Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox
Picture for Yannis Katsis

Yannis Katsis

Abstractified Multi-instance Learning (AMIL) for Biomedical Relation Extraction



William Hogan , Molly Huang , Yannis Katsis , Tyler Baldwin , Ho-Cheol Kim , Yoshiki Vazquez Baeza , Andrew Bartko , Chun-Nan Hsu

Figure 1 for Abstractified Multi-instance Learning (AMIL) for Biomedical Relation Extraction
Figure 2 for Abstractified Multi-instance Learning (AMIL) for Biomedical Relation Extraction
Figure 3 for Abstractified Multi-instance Learning (AMIL) for Biomedical Relation Extraction
Figure 4 for Abstractified Multi-instance Learning (AMIL) for Biomedical Relation Extraction
* 3rd Conference on Automated Knowledge Base Construction (2021) 
 * 14 pages, 3 figures, submitted to Automated Knowledge Base Construction (2021) 
   Access Paper or Ask Questions

AIT-QA: Question Answering Dataset over Complex Tables in the Airline Industry



Yannis Katsis , Saneem Chemmengath , Vishwajeet Kumar , Samarth Bharadwaj , Mustafa Canim , Michael Glass , Alfio Gliozzo , Feifei Pan , Jaydeep Sen , Karthik Sankaranarayanan , Soumen Chakrabarti

Figure 1 for AIT-QA: Question Answering Dataset over Complex Tables in the Airline Industry
Figure 2 for AIT-QA: Question Answering Dataset over Complex Tables in the Airline Industry
Figure 3 for AIT-QA: Question Answering Dataset over Complex Tables in the Airline Industry
Figure 4 for AIT-QA: Question Answering Dataset over Complex Tables in the Airline Industry

   Access Paper or Ask Questions

Theoretical Knowledge Graph Reasoning via Ending Anchored Rules



Canlin Zhang , Yannis Katsis , Yoshiki Vazquez-Baeza , Andrew Bartko , Ho-Cheol Kim , Chun-Nan Hsu

Figure 1 for Theoretical Knowledge Graph Reasoning via Ending Anchored Rules
Figure 2 for Theoretical Knowledge Graph Reasoning via Ending Anchored Rules
Figure 3 for Theoretical Knowledge Graph Reasoning via Ending Anchored Rules
Figure 4 for Theoretical Knowledge Graph Reasoning via Ending Anchored Rules
* Comparing to v2, v3 raises the lower bound of the connection set to be 2, which increases the performances on WN18RR for about 20 percent, and increases those on FB15K-237 for about 6 percent. People may refer to our presentation "EARDict_refinement" posted on github.com/ucsd-cmi/eardict for a detailed comparison between v2 and v3. We also revise our expressions a lot in v3 
   Access Paper or Ask Questions

A Survey of the State of Explainable AI for Natural Language Processing



Marina Danilevsky , Kun Qian , Ranit Aharonov , Yannis Katsis , Ban Kawas , Prithviraj Sen

Figure 1 for A Survey of the State of Explainable AI for Natural Language Processing
Figure 2 for A Survey of the State of Explainable AI for Natural Language Processing
Figure 3 for A Survey of the State of Explainable AI for Natural Language Processing
Figure 4 for A Survey of the State of Explainable AI for Natural Language Processing
* To appear in AACL-IJCNLP 2020 
   Access Paper or Ask Questions