Language is the most important medium for communication. Teaching machines to understand natural language and use language to interact is a coveted goal for artificial general intelligence (AGI). To this end, the China Computer Federation(CCF), Chinese Information Processing Society of China(CIPS), and Baidu Inc. jointly organize 2019 Language and Intelligence Challenge. The challenge will provide large-scale Chinese datasets and platforms for academic exchange. And hopefully, these will advance the technical development of language understanding and artificial intelligence. The competition forum and award ceremony will be held at the Fourth Language & Intelligence Summit. All researchers and developers are welcomed to this challenge.
There are three proposed tasks in the challenge:
1. Machine Reading Comprehension: This task is to let machines read the text and then answer questions about the given text. It aims to equip machines with the ability to understand natural language.
2. Knowledge-driven Dialogue: This is a human-machine dialogue task, which requires machines to have conversations with humans based upon a given knowledge graph. It aims to equip machines with the ability to simulate human conversations.
3. Information Extraction: This task is to let machines automatically extract knowledge such as entities, attributes and relationships from natural language texts. It aims to equip machines with the ability to automatically construct knowledge graphs from massive texts.
1. Machine Reading Comprehension: This task is to let machines read the text and then answer questions about the given text. It aims to equip machines with the ability to understand natural language.
2. Knowledge-driven Dialogue: This is a human-machine dialogue task, which requires machines to have conversations with humans based upon a given knowledge graph. It aims to equip machines with the ability to simulate human conversations.
3. Information Extraction: This task is to let machines automatically extract knowledge such as entities, attributes and relationships from natural language texts. It aims to equip machines with the ability to automatically construct knowledge graphs from massive texts.
Machine Reading Comprehension
Focus on hard questions that current MRC systems fail to answer correctly, and comprehensively evaluate the ability of machines to conduct in-depth natural language understanding so as to answer complex questions.
Knowledge-driven Dialogue
Explore the ability of machine to proactively lead the conversation based on the knowledge graph similar to human process, providing 120,000 turns of conversation data set.
Information Extraction
Provide the largest Chinese information extraction dataset in the industry, making machines gain the ability to automatically acquire knowledge from massive natural language texts.
Organization
1. Hosts
China Computer Federation (CCF)Chinese Information Processing Society of China (CIPS)
2. Organizer
Baidu Inc.Technical Committee on Chinese Information Technology of CCF (CCF TCCI)Committee on Evaluation of CIPS (CIPS CE)
3. Steering committee
Ming ZhouMicrosoft Research AsiaLe SunInstitute of Software, Chinese Academy of Sciences
Dongyan ZhaoPeking UniversityErhong YangBeijing Language and Culture University
Hua WuBaidu Inc.
4. Organizing committee
Quan WangBaidu Inc.Weiwei SunPeking University
Xianpei HanInstitute of Software, Chinese Academy of SciencesNan DuanMicrosoft Research Asia
Jing LiuBaidu Inc.Wenquan WuBaidu Inc.
Yabin ShiBaidu Inc.