The First Workshop on
UM-IoS: Unimodal and Multimodal Induction of Linguistic Structures

EMNLP 2022 Workshop

Invited Speakers

Songyang Zhang
(University of Rochester)
William Schuler (OSU) Kai-Wei Chang (UCLA)
Kewei Tu
(ShanghaiTech University)
Joyce Y. Chai (UMich) Song-Chun Zhu (BIGAI)


Following the timezone of EMNLP2022 (Abu Dhabi time; UTC +4)

Time Speaker Description
09:00 - 9:10   Opening Remark
09:10 - 09:50 Joyce Chai Keynote 1: Learning Grounded Task Structures from Language and Vision
09:50 - 10:30 William Schuler Keynote 2:Evaluating a statistical learning hypothesis for human grammar acquisition
10:30 - 11:00   Coffee Break
11:00 - 11:40 Kewei Tu Keynote 3:Scaling Up Probabilistic Grammar Induction with Tensor Decomposition
11:40 - 12:20 Zilong Zheng Keynote 4: Vision Language Joint Parsing
12:20 - 14:00   Lunch Break
14:00 - 14:40 Songyang Zhang Keynote 5:Learning a Grammar Inducer from Videos
14:40 - 15:20 Kai-Wei Chang Keynote 6:Constraint Mining and Constrained Decoding in NLP
15:20 - 16:00   Coffee Break
16:00 - 17:00   Poster session
17:00 - 17:30   Oral Presentation I
17:30 - 17:45   Mini Break
17:45 - 18:50   Oral Presentation II
18:50 - 19:00   Ending Remark


Induction of structures (IoS) is the process of inducing structured objects (a general term of structured data rather than discrete or real values) from a set of observations. It is a branch of machine learning where the output space consists of discrete combinatorial objects (such as strings, trees, and graphs) and is unobserved or partially observed during learning. IoS in natural language processing has often been very focused on the problem of uncovering the syntactic structure (e.g., a constituent or dependency tree), semantic structure, label sequence, discourse structure etc from input text. Such structures have been found useful in downstream tasks such as relation extraction and machine translation. Apart from the wide usage in language, inducing the underlying structures from raw sensory inputs (e.g., vision) has been a long-standing challenge in the field of artificial intelligence.

This workshop will be virtual.


Wenjuan Han (BIGAI) Zilong Zheng (BIGAI) Lifeng Jin (OSU) Yikang Shen (Mila)
Zhouhan Lin (SJTU) Yoon Kim (MIT) Kewei Tu
(ShanghaiTech University)