Julian Eisenschlos
  • Home
  • About
  • Papers
  • Talks
  • GitHub
  • LinkedIn
Subscribe
Tagged

Natural Language Processing

A collection of 3 posts

Learning to Reason Over Tables from Less Data
Natural Language Processing

Learning to Reason Over Tables from Less Data

In "Understanding tables with intermediate pre-training", published in Findings of EMNLP 2020, we introduce the first pre-training tasks customized for table parsing, enabling models to learn better, faster and from less data.

  • Julian Eisenschlos
Julian Eisenschlos Apr 10, 2021 • 7 min read
Efficient multi-lingual language model fine-tuning
Natural Language Processing

Efficient multi-lingual language model fine-tuning

Our latest paper studies multilingual text classification and introduces MultiFiT, a novel method based on ULMFiT. MultiFiT, trained on 100 labeled documents in the target language, outperforms multi-lingual BERT, and the LASER algorithm—even though LASER requires a corpus of parallel texts.

  • Julian Eisenschlos
Julian Eisenschlos Sep 10, 2019 • 10 min read
Text Classification with TensorFlow Estimators
Natural Language Processing

Text Classification with TensorFlow Estimators

Throughout this post we will explain how to classify text using Estimators, Datasets and Feature Columns, with a scalable high-level API in TensorFlow.

  • Julian Eisenschlos
Julian Eisenschlos Mar 7, 2018 • 14 min read
Julian Eisenschlos © 2021
Powered by Ghost