CoNLL-English NER Task

en | ch

Motivation

Course Project
review the pytorch framework and sequence-labeling task
practice using the transformers of Huggingface

Dataset Introduction

A train set, a test set and a validation set in the data file

-DOCSTART- -X- O O
-sentnce- -pos- -Chuck- -Entity-

Project Structure

-data  # source data
-emb # BERT model files

-util
    -dataTool.py  # data interface
    -model.py
    -trainer.py  # train and evaluate

config.py  # parameters in the project
run.py
requirement.txt

EDA.ipynb # exploratory data analasis, 
          # which aims to confirm the hyper-params in the trials

Coding Pattern

For keeping the convenience and simplicity of experiments,
decouple the model into two units: encoder and tagger

model ==> encoder + tagger

In such a way, encoder extracts the context and linguistit features,
which will be received by tagger to output BIO tags.

Usage

chmod 755 deploy
./deploy

./gpu n  # monitor the GPU (refresh every n seconds)
./run  # start

Baseline Performance (1 ep | macro)

Model	Precision	Recall	F1
Bert-CRF	0.71	0.68	0.69
Bert-softmax	-	-	-
Bert-BiLSTM-CRF	-	-	-
Bert-BiLSTM-softmax	-	-	-

Optimization

cost sensitive learning or drop the few classes
dropout to improve the generalization performance
different backbone structures
DDP training --> large GPU caches for a large batch_size
more epochs --> schedule the learning rate dynamically while training

CoNLL-English NER Task (NER in English)

Related tags

Overview

CoNLL-English NER Task

Motivation

Dataset Introduction

Project Structure

Coding Pattern

Usage

Baseline Performance (1 ep | macro)

Optimization

Owner

Kevin

[WWW 2021 GLB] New Benchmarks for Learning on Non-Homophilous Graphs

Search Git commits in natural language

Conditional probing: measuring usable information beyond a baseline

Code for text augmentation method leveraging large-scale language models

Materials (slides, code, assignments) for the NYU class I teach on NLP and ML Systems (Master of Engineering).

Search with BERT vectors in Solr and Elasticsearch

A simple Flask site that allows users to create, update, and delete posts in a database, as well as perform basic NLP tasks on the posts.

Behavioral Testing of Clinical NLP Models

[ICCV 2021] Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification

The following links explain a bit the idea of semantic search and how search mechanisms work by doing retrieve and rerank

FastFormers - highly efficient transformer models for NLU

Search msDS-AllowedToActOnBehalfOfOtherIdentity

The official implementation of "BERT is to NLP what AlexNet is to CV: Can Pre-Trained Language Models Identify Analogies?, ACL 2021 main conference"

TPlinker for NER 中文/英文命名实体识别

The official code for “DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction”, ACM MM, Oral Paper, 2021.

Officile code repository for "A Game-Theoretic Perspective on Risk-Sensitive Reinforcement Learning"

Coreference resolution for English, German and Polish, optimised for limited training data and easily extensible for further languages

Unsupervised text tokenizer for Neural Network-based text generation.

Russian GPT3 models.

A crowdsourced dataset of dialogues grounded in social contexts involving utilization of commonsense.