Update README.md

README.md

@@ -1,3 +1,88 @@
 ---
 license: apache-2.0
 ---
+
+Big-Bird-base Span-detection model (based off extractive QA) for source detection.
+Similar to alex2awesome/quote-attribution__qa-model, except it's trained on a lot more data.
+
+Scores this accuracy on the original gold-label training dataset mentioned in: https://arxiv.org/pdf/2305.14904.pdf
+
+{'QUOTE_loss': 2.02297043800354,
+ 'QUOTE_f1': 0.6217389042457407,
+ 'QUOTE_e': 0.6541929666366095,
+ 'BACKGROUND_loss': 1.966481328010559,
+ 'BACKGROUND_f1': 0.6724386796945259,
+ 'BACKGROUND_e': 0.7012658227848101,
+ 'PUBLISHED WORK_loss': 3.9905383586883545,
+ 'PUBLISHED WORK_f1': 0.5010885605008405,
+ 'PUBLISHED WORK_e': 0.5612244897959183,
+ 'STATEMENT_loss': 2.5369534492492676,
+ 'STATEMENT_f1': 0.5674802724861037,
+ 'STATEMENT_e': 0.7133757961783439,
+ 'DOCUMENT_loss': 5.588709831237793,
+ 'DOCUMENT_f1': 0.29,
+ 'DOCUMENT_e': 0.35,
+ 'SOCIAL MEDIA POST_loss': 8.032715797424316,
+ 'SOCIAL MEDIA POST_f1': 0.07142857142857142,
+ 'SOCIAL MEDIA POST_e': 0.2857142857142857,
+ 'PRESS REPORT_loss': 5.140520095825195,
+ 'PRESS REPORT_f1': 0.4225235404896422,
+ 'PRESS REPORT_e': 0.5084745762711864,
+ 'DECLINED COMMENT_loss': 2.6083762645721436,
+ 'DECLINED COMMENT_f1': 0.375,
+ 'DECLINED COMMENT_e': 0.5625,
+ 'PROPOSAL/ORDER/LAW_loss': 3.4194986820220947,
+ 'PROPOSAL/ORDER/LAW_f1': 0.3006695221007098,
+ 'PROPOSAL/ORDER/LAW_e': 0.47058823529411764,
+ 'PRICE SIGNAL_loss': 6.789737701416016,
+ 'PRICE SIGNAL_f1': 0.28421052631578947,
+ 'PRICE SIGNAL_e': 0.3684210526315789,
+ 'NARRATIVE_loss': 1.577209711074829,
+ 'NARRATIVE_f1': 0.6666666666666667,
+ 'NARRATIVE_e': 0.7559055118110236,
+ 'Other: DIRECT OBSERVATION_loss': 6.768198013305664,
+ 'Other: DIRECT OBSERVATION_f1': 0.0,
+ 'Other: DIRECT OBSERVATION_e': 0.125,
+ 'COMMUNICATION, NOT TO JOURNO_loss': 3.517451524734497,
+ 'COMMUNICATION, NOT TO JOURNO_f1': 0.5239760062200494,
+ 'COMMUNICATION, NOT TO JOURNO_e': 0.578125,
+ 'PUBLIC SPEECH, NOT TO JOURNO_loss': 1.3050371408462524,
+ 'PUBLIC SPEECH, NOT TO JOURNO_f1': 0.3125,
+ 'PUBLIC SPEECH, NOT TO JOURNO_e': 0.8125,
+ 'PROPOSAL_loss': 8.1436128616333,
+ 'PROPOSAL_f1': 0.18582375478927204,
+ 'PROPOSAL_e': 0.27586206896551724,
+ 'TWEET_loss': 4.489321231842041,
+ 'TWEET_f1': 0.17647058823529413,
+ 'TWEET_e': 0.23529411764705882,
+ 'VOTE/POLL_loss': 5.416122913360596,
+ 'VOTE/POLL_f1': 0.36228119706380574,
+ 'VOTE/POLL_e': 0.34782608695652173,
+ 'LAWSUIT_loss': 5.852302551269531,
+ 'LAWSUIT_f1': 0.28687970379587147,
+ 'LAWSUIT_e': 0.4791666666666667,
+ 'DIRECT OBSERVATION_loss': 6.070340156555176,
+ 'DIRECT OBSERVATION_f1': 0.02,
+ 'DIRECT OBSERVATION_e': 0.2,
+ 'Other: PROPOSAL_loss': 1.81886887550354,
+ 'Other: PROPOSAL_f1': 0.6,
+ 'Other: PROPOSAL_e': 0.6,
+ 'Other: LAWSUIT_loss': 7.36419677734375,
+ 'Other: LAWSUIT_f1': 0.17647058823529413,
+ 'Other: LAWSUIT_e': 0.17647058823529413,
+ 'Other: Campaign filing_loss': 1.9355627298355103,
+ 'Other: Campaign filing_f1': 0.5009827476998723,
+ 'Other: Campaign filing_e': 0.5,
+ 'Other: Campaign Filing_loss': 1.6711688041687012,
+ 'Other: Campaign Filing_f1': 0.375,
+ 'Other: Campaign Filing_e': 0.375,
+ 'Other: Data Analysis_loss': 5.298102855682373,
+ 'Other: Data Analysis_f1': 0.0,
+ 'Other: Data Analysis_e': 0.0,
+ 'Other: Evaluation_loss': 2.1996216773986816,
+ 'Other: Evaluation_f1': 0.0,
+ 'Other: Evaluation_e': 0.6666666666666666,
+ 'full_loss': 2.4775373935699463,
+ 'full_f1': 0.5740516850389779,
+ 'full_e': 0.632161089052751}
+