Sebastian Ruder

AUGUST 15, 2021

Cross-lingual transfer and multilingual NLP Beyond machine translation, I enjoyed the following papers on cross-lingual transfer and multilingual NLP: COSY: COunterfactual SYntax for Cross-Lingual Understanding. They find that incorporating dependencies is more effective than using POS tags.

NLP 52

NLP Explainability Neural Network Natural Language Processing 52

AWS Machine Learning Blog

JULY 3, 2023

Many businesses have diverse global users and need to translate text to enable cross-lingual communication between them. Amazon Translate allows tag modifications, which allows you to specify what text should not be translated. This is a manual, slow, and expensive human effort.

Automation 69

Automation ML Machine Learning Algorithm 69

Google Research AI blog

DECEMBER 7, 2022

Committees Organizing Committee includes: Eunsol Choi , Imed Zitouni Senior Program Committee includes: Don Metzler , Eunsol Choi , Bernd Bohnet , Slav Petrov , Kenthon Lee Papers Transforming Sequence Tagging Into A Seq2Seq Task Karthik Raman , Iftekhar Naim , Jiecao Chen , Kazuma Hashimoto , Kiran Yalasangi , Krishna Srinivasan On the Limitations (..)

Natural Language Processing 52

Natural Language Processing NLP BERT Large Language Models 52

AssemblyAI

DECEMBER 7, 2023

For example, the model can seamlessly convert a dialogue from Mandarin to English, facilitating cross-lingual communication. Alternatively, an analysis tag indicates other types of audio processing, ensuring that the model can differentiate between direct transcription and broader audio analysis.

Explainability 278

Explainability Large Language Models AI AI 278

Sebastian Ruder

NOVEMBER 14, 2022

Cross-lingual performance prediction [42] could be used to estimate performance for a broader set of languages. Cross-lingual parameter-efficient transfer learning is not restricted to adapters but can take other forms [140] such as sparse sub-networks [141]. Unsupervised Cross-lingual Representation Learning at Scale.

Natural Language Processing 52

Natural Language Processing NLP Computational Linguistics AI 52

Marktechpost

APRIL 29, 2024

This benchmark comprises 20 diversified tasks, including named-entity recognition, part-of-speech tagging, question-answering, semantic textual similarity, and classification. The MLMs include French generalist models, cross-lingual generalist models, French biomedical models, and an English biomedical model.

NLP 105

NLP Automation ML Large Language Models 105

The MLOps Blog

JANUARY 25, 2023

This model can produce language-agnostic cross-lingual sentence embeddings for 109 languages. For example, “I love being ignored” may be tagged as a negative example, and “I can be very ambitious” can be tagged as a positive example. This data is then used to train models and make inferences.

BERT 52

BERT Natural Language Processing ML Deep Learning 52