Code and checkpoints for training the transformer-based Table QA models introduced in the paper TAPAS: Weakly Supervised Table Parsing via Pre-training.

2020/06/10

• Bump TensorFlow to v2.2

2020/06/08

• Released the pre-training data.

2020/05/07

• Added a colab to try predictions on SQA

The easiest way to try out TAPAS with free GPU/TPU is in our Colab, which shows how to do predictions on SQA.

The repository uses protocol buffers, and requires the protoc compiler to run. You can download the latest binary for your OS here. On Ubuntu/Debian, it can be installed with:

sudo apt-get install protobuf-compiler

Afterwards, clone and install the git repository:

git clone https://github.com/google-research/tapas
cd tapas
pip install -e .

To run the test suite we use the tox library which can be run by calling:

pip install tox
tox

See the section below for the pre-training data.

The pre-trained TAPAS checkpoints can be downloaded here:

• MASKLM base
• MASKLM large
• SQA base
• SQA large

The first two models are pre-trained on the Mask-LM task and the last two on the Mask-LM task first and SQA second.

You also need to download the task data for the fine-tuning tasks:

• SQA
• WikiSQL
• WTQ 1.0

Note that you can skip pre-training and just use one of the pre-trained checkpoints provided above.

Information about the pre-taining data can be found here.

The TF examples for pre-training can be created using Google Dataflow:

python3 setup.py sdist
python3 tapas/create_pretrain_examples_main.py \
  --input_file="gs://tapas_models/2020_05_11/interactions.txtpb.gz" \
  --vocab_file="gs://tapas_models/2020_05_11/vocab.txt" \
  --output_dir="gs://your_bucket/output" \
  --runner_type="DATAFLOW" \
  --gc_project="you-project" \
  --gc_region="us-west1" \
  --gc_job_name="create-pretrain" \
  --gc_staging_location="gs://your_bucket/staging" \
  --gc_temp_location="gs://your_bucket/tmp" \
  --extra_packages=dist/tapas-0.0.1.dev0.tar.gz

You can also run the pipeline locally but that will take a long time:

python3 tapas/create_pretrain_examples_main.py \
  --input_file="$data/interactions.txtpb.gz" \
  --output_dir="$data/" \
  --vocab_file="$data/vocab.txt" \
  --runner_type="DIRECT"

This will create two tfrecord files for training and testing. The pre-training can then be started with the command below. The init checkpoint should be a standard BERT checkpoint.

python3 tapas/experiments/tapas_pretraining_experiment.py \
  --eval_batch_size=32 \
  --train_batch_size=512 \
  --tpu_iterations_per_loop=5000 \
  --num_eval_steps=100 \
  --save_checkpoints_steps=600 \
  --num_train_examples=512000000 \
  --max_seq_length=128 \
  --input_file_train="${data}/train.tfrecord" \
  --input_file_eval="${data}/test.tfrecord" \
  --init_checkpoint="${tapas_data_dir}/model.ckpt" \
  --bert_config_file="${tapas_data_dir}/bert_config.json" \
  --model_dir="..." \
  --do_train

You can start a separate eval job by setting --nodo_train --doeval.

We need to create the TF examples before starting the training. For example, for SQA that would look like:

python3 tapas/run_task_main.py \
  --task="SQA" \
  --input_dir="${sqa_data_dir}" \
  --output_dir="${output_dir}" \
  --bert_vocab_file="${tapas_data_dir}/vocab.txt" \
  --mode="create_data"

Afterwards, training can be started by running:

python3 tapas/run_task_main.py \
  --task="SQA" \
  --output_dir="${output_dir}" \
  --init_checkpoint="${tapas_data_dir}/model.ckpt" \
  --bert_config_file="${tapas_data_dir}/bert_config.json" \
  --mode="train" \
  --use_tpu

This will use the preset hyper-parameters set in hparam_utils.py.

It's recommended to start a separate eval job to continuously produce predictions for the checkpoints created by the training job. Alternatively, you can run the eval job after training to only get the final results.

python3 tapas/run_task_main.py \
  --task="SQA" \
  --output_dir="${output_dir}" \
  --init_checkpoint="${tapas_data_dir}/model.ckpt" \
  --bert_config_file="${tapas_data_dir}/bert_config.json" \
  --mode="predict_and_evaluate"

Another tool to run experiments is tapas_classifier_experiment.py. It's more flexible than run_task_main.py but also requires setting all the hyper-parameters (via the respective command line flags).

Here we explain some details about different tasks and give some rough numbers. These numbers are denotation accuracy as computed by our tool and not the official metrics of the respective tasks. The numbers are here to to verify whether one's own runs are in the right ballpark. These numbers are not medians but individual runs.

By default, SQA will evaluate using the reference answers of the previous questions. The number in the paper (Table 5) are computed using the more realistic setup where the previous answer are model predictions. run_task_main.py will output additional prediction files for this setup as well if run on GPU.

For the official evaluation results one should convert the TAPAS predictions to the WTQ format and run the official evaluation script. This can be done using convert_predictions.py.

As discussed in the paper our code will compute evaluation metrics that deviate from the official evaluation script (Table 3 and 10).

TAPAS is essentialy a BERT model and thus has the same requirements. This means that training the large model with 512 sequence length will require a TPU. You can use the option max_seq_length to create shorter sequences. This will reduce accuracy but also make the model trainable on GPUs. Another option is to reduce the batch size (train_batch_size), but this will likely also affect accuracy. We added an options gradient_accumulation_steps that allows you to split the gradient over multiple batches. Evaluation with the default test batch size (32) should be possible on GPU.

You can cite the paper to appear at ACL:

@inproceedings{49053,
title = {Tapas: Weakly Supervised Table Parsing via Pre-training},
author = {Jonathan Herzig and Paweł Krzysztof Nowak and Thomas Müller and Francesco Piccinno and Julian Martin Eisenschlos},
year = {2020},
URL = {https://arxiv.org/abs/2004.02349},
note = {to appear},
booktitle = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
address = {Seattle, Washington, United States}
}

This is not an official Google product.

For help or issues, please submit a GitHub issue.