Alert button
Picture for Shijie Chen

Shijie Chen

Alert button

Roll Up Your Sleeves: Working with a Collaborative and Engaging Task-Oriented Dialogue System

Jul 29, 2023
Lingbo Mo, Shijie Chen, Ziru Chen, Xiang Deng, Ashley Lewis, Sunit Singh, Samuel Stevens, Chang-You Tai, Zhen Wang, Xiang Yue, Tianshu Zhang, Yu Su, Huan Sun

Figure 1 for Roll Up Your Sleeves: Working with a Collaborative and Engaging Task-Oriented Dialogue System
Figure 2 for Roll Up Your Sleeves: Working with a Collaborative and Engaging Task-Oriented Dialogue System
Figure 3 for Roll Up Your Sleeves: Working with a Collaborative and Engaging Task-Oriented Dialogue System
Figure 4 for Roll Up Your Sleeves: Working with a Collaborative and Engaging Task-Oriented Dialogue System

We introduce TacoBot, a user-centered task-oriented digital assistant designed to guide users through complex real-world tasks with multiple steps. Covering a wide range of cooking and how-to tasks, we aim to deliver a collaborative and engaging dialogue experience. Equipped with language understanding, dialogue management, and response generation components supported by a robust search engine, TacoBot ensures efficient task assistance. To enhance the dialogue experience, we explore a series of data augmentation strategies using LLMs to train advanced neural models continuously. TacoBot builds upon our successful participation in the inaugural Alexa Prize TaskBot Challenge, where our team secured third place among ten competing teams. We offer TacoBot as an open-source framework that serves as a practical example for deploying task-oriented dialogue systems.

Viaarxiv icon

Mind2Web: Towards a Generalist Agent for the Web

Jun 15, 2023
Xiang Deng, Yu Gu, Boyuan Zheng, Shijie Chen, Samuel Stevens, Boshi Wang, Huan Sun, Yu Su

Figure 1 for Mind2Web: Towards a Generalist Agent for the Web
Figure 2 for Mind2Web: Towards a Generalist Agent for the Web
Figure 3 for Mind2Web: Towards a Generalist Agent for the Web
Figure 4 for Mind2Web: Towards a Generalist Agent for the Web

We introduce Mind2Web, the first dataset for developing and evaluating generalist agents for the web that can follow language instructions to complete complex tasks on any website. Existing datasets for web agents either use simulated websites or only cover a limited set of websites and tasks, thus not suitable for generalist web agents. With over 2,000 open-ended tasks collected from 137 websites spanning 31 domains and crowdsourced action sequences for the tasks, Mind2Web provides three necessary ingredients for building generalist web agents: 1) diverse domains, websites, and tasks, 2) use of real-world websites instead of simulated and simplified ones, and 3) a broad spectrum of user interaction patterns. Based on Mind2Web, we conduct an initial exploration of using large language models (LLMs) for building generalist web agents. While the raw HTML of real-world websites are often too large to be fed to LLMs, we show that first filtering it with a small LM significantly improves the effectiveness and efficiency of LLMs. Our solution demonstrates a decent level of performance, even on websites or entire domains the model has never seen before, but there is still a substantial room to improve towards truly generalizable agents. We open-source our dataset, model implementation, and trained models (https://osu-nlp-group.github.io/Mind2Web) to facilitate further research on building a generalist agent for the web.

* Website: https://osu-nlp-group.github.io/Mind2Web Updated with supplementary material 
Viaarxiv icon

Error Detection for Text-to-SQL Semantic Parsing

May 23, 2023
Shijie Chen, Ziru Chen, Huan Sun, Yu Su

Figure 1 for Error Detection for Text-to-SQL Semantic Parsing
Figure 2 for Error Detection for Text-to-SQL Semantic Parsing
Figure 3 for Error Detection for Text-to-SQL Semantic Parsing
Figure 4 for Error Detection for Text-to-SQL Semantic Parsing

Despite remarkable progress in text-to-SQL semantic parsing in recent years, the performance of existing parsers is still far from perfect. At the same time, modern deep learning based text-to-SQL parsers are often over-confident and thus casting doubt on their trustworthiness when deployed for real use. To that end, we propose to build a parser-independent error detection model for text-to-SQL semantic parsing. The proposed model is based on pre-trained language model of code and is enhanced with structural features learned by graph neural networks. We train our model on realistic parsing errors collected from a cross-domain setting. Experiments with three strong text-to-SQL parsers featuring different decoding mechanisms show that our approach outperforms parser-dependent uncertainty metrics and could effectively improve the performance and usability of text-to-SQL semantic parsers regardless of their architectures.

Viaarxiv icon

Text-to-SQL Error Correction with Language Models of Code

May 22, 2023
Ziru Chen, Shijie Chen, Michael White, Raymond Mooney, Ali Payani, Jayanth Srinivasa, Yu Su, Huan Sun

Figure 1 for Text-to-SQL Error Correction with Language Models of Code
Figure 2 for Text-to-SQL Error Correction with Language Models of Code
Figure 3 for Text-to-SQL Error Correction with Language Models of Code
Figure 4 for Text-to-SQL Error Correction with Language Models of Code

Despite recent progress in text-to-SQL parsing, current semantic parsers are still not accurate enough for practical use. In this paper, we investigate how to build automatic text-to-SQL error correction models. Noticing that token-level edits are out of context and sometimes ambiguous, we propose building clause-level edit models instead. Besides, while most language models of code are not specifically pre-trained for SQL, they know common data structures and their operations in programming languages such as Python. Thus, we propose a novel representation for SQL queries and their edits that adheres more closely to the pre-training corpora of language models of code. Our error correction model improves the exact set match accuracy of different parsers by 2.4-6.5 and obtains up to 4.3 point absolute improvement over two strong baselines. Our code and data are available at https://github.com/OSU-NLP-Group/Auto-SQL-Correction.

* ACL 2023 Short Paper 
Viaarxiv icon

Bootstrapping a User-Centered Task-Oriented Dialogue System

Jul 11, 2022
Shijie Chen, Ziru Chen, Xiang Deng, Ashley Lewis, Lingbo Mo, Samuel Stevens, Zhen Wang, Xiang Yue, Tianshu Zhang, Yu Su, Huan Sun

Figure 1 for Bootstrapping a User-Centered Task-Oriented Dialogue System
Figure 2 for Bootstrapping a User-Centered Task-Oriented Dialogue System
Figure 3 for Bootstrapping a User-Centered Task-Oriented Dialogue System
Figure 4 for Bootstrapping a User-Centered Task-Oriented Dialogue System

We present TacoBot, a task-oriented dialogue system built for the inaugural Alexa Prize TaskBot Challenge, which assists users in completing multi-step cooking and home improvement tasks. TacoBot is designed with a user-centered principle and aspires to deliver a collaborative and accessible dialogue experience. Towards that end, it is equipped with accurate language understanding, flexible dialogue management, and engaging response generation. Furthermore, TacoBot is backed by a strong search engine and an automated end-to-end test suite. In bootstrapping the development of TacoBot, we explore a series of data augmentation strategies to train advanced neural language processing models and continuously improve the dialogue experience with collected real conversations. At the end of the semifinals, TacoBot achieved an average rating of 3.55/5.0.

* Published in 1st Proceedings of Alexa Prize TaskBot (Alexa Prize 2021) 
Viaarxiv icon

Multi-Task Learning in Natural Language Processing: An Overview

Sep 19, 2021
Shijie Chen, Yu Zhang, Qiang Yang

Figure 1 for Multi-Task Learning in Natural Language Processing: An Overview
Figure 2 for Multi-Task Learning in Natural Language Processing: An Overview
Figure 3 for Multi-Task Learning in Natural Language Processing: An Overview
Figure 4 for Multi-Task Learning in Natural Language Processing: An Overview

Deep learning approaches have achieved great success in the field of Natural Language Processing (NLP). However, deep neural models often suffer from overfitting and data scarcity problems that are pervasive in NLP tasks. In recent years, Multi-Task Learning (MTL), which can leverage useful information of related tasks to achieve simultaneous performance improvement on multiple related tasks, has been used to handle these problems. In this paper, we give an overview of the use of MTL in NLP tasks. We first review MTL architectures used in NLP tasks and categorize them into four classes, including the parallel architecture, hierarchical architecture, modular architecture, and generative adversarial architecture. Then we present optimization techniques on loss construction, data sampling, and task scheduling to properly train a multi-task model. After presenting applications of MTL in a variety of NLP tasks, we introduce some benchmark datasets. Finally, we make a conclusion and discuss several possible research directions in this field.

Viaarxiv icon

Technical report on Conversational Question Answering

Sep 24, 2019
Ying Ju, Fubang Zhao, Shijie Chen, Bowen Zheng, Xuefeng Yang, Yunfeng Liu

Figure 1 for Technical report on Conversational Question Answering
Figure 2 for Technical report on Conversational Question Answering
Figure 3 for Technical report on Conversational Question Answering
Figure 4 for Technical report on Conversational Question Answering

Conversational Question Answering is a challenging task since it requires understanding of conversational history. In this project, we propose a new system RoBERTa + AT +KD, which involves rationale tagging multi-task, adversarial training, knowledge distillation and a linguistic post-process strategy. Our single model achieves 90.4(F1) on the CoQA test set without data augmentation, outperforming the current state-of-the-art single model by 2.6% F1.

Viaarxiv icon