[2018 ACL Short and System] 对话系统

Posted 2021-02-04 shiyublog

Short Paper(s)

1.  Task-oriented Dialogue System for Automatic Diagnosis. (Cited by 0)

Zhongyu Wei, Qianlong Liu, Baolin Peng, Huaixiao Tou, Ting Chen, Xuanjing Huang, Kam-Fai Wong, Xiangying Dai.

In this paper, we make a move to build a dialogue system for automatic diagnosis. We first build a dataset collected from an online medical forum by extracting symptoms( 症状) from both patients‘ self-reports and conversational data between patients and doctors. Then we propose a task-oriented dialogue system framework to make diagnosis for patients automatically, which can converse with patients to collect additional symptoms beyond their self-reports. Experimental results on our dataset show that additional symptoms extracted from conversation can greatly improve the accuracy for disease identification and our dialogue system is able to collect these symptoms automatically and make a better diagnosis.

 

System Demonstration Paper(s)

1. DeepPavlov: Open-Source Library for Dialogue Systems (Cited by 1)

Mikhail Burtsev, Alexander Seliverstov, Rafael Airapetyan, Mikhail Arkhipov, Dilyara Baymurzina, Nickolay Bushkov, Olga Gureenkova, Taras Khakhulin, Yuri Kuratov, Denis Kuznetsov, Alexey Litinsky, Varvara Logacheva, Alexey Lymar, Valentin Malykh, Maxim Petrov, Vadim Polulyakh, Leonid Pugachev, Alexey Sorokin, Maria Vikhreva, Marat Zaynutdinov

Adoption of messaging communication and voice assistants has grown rapidly in the last years. This creates a demand for tools that speed up prototyping(原型机制造) of feature-rich dialogue systems. An open-source library DeepPavlov is tailored for development of conversational agents. The library prioritises efficiency, modularity, and extensibility with the goal to make it easier to develop dialogue systems from scratch and with limited data available. It supports modular as well as end-to-end approaches to implementation of conversational agents. Conversational agent consists of skills and every skill can be decomposed into components. Components are usually models which solve typical NLP tasks such as intent classification, named entity recognition or pre-trained word vectors. Sequence-to-sequence chit-chat skill, question answering skill or task-oriented skill can be assembled from components provided in the library.

2. ScoutBot: A Dialogue System for Collaborative Navigation

Stephanie M. Lukin, Felix Gervits, Cory Hayes, Pooja Moolchandani, Anton Leuski, John Rogers, Carlos Sanchez Amaro, Matthew Marge, Clare Voss, David Traum

ScoutBot is a dialogue interface to physical and simulated robots that supports collaborative exploration of environments. The demonstration will allow users to issue unconstrained spoken language commands to ScoutBot. ScoutBot will prompt for clarification if the user’s instruction needs additional input. It is trained on human-robot dialogue collected from Wizard-of-Oz experiments, where robot responses were initiated by a human wizard(行家; 向导) in previous interactions. The demonstration will show a simulated ground robot (Clearpath Jackal) in a simulated environment supported by ROS (Robot Operating System).