Few-Shot-Intent-Detection includes popular challenging intent detection datasets with/without OOS queries and state-of-the-art baselines and results.

Overview

Few-Shot-Intent-Detection

Few-Shot-Intent-Detection is a repository designed for few-shot intent detection with/without Out-of-Scope (OOS) intents. It includes popular challenging intent detection datasets and baselines. For more details of the new released OOS datasets, please check our paper.

Intent detection datasets

We process data based on previous published resources, all the data are in the same format as DNNC.

Dataset Description #Train #Valid #Test Processed Data Link
BANKING77 one banking domain with 77 intents 8622 1540 3080 Link
CLINC150 10 domains and 150 intents 15000 3000 4500 Link
HWU64 personal assistant with 64 intents and several domains 8954 1076 1076 Link
SNIPS snips voice platform with 7 intents 13084 700 700 Link
ATIS airline travel information system 4478 500 893 Link

Intent detection datasets with OOS queries

What is OOS queires:

OOD-OOS: i.e., out-of-domain OOS. General out-of-scope queries which are not supported by the dialog systems, also called out-of-domain OOS. For instance, requesting an online NBA/TV show service in a banking system.

ID-OOS: i.e., in-domain OOS. Out-of-scope queries which are more related to the in-scope intents, which makes the intent detection task more challenging. For instance, requesting a banking service that is not supported by the banking system.

Dataset Description #Train #Valid #Test #OOD-OOS-Train #OOD-OOS-Valid #OOD-OOS-Test #ID-OOS-Train #ID-OOS-Valid #ID-OOS-Test Processed Data Link
CLINC150 A dataset with general OOS-OOS queries 15000 3000 4500 100 100 1000 - - - Link
CLINC-Single-Domain-OOS Two domains with both general OOS-OOS queries and ID-OOS queries 500 500 500 - 200 1000 - 400 350 Link
BANKING77-OOS One banking domain with both general OOS-OOS queries and ID-OOS queries 5905 1506 2000 - 200 1000 2062 530 1080 Link

Data structure:

Datasets/
├── BANKING77
│   ├── train
│   ├── train_10
│   ├── train_5
│   ├── valid
│   └── test
├── CLINC150
│   ├── train
│   ├── train_10
│   ├── train_5
│   ├── valid
│   ├── test
│   ├── oos
│       ├──train
│       ├──valid
│       └──test
├── HWU64
│   ├── train
│   ├── train_10
│   ├── train_5
│   ├── valid
│   └── test
├── SNIPS
│   ├── train
│   ├── valid
│   └── test
├── ATIS
│   ├── train
│   ├── valid
│   └── test
├── BANKING77-OOS
│   ├── train
│   ├── valid
│   ├── test
│   ├── id-oos
│   │   ├──train
│   │   ├──valid
│   │   └──test
│   ├── ood-oos
│       ├──valid
│       └──test
├── CLINC-Single-Domain-OOS
│   ├── banking
│   │   ├── train
│   │   ├── valid
│   │   ├── test
│   │   ├── id-oos
│   │   │   ├──valid
│   │   │   └──test
│   │   ├── ood-oos
│   │       ├──valid
│   │       └──test
│   ├── credit_cards
│   │   ├── train
│   │   ├── valid
│   │   ├── test
│   │   ├── id-oos
│   │   │   ├──valid
│   │   │   └──test
│   │   ├── ood-oos
│   │       ├──valid
└── └──     └──test

Briefly describe the BANKING77-OOS dataset.

  • A dataset with a single banking domain, includes both general Out-of-Scope (OOD-OOS) queries and In-Domain but Out-of-Scope (ID-OOS) queries, where ID-OOS queries are semantically similar intents/queries with in-scope intents. BANKING77 originally includes 77 intents. BANKING77-OOS includes 50 in-scope intents in this dataset, and the ID-OOS queries are built up based on 27 held-out semantically similar in-scope intents.

Briefly describe the CLINC-Single-Domain-OOS dataset.

  • A dataset with two separate domains, i.e., the "Banking'' domain and the "Credit cards'' domain with both general Out-of-Scope (OOD-OOS) queries and In-Domain but Out-of-Scope (ID-OOS) queries, where ID-OOS queries are semantically similar intents/queries with in-scope intents. Each domain in CLINC150 originally includes 15 intents. Each domain in the new dataset includes ten in-scope intents in this dataset, and the ID-OOS queries are built up based on five held-out semantically similar in-scope intents.

Both datasets can be used to conduct intent detection with and without OOD-OOS and ID-OOS queries

You can easily load the processed data:

class IntentExample:
    def __init__(self, text, label, do_lower_case):
        self.original_text = text
        self.text = text
        self.label = label

        if do_lower_case:
            self.text = self.text.lower()
        
def load_intent_examples(file_path, do_lower_case=True):
    examples = []

    with open('{}/seq.in'.format(file_path), 'r', encoding="utf-8") as f_text, open('{}/label'.format(file_path), 'r', encoding="utf-8") as f_label:
        for text, label in zip(f_text, f_label):
            e = IntentExample(text.strip(), label.strip(), do_lower_case)
            examples.append(e)

    return examples

More details can check code for load data and do random sampling for few-shot learning.

State-of-the art models and baselines

DNNC

Download pre-trained RoBERTa NLI checkpoint:

wget https://storage.googleapis.com/sfr-dnnc-few-shot-intent/roberta_nli.zip

Access to public code: Link

CONVERT

Download pre-trained checkpoint:

wget https://github.com/connorbrinton/polyai-models/releases/download/v1.0/model.tar.gz

Access to public code:

wget https://github.com/connorbrinton/polyai-models/archive/refs/tags/v1.0.zip

CONVBERT

Download pre-trained checkpoints:

Step-1: install AWS CL2: e.g., install MacOS PKG

Step-2:

aws s3 cp s3://dialoglue/ --no-sign-request `Your_folder_name` --recursive

Then the checkpoints are downloaded into Your_folder_name

Few-shot intent detection baselines/leaderboard:

5-shot learning

Model BANKING77 CLICN150 HWU64
RoBERTa+Classifier (EMNLP 2020) 74.04 87.99 75.56
USE (ACL 2020 NLP4ConvAI) 76.29 87.82 77.79
CONVERT (ACL 2020 NLP4ConvAI) 75.32 89.22 76.95
USE+CONVERT (ACL 2020 NLP4ConvAI) 77.75 90.49 80.01
CONVBERT+MLM+Example+Observers (NAACL 2021) - - -
DNNC (EMNLP 2020) 80.40 91.02 80.46
CPFT (EMNLP 2021) 80.86 92.34 82.03

10-shot learning

Model BANKING77 CLICN150 HWU64
RoBERTa+Classifier (EMNLP 2020) 84.27 91.55 82.90
USE (ACL 2020 NLP4ConvAI) 84.23 90.85 83.75
CONVERT(ACL 2020 NLP4ConvAI) 83.32 92.62 82.65
USE+CONVERT (ACL 2020 NLP4ConvAI) 85.19 93.26 85.83
CONVBERT (ArXiv 2020) 83.63 92.10 83.77
CONVBERT+MLM (ArXiv 2020) 83.99 92.75 84.52
CONVBERT+MLM+Example+Observers (NAACL 2021) 85.95 93.97 86.28
DNNC (EMNLP 2020) 86.71 93.76 84.72
CPFT (EMNLP 2021) 87.20 94.18 87.13

Note: the 5-shot learning results of RoBERTa+Classifier, DNNC and CPFT, and the 10-shot learning results of all the models are reported by the paper authors.

Citation

Please cite our paper if you use above resources in your work:

@article{zhang2020discriminative,
  title={Discriminative nearest neighbor few-shot intent detection by transferring natural language inference},
  author={Zhang, Jian-Guo and Hashimoto, Kazuma and Liu, Wenhao and Wu, Chien-Sheng and Wan, Yao and Yu, Philip S and Socher, Richard and Xiong, Caiming},
  journal={EMNLP},
  pages={5064--5082},
  year={2020}
}

@article{zhang2021pretrained,
  title={Are Pretrained Transformers Robust in Intent Classification? A Missing Ingredient in Evaluation of Out-of-Scope Intent Detection},
  author={Zhang, Jian-Guo and Hashimoto, Kazuma and Wan, Yao and Liu, Ye and Xiong, Caiming and Yu, Philip S},
  journal={arXiv preprint arXiv:2106.04564},
  year={2021}
}

@article{zhang2021few,
  title={Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuning},
  author={Zhang, Jianguo and Bui, Trung and Yoon, Seunghyun and Chen, Xiang and Liu, Zhiwei and Xia, Congying and Tran, Quan Hung and Chang, Walter and Yu, Philip},
  journal={EMNLP},
  year={2021}
}
Owner
Jian-Guo Zhang
Jian-Guo Zhang
Have you ever wondered how cool it would be to have your own A.I

Have you ever wondered how cool it would be to have your own A.I. assistant Imagine how easier it would be to send emails without typing a single word, doing Wikipedia searches without opening web br

Harsh Gupta 1 Nov 09, 2021
A task-agnostic vision-language architecture as a step towards General Purpose Vision

Towards General Purpose Vision Systems By Tanmay Gupta, Amita Kamath, Aniruddha Kembhavi, and Derek Hoiem Overview Welcome to the official code base f

AI2 79 Dec 23, 2022
A framework for attentive explainable deep learning on tabular data

🧠 kendrite A framework for attentive explainable deep learning on tabular data 💨 Quick start kedro run 🧱 Built upon Technology Description Links ke

Marnix Koops 3 Nov 06, 2021
Self-supervised Deep LiDAR Odometry for Robotic Applications

DeLORA: Self-supervised Deep LiDAR Odometry for Robotic Applications Overview Paper: link Video: link ICRA Presentation: link This is the correspondin

Robotic Systems Lab - Legged Robotics at ETH Zürich 181 Dec 29, 2022
A curated list of neural network pruning resources.

A curated list of neural network pruning and related resources. Inspired by awesome-deep-vision, awesome-adversarial-machine-learning, awesome-deep-learning-papers and Awesome-NAS.

Yang He 1.7k Jan 09, 2023
Implementation of Bagging and AdaBoost Algorithm

Bagging-and-AdaBoost Implementation of Bagging and AdaBoost Algorithm Dataset Red Wine Quality Data Sets For simplicity, we will have 2 classes of win

Zechen Ma 1 Nov 01, 2021
Official implementation for the paper "Attentive Prototypes for Source-free Unsupervised Domain Adaptive 3D Object Detection"

Attentive Prototypes for Source-free Unsupervised Domain Adaptive 3D Object Detection PyTorch code release of the paper "Attentive Prototypes for Sour

Deepti Hegde 23 Oct 17, 2022
Awesome Remote Sensing Toolkit based on PaddlePaddle.

基于飞桨框架开发的高性能遥感图像处理开发套件,端到端地完成从训练到部署的全流程遥感深度学习应用。 最新动态 PaddleRS 即将发布alpha版本!欢迎大家试用 简介 PaddleRS是遥感科研院所、相关高校共同基于飞桨开发的遥感处理平台,支持遥感图像分类,目标检测,图像分割,以及变化检测等常用遥

146 Dec 11, 2022
Refactoring dalle-pytorch and taming-transformers for TPU VM

Text-to-Image Translation (DALL-E) for TPU in Pytorch Refactoring Taming Transformers and DALLE-pytorch for TPU VM with Pytorch Lightning Requirements

Kim, Taehoon 61 Nov 07, 2022
WarpRNNT loss ported in Numba CPU/CUDA for Pytorch

RNNT loss in Pytorch - Numba JIT compiled (warprnnt_numba) Warp RNN Transducer Loss for ASR in Pytorch, ported from HawkAaron/warp-transducer and a re

Somshubra Majumdar 15 Oct 22, 2022
Heat transfer problemas solved using python

heat-transfer Heat transfer problems solved using python isolation-convection.py compares the temperature distribution on the problem as shown in the

2 Nov 14, 2021
Training DALL-E with volunteers from all over the Internet using hivemind and dalle-pytorch (NeurIPS 2021 demo)

Training DALL-E with volunteers from all over the Internet This repository is a part of the NeurIPS 2021 demonstration "Training Transformers Together

<a href=[email protected]"> 19 Dec 13, 2022
MAUS: A Dataset for Mental Workload Assessment Using Wearable Sensor - Baseline system

MAUS: A Dataset for Mental Workload Assessment Using Wearable Sensor - Baseline system Getting started To start working on this assignment, you should

2 Aug 06, 2022
A hyperparameter optimization framework

Optuna: A hyperparameter optimization framework Website | Docs | Install Guide | Tutorial Optuna is an automatic hyperparameter optimization software

7.4k Jan 04, 2023
A toolkit for developing and comparing reinforcement learning algorithms.

Status: Maintenance (expect bug fixes and minor updates) OpenAI Gym OpenAI Gym is a toolkit for developing and comparing reinforcement learning algori

OpenAI 29.6k Jan 08, 2023
High dimensional black-box optimizer using Latent Action Monte Carlo Tree Search algorithm

LA-MCTS The code is based of paper Learning Search Space Partition for Black-box Optimization using Monte Carlo Tree Search. Component LA-MCTS has thr

Meta Research 18 Oct 24, 2022
Spatial Single-Cell Analysis Toolkit

Single-Cell Image Analysis Package Scimap is a scalable toolkit for analyzing spatial molecular data. The underlying framework is generalizable to spa

Laboratory of Systems Pharmacology @ Harvard 30 Nov 08, 2022
A lightweight library to compare different PyTorch implementations of the same network architecture.

TorchBug is a lightweight library designed to compare two PyTorch implementations of the same network architecture. It allows you to count, and compar

Arjun Krishnakumar 5 Jan 02, 2023
GradAttack is a Python library for easy evaluation of privacy risks in public gradients in Federated Learning

GradAttack is a Python library for easy evaluation of privacy risks in public gradients in Federated Learning, as well as corresponding mitigation strategies.

129 Dec 30, 2022
Only works with the dashboard version / branch of jesse

Jesse optuna Only works with the dashboard version / branch of jesse. The config.yml should be self-explainatory. Installation # install from git pip

Markus K. 8 Dec 04, 2022