ACCENTOR: Adding Chit-Chat to Enhance Task-Oriented Dialogues

Overview

ACCENTOR consists of the human-annotated chit-chat additions to the 23.8K dialogues from Schema Guided Dialogue (SGD) and MultiWOZ 2.1, allowing researchers to study contexutal addition of chit-chat utterances for virtual assistants, to make task-oriented dialogues more engaging and social.

We also provide three new models for ACCENTOR explicitly trained to predict user goals and to generate contextually relevant chit-chat responses.

Automatic and human evaluations show that, compared with the state of-the-art task-oriented baseline, our models can code-switch between task and chit-chat to be more engaging, interesting, knowledgeable, and humanlike, while maintaining competitive task performance.

For more details, please refer to this paper.

Data

v1.0/candidates-{sgd,multiwoz}.json: Annotated chit-chat candidates. The format is as follows.

{
 "dialogue 1 / id": [
  [
   dialogue 1 / candidate 1 / turn id,
   dialogue 1 / candidate 1 / position,
   dialogue 1 / candidate 1 / candidate,
   dialogue 1 / candidate 1 / label,
   dialogue 1 / candidate 1 / justification
  ],
  [
   dialogue 1 / candidate 2 / turn id,
   ...
  ],
  ...
 ],
 "dialogue 2 / id": [
  ...
 ],
 ...
}

Folder v1.0/accentor-sgd: The augmented SGD dataset. The format follows the original SGD dataset, with two additional keys (i.e., beginning and end) that store lists of (candidate, label, justification) tuples.
- The folder is generated by v1.0/accentor-sgd.py (with v1.0/candidates-sgd.json and the original SGD dataset as input). Usage: python3 v1.0/accentor-sgd.py --help.
v1.0/accentor-multiwoz-1k.json: 1K augmented MultiWOZ 2.1 dialogues. The format follows the original MultiWOZ dataset, with two additional keys (i.e., beginning and end) that store lists of (candidate, label, justification) tuples.
- The file is generated by v1.0/accentor-multiwoz.py (with v1.0/candidates-multiwoz.json and the original MultiWOZ 2.1 dataset as input). Usage: python3 v1.0/accentor-multiwoz.py --help.

Baseline Models

Preparation

Dependencies: ParlAI (af12799a) and Transformers (2.11.0)
Run the following commands to prepare the data for model training and the off-the-shelf models (i.e., a task-oriented dialogue model and a chit-chat model) for Arranger and Rewriter.

cp -r ./v1.0/accentor-sgd .

python3 gen_delex.py

python3 gen_parlai_data.py

parlai train_model -t fromfile:parlaiformat --fromfile_datapath ./parlai --fromfile-datatype-extension true  -m transformer/generator --init-model zoo:tutorial_transformer_generator/model --dict-file zoo:tutorial_transformer_generator/model.dict --embedding-size 512 --n-layers 8 --ffn-size 2048 --dropout 0.1 --n-heads 16 --learn-positional-embeddings True --n-positions 512 --variant xlm --activation gelu --skip-generation True --fp16 True --text-truncate 512 --label-truncate 128 --dict-tokenizer bpe --dict-lower True -lr 1e-06 --optimizer adamax --lr-scheduler reduceonplateau --gradient-clip 0.1 -veps 0.25 --betas 0.9,0.999 --update-freq 1 --attention-dropout 0.0 --relu-dropout 0.0 --skip-generation True -vp 15 -stim 60 -vme 20000 -bs 16 -vmt ppl -vmm min --save-after-valid True --model-file ./train_90M

parlai interactive -mf ./train_90M < lm.input.dev.cc.txt > lm.output.dev.cc.txt

parlai interactive -mf ./train_90M < lm.input.test.cc.txt > lm.output.test.cc.txt

python3 run_language_modeling.py --output_dir=output_gpt2_10epoch_1e-3_fp16 --model_type=gpt2 --model_name_or_path=gpt2 --do_train --train_data_file=lm.input.train.txt --do_eval  --eval_data_file=lm.input.dev.txt --per_device_train_batch_size 2 --gradient_accumulation_steps 18 --num_train_epochs 10 --learning_rate 1e-3 --fp16 --overwrite_output_dir

python3 run_generation.py --input lm.input.dev.eval.txt --output dev.inference.gpt2_10epoch_1e-3_fp16.json --model_name_or_path ./output_gpt2_10epoch_1e-3_fp16 --eos_token_id 50262

python3 run_generation.py --input lm.input.test.eval.txt --output test.inference.gpt2_10epoch_1e-3_fp16.json --model_name_or_path ./output_gpt2_10epoch_1e-3_fp16 --eos_token_id 50262

SimpleTOD+

Dependency: Transformers (2.11.0)

python3 run_language_modeling.py --output_dir=output_both_gpt2_10epoch_1e-3_fp16 --model_type=gpt2 --model_name_or_path=gpt2 --do_train --train_data_file=lm.input.train.both.txt --do_eval  --eval_data_file=lm.input.dev.both.txt --per_device_train_batch_size 2 --gradient_accumulation_steps 18 --num_train_epochs 10 --learning_rate 1e-3 --fp16 --overwrite_output_dir

python3 run_generation.py --input lm.input.dev.eval.txt --output dev.inference.both_gpt2_10epoch_1e-3_fp16.json --model_name_or_path ./output_both_gpt2_10epoch_1e-3_fp16 --eos_token_id 50262

python3 run_generation.py --input lm.input.test.eval.txt --output test.inference.both_gpt2_10epoch_1e-3_fp16.json --model_name_or_path ./output_both_gpt2_10epoch_1e-3_fp16 --eos_token_id 50262

Arranger

Dependency: Transformers (2.2.0)

python3 gen_arranger_input.py

python3 run_multiple_choice.py --model_type roberta --task_name acc --model_name_or_path roberta-base --do_train --do_eval --do_test --do_lower_case --data_dir . --learning_rate 2e-5 --num_train_epochs 3 --max_seq_length 512 --output_dir acc_arranger_roberta_base_3epoch --per_gpu_eval_batch_size=16 --per_gpu_train_batch_size=1 --gradient_accumulation_steps 24 --overwrite_output --save_steps 10000

python3 gen_arranger_output.py

Rewriter

Dependency: Transformers 2.11.0

python3 gen_rewriter_data.py

python3 run_language_modeling.py --output_dir=output_ff_gpt2_10epoch_1e-3_fp16 --model_type=gpt2 --model_name_or_path=gpt2 --do_train --train_data_file=lm.input.train.ff.txt  --do_eval --eval_data_file=lm.input.dev.ff.txt --per_device_train_batch_size 2 --gradient_accumulation_steps 18 --num_train_epochs 10 --learning_rate 1e-3 --fp16 --overwrite_output_dir

python3 run_generation.py --input lm.input.dev.eval.ff.txt --output dev.inference.ff_gpt2_10epoch_1e-3_fp16.json --model_name_or_path ./output_ff_gpt2_10epoch_1e-3_fp16 --eos_token_id 50262

python3 run_generation.py --input lm.input.test.eval.ff.txt --output test.inference.ff_gpt2_10epoch_1e-3_fp16.json --model_name_or_path ./output_ff_gpt2_10epoch_1e-3_fp16 --eos_token_id 50262

Evaluation

Dependency: the official evaluation script of SGD
Pass the output inference files (i.e., {dev,test}.inference*.json) to gen_predict.py to obtain act-slot F1 and BLEU-4 scores. For example,

python3 gen_predict.py --inference test.inference.both_gpt2_10epoch_1e-3_fp16.json --split test

The above command will also generate a folder (named ./prediction/ by default), which can be passed to the official evaluation script of SGD to obtain the joint goal accuracy and average accuracy. For example,

python3 -m schema_guided_dst.evaluate --dstc8_data_dir ./simpletod/ --prediction_dir ./prediction/test/ --eval_set test --output_metric_file simpletod+_test_result.json

Citations

If you want to publish experimental results with our datasets or use the baseline models, please cite the following article (pdf):

@inproceedings{sun2020adding,
  title={Adding Chit-Chat to Enhance Task-Oriented Dialogues},
  author={Sun, Kai and Moon, Seungwhan and Crook, Paul and Roller, Stephen and Silvert, Becka and Liu, Bing and Wang, Zhiguang and Liu, Honglei and Cho, Eunjoon and Cardie, Claire},
  booktitle={Proceedings of the NAACL-HLT},
  year={2021},
  url={https://arxiv.org/abs/2010.12757}
}

License

ACCENTOR is released under CC-BY-SA-4.0, see LICENSE for details.

Data & Code for ACCENTOR Adding Chit-Chat to Enhance Task-Oriented Dialogues

Related tags

Overview

ACCENTOR: Adding Chit-Chat to Enhance Task-Oriented Dialogues

Overview

Data

Baseline Models

Citations

License

Owner

Facebook Research

Mask-invariant Face Recognition through Template-level Knowledge Distillation

Implementation of the state of the art beat-detection, downbeat-detection and tempo-estimation model

Deep Learning to Create StepMania SM FIles

Allows including an action inside another action (by preprocessing the Yaml file). This is how composite actions should have worked.

Integrated Semantic and Phonetic Post-correction for Chinese Speech Recognition

Waymo motion prediction challenge 2021: 3rd place solution

Official Implementation of DE-CondDETR and DELA-CondDETR in "Towards Data-Efficient Detection Transformers"

Code implementation of Data Efficient Stagewise Knowledge Distillation paper.

Explore the Expression: Facial Expression Generation using Auxiliary Classifier Generative Adversarial Network

This project aims at building a real-time wide band channel sounder using USRPs

In this tutorial, you will perform inference across 10 well-known pre-trained object detectors and fine-tune on a custom dataset. Design and train your own object detector.

Learning to Simulate Dynamic Environments with GameGAN (CVPR 2020)

A bare-bones Python library for quality diversity optimization.

Using image super resolution models with vapoursynth and speeding them up with TensorRT

HAR-stacked-residual-bidir-LSTMs - Deep stacked residual bidirectional LSTMs for HAR

The 2nd Version Of Slothybot

Code to use Augmented Shapiro Wilks Stopping, as well as code for the paper "Statistically Signifigant Stopping of Neural Network Training"

Generic image compressor for machine learning. Pytorch code for our paper "Lossy compression for lossless prediction".

Official repository for "Exploiting Session Information in BERT-based Session-aware Sequential Recommendation", SIGIR 2022 short.

Training a deep learning model on the noisy CIFAR dataset