nlp · Veritable Tech Blog

2021

May 1

Text Analysis using Julia

Apr 4

[Notes] Gradient Checkpointing with BERT

Mar 18

[Paper] Adafactor: Adaptive Learning Rates with Sublinear Memory Cost

Feb 14

[Paper] Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control

Jan 18

Reducing the SentencePiece Vocabulary Size of Pretrained NLP Models

2020

Aug 19

[Paper] Language-agnostic BERT Sentence Embedding

Aug 5

[Competition] Jigsaw Multilingual Toxic Comment Classification

Jul 23

[Paper] Training Question Answering Models From Synthetic Data

Jun 28

Using Julia to Do Whole Word Masking

Jun 16

[Failure Report] Distill Fine-tuned Transformers into Recurrent Neural Networks

Feb 13

TensorFlow 2.1 with TPU in Practice

2019

Dec 17

Create a Customized Text Annotation Tool in Two Days - Part 2

Dec 16

Create a Customized Text Annotation Tool in Two Days - Part 1

Nov 28

Fine-tuning BERT for Similarity Search

Sep 24

Zero Shot Cross-Lingual Transfer with Multilingual BERT

Aug 14

Customizing Spacy Sentence Segmentation

Aug 4

[Notes] Jigsaw Unintended Bias in Toxicity Classification

Apr 24

Detecting Chinese Characters in Unicode Strings

Feb 15

Multilingual Similarity Search Using Pretrained Bidirectional LSTM Encoder

Feb 10

News Topic Similarity Measure using Pretrained BERT Model

2018

Dec 7

Use TextRank to Extract Most Important Sentences in Article

Nov 7

Implementing Beam Search - Part 2

Nov 5

Implementing Beam Search - Part 1

Oct 13

[Notes] Neural Language Models with PyTorch

Mar 24

[Review] Kaggle Toxic Comment Classification Challenge

Feb 27

Analyzing Tweets with R