A sample pytorch Implementation of ACL 2021 research paper "Learning Span-Level Interactions for Aspect Sentiment Triplet Extraction".

Related tags

Overview

Span-ASTE-Pytorch

This repository is a pytorch version that implements Ali's ACL 2021 research paper Learning Span-Level Interactions for Aspect Sentiment Triplet Extraction .

🤗 The original repository of the paper is based on the allennlp implementation
🤗 Thanks to Ali's dataset SemEval-Triplet-data that was open sourced, so that we can use it for research

Usage

🍉 Download dataset from here SemEval-Triplet-data, ASTE-Data-V2-EMNLP2020 is used in my repository
🥭 Download GloVe pre-trained word vectors,
🍑 Convert glove_input_file in GloVe format to word2vec format and write it to `word2vec_output_file

from gensim.scripts.glove2word2vec import glove2word2vec

glove2word2vec("path/to/dir/glove_input_file", "path/to/dir/word2vec_output_file")

🍓 train the span-aste model

python train.py --glove_word2vector vector_cache/w2v.txt \
          --dataset data/ASTE-Data-V2-EMNLP2020/15res/ \
          --output_path output/

🍇 test the span-aste model

python test.py --model_path  \
          --glove_word2vector corpus/w2v.txt \
          --dataset data/ASTE-Data-V2-EMNLP2020/15res/\
          -model `path/to/model/model.pkl`

Comments

About the results

For this dataset 15res, the bilstm version(your code) i got the best f1 in the eval is 0.6382,the paper is 0.6426, and the bert version i got the best f1 in the eval is 0.6564, the paper is 0.7075. I can't get close to the results of the paper, can you give me some suggestions? Thank you very much!

opened by codewen77 7
Questions about the BERT version of span-aste.

Thank you very much for your open source pytorch version of span-aste network code. I replaced the encoder of LSTM version span-aste with BERT. However, the accuracy, recall and F1 score during training and verification are all 0, and I could not find the error. Do you have a plan to develop the BERT version span-aste? Or could you tell me the way to change the model to BERT encoder?

opened by zlyoung 2
请问大家可以稍微帮我解释一下这段代码的含义吗，我不太理解，谢谢

self.bucket_bins = [0, 1, 2, 3, 4, 5, 7, 8, 15, 16, 31, 32, 63, 64]
self.span_width_embedding = nn.Embedding(len(self.bucket_bins), span_width_embedding_dim)

def bucket_embedding(self, width, device): em = [ix for ix, v in enumerate(self.bucket_bins) if width >= v][0] return self.span_width_embedding(torch.LongTensor([em]).to(device))

model.py文件下的bucket_embedding函数，应当是对于Span的长度feature进行编码的。但是em得到的数值难道不是永远是0吗，这样也没有用到长度特征呀。我想知道bucket_embedding到底是要实现什么功能，谢谢各位。

opened by tongzeliang 1

This repository contains the code, data, and models of the paper titled "XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages" published in Findings of the Association for Computational Linguistics: ACL 2021.

XL-Sum This repository contains the code, data, and models of the paper titled "XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Lang

190 Jan 3, 2023

Data and Code for ACL 2021 Paper "Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning"

Introduction Code and data for ACL 2021 Paper "Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning". We cons

81 Dec 27, 2022

Code for ACL'2021 paper WARP 🌀 Word-level Adversarial ReProgramming

Code for ACL'2021 paper WARP 🌀 Word-level Adversarial ReProgramming. Outperforming `GPT-3` on SuperGLUE Few-Shot text classification.

75 Nov 6, 2022

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

Detectron is deprecated. Please see detectron2, a ground-up rewrite of Detectron in PyTorch. Detectron Detectron is Facebook AI Research's software sy

25.5k Jan 7, 2023

A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)

MMF is a modular framework for vision and language multimodal research from Facebook AI Research. MMF contains reference implementations of state-of-t

5.1k Jan 4, 2023

The official implementation for ACL 2021 "Challenges in Information Seeking QA: Unanswerable Questions and Paragraph Retrieval".

Code for "Challenges in Information Seeking QA: Unanswerable Questions and Paragraph Retrieval" (ACL 2021, Long) This is the repository for baseline m

25 Oct 30, 2022

The GitHub repository for the paper: “Time Series is a Special Sequence: Forecasting with Sample Convolution and Interaction“.

SCINet This is the original PyTorch implementation of the following work: Time Series is a Special Sequence: Forecasting with Sample Convolution and I

386 Jan 1, 2023

[NAACL & ACL 2021] SapBERT: Self-alignment pretraining for BERT.

SapBERT: Self-alignment pretraining for BERT This repo holds code for the SapBERT model presented in our NAACL 2021 paper: Self-Alignment Pretraining

104 Dec 7, 2022

PIGLeT: Language Grounding Through Neuro-Symbolic Interaction in a 3D World [ACL 2021]

piglet PIGLeT: Language Grounding Through Neuro-Symbolic Interaction in a 3D World [ACL 2021] This repo contains code and data for PIGLeT. If you like

51 Oct 8, 2022

A sample pytorch Implementation of ACL 2021 research paper "Learning Span-Level Interactions for Aspect Sentiment Triplet Extraction".

Related tags

Overview

Span-ASTE-Pytorch

Usage

You might also like...

This repository contains the code, data, and models of the paper titled "XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages" published in Findings of the Association for Computational Linguistics: ACL 2021.

Data and Code for ACL 2021 Paper "Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning"

Code for ACL'2021 paper WARP 🌀 Word-level Adversarial ReProgramming

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)

The official implementation for ACL 2021 "Challenges in Information Seeking QA: Unanswerable Questions and Paragraph Retrieval".

The GitHub repository for the paper: “Time Series is a Special Sequence: Forecasting with Sample Convolution and Interaction“.

[NAACL & ACL 2021] SapBERT: Self-alignment pretraining for BERT.

PIGLeT: Language Grounding Through Neuro-Symbolic Interaction in a 3D World [ACL 2021]

Comments

About the results

Questions about the BERT version of span-aste.

请问大家可以稍微帮我解释一下这段代码的含义吗，我不太理解，谢谢

Owner

来自丹麦的天籁

PyTorch implementation for ACL 2021 paper "Maria: A Visual Experience Powered Conversational Agent".

Official PyTorch Implementation of SSMix (Findings of ACL 2021)

Code release for the ICML 2021 paper "PixelTransformer: Sample Conditioned Signal Generation".

Code for our ACL 2021 paper - ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer

Codes for ACL-IJCNLP 2021 Paper "Zero-shot Fact Verification by Claim Generation"

Code for our paper "SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarization", ACL 2021

Code and data of the ACL 2021 paper: Few-Shot Text Ranking with Meta Adapted Synthetic Weak Supervision

Code for our ACL 2021 paper "One2Set: Generating Diverse Keyphrases as a Set"

code associated with ACL 2021 DExperts paper

The source codes for ACL 2021 paper 'BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Data'