B-MRC

MRC approach for Aspect-based Sentiment Analysis (ABSA)

Paper: Bidirectional Machine Reading Comprehension for Aspect Sentiment Triplet Extraction

Dataset: https://github.com/xuuuluuu/SemEval-Triplet-data

Usage

Prepare data:

python data_process.py --data_path data/14lap --version bidirectional (unidirectional)

Arguments:
    --data_path :       Path to the dataset
    --version   :       Optional version: unidirectional (A2O) and bidirectional (A2O + O2A) 
                        (default = 'bidirectiona')
                        Choices=['uni', 'bi', 'unidirectional', 'bidirectional']

python make_data_dual --data_path data/14lap/preprocess --version bidirectional (unidirectional)

Arguments:
    --data_path :       Path to the dataset
    --version   :       Optional version: unidirectional (A2O) and bidirectional (A2O + O2A)
                        (default = 'bidirectiona')
                        Choices=['uni', 'bi', 'unidirectional', 'bidirectional']

python make_data_standard --data_path data/14lab/pair --output_path ./data/14lap/preprocess

Arguments:
    --data_path  :      Path to the dataset
    --output_path:      Path to the output data

Training:

python main.py \
    --version bidirectional (unidirectional) \
    --data_path ./data/14lap/preprocess/ \
    --mode train \
    --model_type bert-base-uncased \
    --epoch_num 40 \
    --batch_size 4 \
    --learning_rate 1e-3

MRC approach for Aspect-based Sentiment Analysis (ABSA)

Related tags

Overview

B-MRC

Usage

Owner

Phuc Phan

Code for the paper "BERT Loses Patience: Fast and Robust Inference with Early Exit".

A python script that will use hydra to get user and password to login to ssh, ftp, and telnet

apple's universal binaries BUT MUCH WORSE (PRACTICAL SHITPOST) (NOT PRODUCTION READY)

Text Classification Using LSTM

Official implementation of MLP Singer: Towards Rapid Parallel Korean Singing Voice Synthesis

Pipelines de datos, 2021.

Simple telegram bot to convert files into direct download link.you can use telegram as a file server 🪁

Text-to-Speech for Belarusian language

aMLP Transformer Model for Japanese

Ptorch NLU, a Chinese text classification and sequence annotation toolkit, supports multi class and multi label classification tasks of Chinese long text and short text, and supports sequence annotation tasks such as Chinese named entity recognition, part of speech tagging and word segmentation.

SpeechBrain is an open-source and all-in-one speech toolkit based on PyTorch.

Code for using and evaluating SpanBERT.

The Sudachi synonym dictionary in Solar format.

This is an incredibly powerful calculator that is capable of many useful day-to-day functions.

Train 🤗transformers with DeepSpeed: ZeRO-2, ZeRO-3

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

This is the code for the EMNLP 2021 paper AEDA: An Easier Data Augmentation Technique for Text Classification

MILES is a multilingual text simplifier inspired by LSBert - A BERT-based lexical simplification approach proposed in 2018. Unlike LSBert, MILES uses the bert-base-multilingual-uncased model, as well as simple language-agnostic approaches to complex word identification (CWI) and candidate ranking.

This is the 25 + 1 year anniversary version of the 1995 Rachford-Rice contest

ALIbaba's Collection of Encoder-decoders from MinD (Machine IntelligeNce of Damo) Lab