Donghan Yu
@Yudh9662
Followers
566
Following
459
Media
2
Statuses
66
Researcher @Microsoft | ex PhD student at @LTIatCMU
Pittsburgh, PA
Joined July 2017
Don't wanna be here?
Send us removal request.
Explore trending content on Musk Viewer
#2024MAMAVOTE
• 3039722 Tweets
EP6 U STEAL MY HEART
• 471452 Tweets
JIN IS COMING
• 307321 Tweets
Columbus
• 261238 Tweets
Libya
• 232997 Tweets
HAPPY IS COMING
• 212652 Tweets
Nobel
• 193755 Tweets
Bill Clinton
• 117576 Tweets
MY ROYALTY HEESEUNG DAY
• 103728 Tweets
Thanksgiving
• 81174 Tweets
Laken Riley
• 53316 Tweets
Bret
• 36905 Tweets
Leire
• 31782 Tweets
Europeans
• 30945 Tweets
Amaia
• 21308 Tweets
Geraldo
• 18003 Tweets
Belgique
• 14302 Tweets
Sombra
• 11767 Tweets
National Grid
• 11443 Tweets
Pinned Tweet
Thrilled to share some life updates! I've officially completed my Ph.D. journey at
@LTIatCMU
and started an exciting new role as a Senior Researcher at
@Microsoft
!
4
3
90
New preprint! DecAF: Joint Decoding of Answers and Logical Forms for Question Answering over Knowledge Bases. Our proposed method achieved new SoTAs on KBQA! (1/5)
Arxiv link:
4
9
35
I’m so glad to share that DecAF has been accepted to
#ICLR2023
!
New preprint! DecAF: Joint Decoding of Answers and Logical Forms for Question Answering over Knowledge Bases. Our proposed method achieved new SoTAs on KBQA! (1/5)
Arxiv link:
4
9
35
1
0
16
Our paper "Knowledge Embedding Based Graph Convolutional Network" has been accepted to
#www2021
Want to incorporate KE methods like TransH, TransD, QuatE... into GCN? Check an old version of this paper: . New version will be updated soon.
0
2
11
#StopAsianHate
CMU Graduate Student Assembly: Petition of Asian And Asian American students to the CMU GSA executive committee - Sign the Petition! via
@Change
1
3
6
Code available at:
0
1
5
@PMinervini
Great work! Just want to mention that our TheWebConf 2021 paper also builds a connection between traditional KG embedding models and GNNs.
1
0
5
Please check this excellent paper if you’re working on text2sql!
I am excited to share our paper “Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustness” got accepted as a top 5% paper (oral) to
#ICLR2023
.
9
13
82
1
0
4
I am speaking at ECML-PKDD 2020. Please checkout the details of my talk at:
0
0
3
We propose a novel framework that jointly generates both logical forms and direct answers, and then combines them for the final answers. Moreover, DecAF is based on simple free-text retrieval without relying on any entity linking tools. (3/5)
1
1
2
“Had a bad day” can be the excuse of killing 8 people?!!
0
0
2
Previous methods either generate logical forms that can be executed over KBs to obtain final answers or predict answers directly. Empirical results show that the former often produces more accurate answers, but it suffers from non-execution issues. (2/5)
1
1
2
Our model achieves new state-of-the-art results on WebQSP, GrailQA, and FreebaseQA benchmarks, and gets very competitive results on the ComplexWebQuestions benchmark. (4/5)
1
0
1
Ridiculous
Please sign and share this petition to reinstate UIUC graduate worker Ivor Chen after the University decided to dismiss him for behavior that they admit deserves a testing exemption! This is cruel and unjust, and we must stand up to UIUC on his behalf!
9
107
155
0
0
1
Together with Sheng Zhang, Patrick Ng, Henghui Zhu, Alexander Hanbo Li, Jun Wang, Yiqun Hu,
@WilliamWangNLP
, Zhiguo Wang, Bing Xiang, in collaboration with AWS AI Labs. (5/5)
0
0
1
Tried yesterday. Amazing!
We often cite papers using arXiv info w/o noting that they are already PUBLISHED in confs like
@aclmeeting
and
@iclr_conf
. These incorrect bib entries are so annoying!😠 We introduce Rebiber, a tool to fix them using
@aclanthology
and
@dblp_org
. 😆
Code:
24
226
1K
1
0
1