Results

IMAGES SYS IMAGES GS
  F +T +S +TS RANK   F +T +S +TS RANK
Baseline 0.7127 0.4043 0.6251 0.4043   Baseline 0.8556 0.4799 0.7456 0.4799  
                       
DTSim_run3 0.8429 0.6276 0.7813 0.6095 1 UWB_run3 0.8922 0.6867 0.8408 0.6708 1
DTSim_run2 0.8429 0.6148 0.7806 0.599 2 UWB_run1 0.8937 0.6829 0.8397 0.6672 2
DTSim_run1 0.8429 0.6148 0.7591 0.587 3 DTSim_run3 0.8766 0.6675 0.8156 0.6483 3
Inspire_run1 0.7535 0.5638 0.7036 0.5625 4 DTSim_run2 0.8766 0.653 0.8144 0.6362 4
FBK-HLT-NLP_run1 0.8427 0.5655 0.7862 0.5475 5 DTSim_run1 0.8766 0.653 0.7955 0.6238 5
Inspire_run2 0.8166 0.5428 0.7416 0.5355 6 UWB_run2 0.8713 0.6346 0.8083 0.6206 6
FBK-HLT-NLP_run3 0.8418 0.5541 0.7847 0.5351 7 Inspire_run1 0.7971 0.614 0.7484 0.613 7
FBK-HLT-NLP_run2 0.8427 0.5179 0.7807 0.4969 8 Inspire_run2 0.8674 0.5957 0.7945 0.5877 8
IISCNLP_run2 0.8459 0.4993 0.777 0.4872 9 FBK-HLT-NLP_run1 0.8728 0.5945 0.8147 0.5739 9
IISCNLP_run1 0.8335 0.4862 0.7654 0.4744 10 Venseseval_run1 0.8443 0.5789 0.8046 0.5735 10
IISCNLP_run3 0.8335 0.4862 0.7654 0.4744 11 FBK-HLT-NLP_run3 0.8786 0.5884 0.8193 0.5656 11
Venseseval_run1 0.7428 0.4667 0.6949 0.4624 12 VRep_run1 0.8539 0.5516 0.7651 0.5478 12
Inspire_run3 0.8105 0.4533 0.7348 0.45 13 VRep_run3 0.8546 0.5511 0.7652 0.5473 13
            VRep_run2 0.8573 0.5468 0.7633 0.5429 14
*iUBC_run2 0.8557 0.5606 0.7961 0.5504   FBK-HLT-NLP_run2 0.8789 0.543 0.8178 0.525 15
*iUBC_run3 0.8557 0.5232 0.7936 0.5162   IISCNLP_run2 0.8929 0.5247 0.8231 0.5088 16
*iUBC_run1 0.8557 0.4888 0.7703 0.4773   Rev_run1 0.831 0.5014 0.7399 0.4929 17
            IISCNLP_run3 0.8929 0.505 0.8264 0.4915 18
            Inspire_run3 0.855 0.489 0.7806 0.4865 19
            IISCNLP_run1 0.8929 0.5015 0.8285 0.4845 20
                       
            *iUBC_run2 0.9077 0.622 0.8552 0.612  
            *iUBC_run3 0.9077 0.5868 0.8455 0.5775  
            *iUBC_run1 0.9077 0.5195 0.8162 0.5125  

HEADLINES SYS HEADLINES GS
  F +T +S +TS RANK   F +T +S +TS RANK
Baseline 0.6486 0.4379 0.5912 0.4379   Baseline 0.8462 0.5462 0.761 0.5461  
                       
DTSim_run2 0.8366 0.5605 0.7595 0.5467 1 Inspire_run1 0.8194 0.7031 0.7865 0.696 1
DTSim_run3 0.8376 0.5595 0.7586 0.5446 2 Inspire_run2 0.892 0.6725 0.8315 0.6627 2
DTSim_run1 0.8366 0.5605 0.7394 0.5384 3 DTSim_run2 0.9072 0.665 0.836 0.6487 3
Inspire_run1 0.7038 0.5263 0.6593 0.52 4 DTSim_run3 0.9072 0.6583 0.8329 0.6405 4
FBK-HLT-NLP_run1 0.8078 0.5234 0.7374 0.5099 5 DTSim_run1 0.9072 0.665 0.8187 0.6385 5
FBK-HLT-NLP_run3 0.805 0.5185 0.7374 0.5054 6 UWB_run3 0.8987 0.6412 0.8382 0.6296 6
FBK-HLT-NLP_run2 0.7973 0.5138 0.7309 0.5028 7 UWB_run1 0.8979 0.6319 0.8346 0.6212 7
Inspire_run2 0.759 0.5028 0.6911 0.495 8 UWB_run2 0.8897 0.6146 0.815 0.6013 8
IISCNLP_run2 0.821 0.508 0.7401 0.4919 9 VRep_run3 0.8934 0.6024 0.8051 0.5973 9
IISCNLP_run1 0.8105 0.4888 0.723 0.4686 10 VRep_run2 0.9007 0.6032 0.8078 0.5972 10
IISCNLP_run3 0.8105 0.4944 0.721 0.4685 11 VRep_run1 0.8908 0.6015 0.8027 0.5964 11
Venseseval_run1 0.7081 0.4679 0.6493 0.4531 12 Inspire_run3 0.8972 0.5893 0.8178 0.5791 12
Inspire_run3 0.769 0.4554 0.6868 0.4459 13 Venseseval_run1 0.8731 0.5927 0.8099 0.5729 13
            Rev_run1 0.8662 0.5705 0.7844 0.5624 14
*iUBC_run3 0.809 0.5066 0.7385 0.4976   FBK-HLT-NLP_run3 0.8853 0.5771 0.8089 0.562 15
*iUBC_run2 0.809 0.4856 0.7376 0.4757   FBK-HLT-NLP_run1 0.879 0.5744 0.8096 0.5591 16
*iUBC_run1 0.809 0.4311 0.7143 0.4229   IISCNLP_run2 0.9134 0.5755 0.829 0.5555 17
            FBK-HLT-NLP_run2 0.8859 0.5643 0.8019 0.5554 18
            IISCNLP_run1 0.9144 0.5734 0.82 0.5509 19
            IISCNLP_run3 0.9144 0.567 0.8206 0.5405 20
                       
            *iUBC_run3 0.9278 0.6017 0.8582 0.5915  
            *iUBC_run2 0.9278 0.6003 0.8607 0.587  
            *iUBC_run1 0.9278 0.512 0.83 0.5049  

ANSWER-STUDENTS SYS ANSWER-STUDENTS GS
  F +T +S +TS RANK   F +T +S +TS RANK
Baseline 0.6188 0.4431 0.5702 0.4431   Baseline 0.8203 0.5566 0.7464 0.5566  
                       
FBK-HLT-NLP_run3 0.8166 0.5613 0.7574 0.5547 1 IISCNLP_run1 0.8684 0.6511 0.8245 0.6385 1
IISCNLP_run3 0.7563 0.5604 0.71 0.5451 2 IISCNLP_run3 0.8684 0.6511 0.8245 0.6385 2
FBK-HLT-NLP_run1 0.8162 0.5479 0.7589 0.542 3 UWB_run1 0.8644 0.6299 0.8089 0.6248 3
FBK-HLT-NLP_run2 0.8161 0.5434 0.7481 0.5405 4 IISCNLP_run2 0.8684 0.627 0.8263 0.6167 4
IISCNLP_run1 0.756 0.5525 0.71 0.5397 5 UWB_run3 0.8588 0.6167 0.8038 0.6114 5
IISCNLP_run2 0.7449 0.5317 0.6995 0.5198 6 FBK-HLT-NLP_run3 0.8505 0.5984 0.7896 0.589 6
DTSim_run2 0.8165 0.5157 0.7367 0.5074 7 FBK-HLT-NLP_run1 0.8775 0.5888 0.8102 0.5808 7
DTSim_run1 0.8165 0.5157 0.7248 0.5049 8 VRep_run3 0.8785 0.5823 0.7916 0.5799 8
DTSim_run3 0.8181 0.5112 0.736 0.5029 9 VRep_run2 0.8702 0.5814 0.7849 0.5792 9
Inspire_run1 0.6896 0.4554 0.6401 0.4524 10 FBK-HLT-NLP_run2 0.859 0.5758 0.791 0.5714 10
Inspire_run2 0.7246 0.4238 0.6525 0.4191 11 DTSim_run2 0.8584 0.5552 0.7809 0.5458 11
Inspire_run3 0.7617 0.3426 0.6697 0.3381 12 DTSim_run1 0.8584 0.5552 0.7686 0.5432 12
            DTSim_run3 0.8614 0.5468 0.7798 0.5374 13
*iUBC_run2 0.7963 0.5651 0.748 0.5592   VRep_run1 0.7723 0.5249 0.7014 0.5226 14
*iUBC_run3 0.7963 0.5651 0.748 0.5592   Inspire_run1 0.7949 0.5134 0.7349 0.5103 15
*iUBC_run1 0.7963 0.4499 0.7099 0.4493   Inspire_run2 0.8205 0.4828 0.744 0.4789 16
            UWB_run2 0.8752 0.4806 0.7826 0.4748 17
            Rev_run1 0.8458 0.4179 0.7265 0.4104 18
            Inspire_run3 0.8742 0.3914 0.7704 0.3855 19
                       
            *iUBC_run2 0.8922 0.6506 0.8433 0.6441  
            *iUBC_run3 0.8922 0.6506 0.8433 0.6441  
            *iUBC_run1 0.8922 0.5016 0.7939 0.4994  

  I-SYS H-SYS AS-SYS MEAN     I-GS H-GS AS-GS MEAN  
  F+TS F+TS F+TS F+TS Rank   F+TS F+TS F+TS F+TS Rank
Baseline 0.4043 0.4379 0.4431 0.4284333333   Baseline 0.4799 0.5461 0.5566 0.5275333333  
                       
DTSim_run3 0.6095 0.5446 0.5029 0.5523333333 1 UWB_run1 0.6672 0.6212 0.6248 0.6377333333 1
DTSim_run2 0.599 0.5467 0.5074 0.5510333333 2 UWB_run3 0.6708 0.6296 0.6114 0.6372666667 2
DTSim_run1 0.587 0.5384 0.5049 0.5434333333 3 DTSim_run2 0.6362 0.6487 0.5458 0.6102333333 3
FBK-HLT-NLP_run1 0.5475 0.5099 0.542 0.5331333333 4 DTSim_run3 0.6483 0.6405 0.5374 0.6087333333 4
FBK-HLT-NLP_run3 0.5351 0.5054 0.5547 0.5317333333 5 Inspire_run1 0.613 0.696 0.5103 0.6064333333 5
FBK-HLT-NLP_run2 0.4969 0.5028 0.5405 0.5134 6 DTSim_run1 0.6238 0.6385 0.5432 0.6018333333 6
Inspire_run1 0.5625 0.52 0.4524 0.5116333333 7 Inspire_run2 0.5877 0.6627 0.4789 0.5764333333 7
IISCNLP_run2 0.4872 0.4919 0.5198 0.4996333333 8 VRep_run3 0.5473 0.5973 0.5799 0.5748333333 8
IISCNLP_run3 0.4744 0.4685 0.5451 0.496 9 VRep_run2 0.5429 0.5972 0.5792 0.5731 9
IISCNLP_run1 0.4744 0.4686 0.5397 0.4942333333 10 FBK-HLT-NLP_run3 0.5656 0.562 0.589 0.5722 10
Inspire_run2 0.5355 0.495 0.4191 0.4832 11 FBK-HLT-NLP_run1 0.5739 0.5591 0.5808 0.5712666667 11
Inspire_run3 0.45 0.4459 0.3381 0.4113333333 12 UWB_run2 0.6206 0.6013 0.4748 0.5655666667 12
Venseseval_run1 0.4624 0.4531 - -   IISCNLP_run2 0.5088 0.5555 0.6167 0.5603333333 13
            IISCNLP_run1 0.4845 0.5509 0.6385 0.5579666667 14
*iUBC_run2 0.5504 0.4757 0.5592 0.5284333333   IISCNLP_run3 0.4915 0.5405 0.6385 0.5568333333 15
*iUBC_run3 0.5162 0.4976 0.5592 0.5243333333   VRep_run1 0.5478 0.5964 0.5226 0.5556 16
*iUBC_run1 0.4773 0.4229 0.4493 0.4498333333   FBK-HLT-NLP_run2 0.525 0.5554 0.5714 0.5506 17
            Rev_run1 0.4929 0.5624 0.4104 0.4885666667 18
            Inspire_run3 0.4865 0.5791 0.3855 0.4837 19
            Venseseval_run1 0.5735 0.5729 - -  
                       
            *iUBC_run2 0.612 0.587 0.6441 0.6143666667  
            *iUBC_run3 0.5775 0.5915 0.6441 0.6043666667  
            *iUBC_run1 0.5125 0.5049 0.4994 0.5056  

(*) Runs by team which includes organizers

Contact Info

Organizers

  • Eneko Agirre
  • Aitor Gonzalez-Agirre
  • Inigo Lopez-Gazpio
  • Montse Maritxalar
  • German Rigau
  • Larraitz Uria
  • University of the Basque Country (UPV/EHU)

email : ists-semeval@googlegroups.com

group : Interpretable STS SemEval

Other Info