However, developing these tools for different languages requires data that is not always available. This paper collects the available emotion detection datasets across 19 languages. We train a multilingual emotion prediction model for social media data, XLM-EMO. The model shows competitive performance in a zero-shot setting, suggesting it is helpful in the context of low-resource languages. We release our model to the community so that interested researchers…

F001F002F003F004F005F006F007F008F009F010F011F012F013