The official code for paper "R2D2: Recursive Transformer based on Differentiable Tree for Interpretable Hierarchical Language Modeling".

Overview

R2D2

This is the official code for paper titled "R2D2: Recursive Transformer based on Differentiable Tree for Interpretable Hierarchical Language Modeling". The current repo is refactored from the original version used in the paper. If meet any issue, please feel free to feedback.

Data

Train

Multi-GPUs

For training from scratch in a single machine with multiple GPUs, please follow scripts below:

CORPUS_PATH=
OUTPUT_PATH=
NODE_NUM=

python -m torch.distributed.launch \
    --nproc_per_node $NODE_NUM R2D2_trainer.py --batch_size 16 \
    --min_len 2 \
    --max_batch_len 512 \
    --max_line -1 \
    --corpus_path $CORPUS_PATH \
    --vocab_path data/en_bert/bert-base-uncased-vocab.txt \
    --config_path data/en_bert/config.json \
    --epoch 60 \
    --output_dir $OUTPUT_PATH \
    --window_size 4 \
    --input_type txt

Single-GPU

CORPUS_PATH=
OUTPUT_PATH=

python trainer.R2D2_trainer \
    --batch_size 16 \
    --min_len 2 \
    --max_batch_len 512 \
    --max_line -1 \
    --corpus_path $CORPUS_PATH \
    --vocab_path data/en_bert/bert-base-uncased-vocab.txt \
    --config_path data/en_bert/config.json \
    --epoch 10 \
    --output_dir $OUTPUT_PATH \
    --input_type txt

Evaluation

Evaluating the bidirectional language model task.

CORPUS_PATH=path to training corpus
VOCAB_DIR=directory of vocab.txt
MODEL_PATH=path to model.bin
CONFIG_PATH=path to config.json

python lm_eval_buckets.py \
    --model_name R2D2 \
    --dataset test \
    --config_path CONFIG_PATH \
    --model_path MODEL_PATH \
    --vocab_dir VOCAB_DIR \
    --corpus_path CORPUS_PATH

For evaluating F1 score on constituency trees, please refer to https://github.com/harvardnlp/compound-pcfg/blob/master/compare_trees.py

Evaluating compatibility with dependency trees: Download WSJ dataset and convert to dependency trees by Stanford CoreNLP(https://stanfordnlp.github.io/CoreNLP/). As WSJ is not a free dataset, it's not included in our project. Please refer to the files in data/predict_trees for detail format of tree induced.

python eval_tree.py \
    --pred_tree_path path_to_tree_induced \
    --ground_truth_path path_to_dependency_trees
    --vocab_dir VOCAB_DIR

On-going work

  1. Re-implement whole model to increase GPU utility ratio.
  2. Pre-train on large corpus

Contact

[email protected] and [email protected]

You might also like...
Official code repository of the paper Learning Associative Inference Using Fast Weight Memory by Schlag et al.

Learning Associative Inference Using Fast Weight Memory This repository contains the offical code for the paper Learning Associative Inference Using F

Official PyTorch code for CVPR 2020 paper
Official PyTorch code for CVPR 2020 paper "Deep Active Learning for Biased Datasets via Fisher Kernel Self-Supervision"

Deep Active Learning for Biased Datasets via Fisher Kernel Self-Supervision https://arxiv.org/abs/2003.00393 Abstract Active learning (AL) aims to min

Official Code for ICML 2021 paper
Official Code for ICML 2021 paper "Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline"

Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline Ankit Goyal, Hei Law, Bowei Liu, Alejandro Newell, Jia Deng Internati

CVPR 2021 - Official code repository for the paper: On Self-Contact and Human Pose.
CVPR 2021 - Official code repository for the paper: On Self-Contact and Human Pose.

selfcontact This repo is part of our project: On Self-Contact and Human Pose. [Project Page] [Paper] [MPI Project Page] It includes the main function

CVPR 2021 - Official code repository for the paper: On Self-Contact and Human Pose.
CVPR 2021 - Official code repository for the paper: On Self-Contact and Human Pose.

SMPLify-XMC This repo is part of our project: On Self-Contact and Human Pose. [Project Page] [Paper] [MPI Project Page] License Software Copyright Lic

Official code of paper "PGT: A Progressive Method for Training Models on Long Videos" on CVPR2021

PGT Code for paper PGT: A Progressive Method for Training Models on Long Videos. Install Run pip install -r requirements.txt. Run python setup.py buil

This is the official code of our paper
This is the official code of our paper "Diversity-based Trajectory and Goal Selection with Hindsight Experience Relay" (PRICAI 2021)

Diversity-based Trajectory and Goal Selection with Hindsight Experience Replay This is the official implementation of our paper "Diversity-based Traje

Official repository with code and data accompanying the NAACL 2021 paper "Hurdles to Progress in Long-form Question Answering" (https://arxiv.org/abs/2103.06332).

Hurdles to Progress in Long-form Question Answering This repository contains the official scripts and datasets accompanying our NAACL 2021 paper, "Hur

Official code for paper
Official code for paper "Demystifying Local Vision Transformer: Sparse Connectivity, Weight Sharing, and Dynamic Weight"

Demysitifing Local Vision Transformer, arxiv This is the official PyTorch implementation of our paper. We simply replace local self attention by (dyna

Comments
  • question about perplexity measures with R2D2 original model

    question about perplexity measures with R2D2 original model

    I have a few minor questions about the R2D2 PPPL measurements and their implementation.

    Q1: In the paper, it says PPPL is defined as, exp(-(1/N) sum(L(S)))

    This makes sense. But in the evaluation code here,

                    log_p_sums, b_c, pppl = self.predictor(ids, self.bucket_size, self.get_bucket_id)
                    PPPL += (pppl - PPPL) / counter
                    print(PPPL, file=f_out)
    

    We are outputting PPPL without taking the exponential. I assume the numbers in the paper are actually 2^{PPPL} here right? assuming we are using 2 as the base. I simply load a random BERT model, PPPL outputted here is around 10.4, 2^{10.4} ~= 1351, which is about right.

    Q2: For pretraining the BERT model baseline, are you guys loading the same dataset as in the link below? or loading some default huggingface dataset? https://github.com/alipay/StructuredLM_RTDT/tree/r2d2/data/en_wiki

    Sorry to throw random questions at you, but this would be very helpful for me to build something on top of this.

    Thanks.

    opened by frankaging 4
  • an potential issue found for the nn.MultiheadAttention module setup

    an potential issue found for the nn.MultiheadAttention module setup

    Hi Authors!

    Thanks for sharing this repo, I enjoyed when reading your paper, and I am working on a related project. As I am going through the code, I found one potential issue with the current setup. I will (1) explain the issue, and (2) provide a simple test case that I ran on my end. Please help with verifying.

    Issue:

    • nn.MultiheadAttention module inside the BinaryEncoder module is set with batch_first=True, however it seems like we are passing in Q, K, V matrics without the first dimension being the batch dimension.

    Code Analysis: In r2d2.py, it is calling the encoder here, as the following

            tasks_embedding = self.embedding(task_ids)  # (?, 2, dim)
            input_embedding = torch.cat([tasks_embedding, tensor_batch], dim=1)  # (?, 4, dim)
            outputs = self.tree_encoder(input_embedding.transpose(0, 1)).transpose(0, 1)  # (? * batch_size, 4, dim)
    

    We can see that input_embedding is definitely with the first dimension being the batch_size as it concat with the embeddings from the nn.embedding module. Before we call self.tree_encoder, .transpose(0, 1) makes the the second dimension of the input being the batch_size instead. Specifically, the first dimension, in this case, is always 4.

    Testing Done: I simply add some logs inside TreeEncoderLayer as,

        def forward(self, src, src_mask=None, pos_ids=None):
            """
            :param src: concatenation of task embeddings and representation for left and right.
                        src shape: (task_embeddings + left + right, batch_size, dim)
            :param src_mask:
            :param pos_ids:
            :return:
            """
            if len(pos_ids.shape) == 1:
                sz = src.shape[0]  # sz: batch_size
                pos_ids = pos_ids.unsqueeze(0).expand(sz, -1)  # (3, batch_size)
            position_embedding = self.position_embedding(pos_ids)
            print("pre: ", src.shape)
            print("pos_emb: ", position_embedding.shape)
            output = self.self_attn(src + position_embedding, src + position_embedding, src, attn_mask=src_mask)
            src2 = output[0]
            attn_weights = output[1]
            print("attn_w: ", attn_weights.shape)
            src = src + self.dropout1(src2)
            src = self.norm1(src)
            src2 = self.linear2(self.dropout(self.activation(self.linear1(src))))
            src = src + self.dropout2(src2)
            src = self.norm2(src)
            print("post: ", src.shape)
            return src
    

    And this is what I get,

    pre:  torch.Size([4, 8, 768])
    pos_emb:  torch.Size([4, 8, 768])
    attn_w:  torch.Size([4, 8, 8])
    post:  torch.Size([4, 8, 768])
    

    Summary: It seems like for r2d2.py, the self-attention is not on those 4 tokens (2 special prefix + left and right children embedding), but it is on the full collection of candidates with their children.

    I saw this issue is not presented in r2d2_cuda.py as,

                outputs = self.tree_encoder(
                    input_embedding)  # (? * batch_size, 4, dim)
    

    This is great. I have not checked the rest of the code for r2d2_cuda.py though. With this, I am wondering are the numbers from either of your papers need to be updated with this potential issue? Either way, I am not blocked by this potential issue, and I was inspired quite a lot by your codebase. Thanks!

    opened by frankaging 3
  • 关于backbone的疑问。

    关于backbone的疑问。

    作者你好,非常感谢你的贡献,我觉得你的工作很有意义,感觉是一个新方向。 有2个疑问需要请教一下:

    1. encoder 使用 transformer,基于注意力的模型,其能力很大部门来源于能通过注意力机制编码出上下文中有用的信息,但这里每次输入只有 [SUM], [CLS], [token1], [token2] 共4个,上下文短,个人感觉 transformer 可能不是最合适的,有试过其它编码器吗?比如gru,或者textCNN?
    2. 有办法并行编码吗?虽然 transformer 的时间复杂度高,但是GPU并行编码很好解决了训练时间长的问题。从论文的E图看 CKY 树编码,一个 token 要分别编码几次,这样会不会导致训练时间实际更长?如,3层 R2D2 比 12 层 transformer 训练数据时间更长? 谢谢作者。
    opened by wulaoshi 1
Releases(fast-R2D2)
Owner
Alipay
Ant Group Open Source
Alipay
Explainability of the Implications of Supervised and Unsupervised Face Image Quality Estimations Through Activation Map Variation Analyses in Face Recognition Models

Explainable_FIQA_WITH_AMVA Note This is the official repository of the paper: Explainability of the Implications of Supervised and Unsupervised Face I

3 May 08, 2022
Another pytorch implementation of FCN (Fully Convolutional Networks)

FCN-pytorch-easiest Trying to be the easiest FCN pytorch implementation and just in a get and use fashion Here I use a handbag semantic segmentation f

Y. Dong 158 Dec 21, 2022
A Closer Look at Invalid Action Masking in Policy Gradient Algorithms

A Closer Look at Invalid Action Masking in Policy Gradient Algorithms This repo contains the source code to reproduce the results in the paper A Close

Costa Huang 73 Dec 24, 2022
MMFlow is an open source optical flow toolbox based on PyTorch

Documentation: https://mmflow.readthedocs.io/ Introduction English | 简体中文 MMFlow is an open source optical flow toolbox based on PyTorch. It is a part

OpenMMLab 688 Jan 06, 2023
Repository for tackling Kaggle Ultrasound Nerve Segmentation challenge using Torchnet.

Ultrasound Nerve Segmentation Challenge using Torchnet This repository acts as a starting point for someone who wants to start with the kaggle ultraso

Qure.ai 46 Jul 18, 2022
Implementation of algorithms for continuous control (DDPG and NAF).

DEPRECATION This repository is deprecated and is no longer maintaned. Please see a more recent implementation of RL for continuous control at jax-sac.

Ilya Kostrikov 288 Dec 31, 2022
SwinIR: Image Restoration Using Swin Transformer

SwinIR: Image Restoration Using Swin Transformer This repository is the official PyTorch implementation of SwinIR: Image Restoration Using Shifted Win

Jingyun Liang 2.4k Jan 08, 2023
Simple Python project using Opencv and datetime package to recognise faces and log attendance data in a csv file.

Attendance-System-based-on-Facial-recognition-Attendance-data-stored-in-csv-file- Simple Python project using Opencv and datetime package to recognise

3 Aug 09, 2022
Molecular Sets (MOSES): A benchmarking platform for molecular generation models

Molecular Sets (MOSES): A benchmarking platform for molecular generation models Deep generative models are rapidly becoming popular for the discovery

Neelesh C A 3 Oct 14, 2022
Solve a Rubiks Cube using Python Opencv and Kociemba module

Rubiks_Cube_Solver Solve a Rubiks Cube using Python Opencv and Kociemba module Main Steps Get the countours of the cube check whether there are tota

Adarsh Badagala 176 Jan 01, 2023
An experiment on the performance of homemade Q-learning AIs in Agar.io depending on their state representation and available actions

Agar.io_Q-Learning_AI An experiment on the performance of homemade Q-learning AIs in Agar.io depending on their state representation and available act

1 Jun 09, 2022
RuleBERT: Teaching Soft Rules to Pre-Trained Language Models

RuleBERT: Teaching Soft Rules to Pre-Trained Language Models (Paper) (Slides) (Video) RuleBERT is a pre-trained language model that has been fine-tune

16 Aug 24, 2022
Learning Neural Painters Fast! using PyTorch and Fast.ai

The Joy of Neural Painting Learning Neural Painters Fast! using PyTorch and Fast.ai Blogpost with more details: The Joy of Neural Painting The impleme

Libre AI 72 Nov 10, 2022
Deep motion generator collections

GenMotion GenMotion (/gen’motion/) is a Python library for making skeletal animations. It enables easy dataset loading and experiment sharing for synt

23 May 24, 2022
Scripts and a shader to get you started on setting up an exported Koikatsu character in Blender.

KK Blender Shader Pack A plugin and a shader to get you started with setting up an exported Koikatsu character in Blender. The plugin is a Blender add

166 Jan 01, 2023
Aerial Single-View Depth Completion with Image-Guided Uncertainty Estimation (RA-L/ICRA 2020)

Aerial Depth Completion This work is described in the letter "Aerial Single-View Depth Completion with Image-Guided Uncertainty Estimation", by Lucas

ETHZ V4RL 70 Dec 22, 2022
Train Dense Passage Retriever (DPR) with a single GPU

Gradient Cached Dense Passage Retrieval Gradient Cached Dense Passage Retrieval (GC-DPR) - is an extension of the original DPR library. We introduce G

Luyu Gao 92 Jan 02, 2023
Library of various Few-Shot Learning frameworks for text classification

FewShotText This repository contains code for the paper A Neural Few-Shot Text Classification Reality Check Environment setup # Create environment pyt

Thomas Dopierre 47 Jan 03, 2023
Official pytorch implementation of "Scaling-up Disentanglement for Image Translation", ICCV 2021.

Official pytorch implementation of "Scaling-up Disentanglement for Image Translation", ICCV 2021.

Aviv Gabbay 41 Nov 29, 2022
Semi-supervised Domain Adaptation via Minimax Entropy

Semi-supervised Domain Adaptation via Minimax Entropy (ICCV 2019) Install pip install -r requirements.txt The code is written for Pytorch 0.4.0, but s

Vision and Learning Group 243 Jan 09, 2023