Update README.md

README.md

@@ -13,6 +13,19 @@ widget:
   example_title: "Example 1"
 - text: "In this work, we explore how to learn taskspecific language models aimed towards learning rich representation of keyphrases fromtext documents. We experiment with different masking strategies for pre-training transformer language models (LMs) in discriminative as well as generative settings. In thediscriminative setting, we introduce a newpre-training objective - Keyphrase BoundaryInfilling with Replacement (KBIR), showinglarge gains in performance (upto 9.26 pointsin F1) over SOTA, when LM pre-trained usingKBIR is fine-tuned for the task of keyphraseextraction. In the generative setting, we introduce a new pre-training setup for BART - KeyBART, that reproduces the keyphrases relatedto the input text in the CatSeq format, insteadof the denoised original input. This also ledto gains in performance (upto 4.33 points inF1@M) over SOTA for keyphrase generation.Additionally, we also fine-tune the pre-trainedlanguage models on named entity recognition(NER), question answering (QA), relation extraction (RE), abstractive summarization andachieve comparable performance with that ofthe SOTA, showing that learning rich representation of keyphrases is indeed beneficial formany other fundamental NLP tasks."
   example_title: "Example 2"
+model-index:
+- name: DeDeckerThomas/keyphrase-extraction-kbir-inspec
+  results:
+  - task: 
+      type: keyphrase-extraction
+      name: Keyphrase Extraction
+    dataset:
+      type: midas/inspec
+      name: inspec
+    metrics:
+      - type: seqeval    # Required. Example: wer
+        value: 0.58  # Required. Example: 20.90
+        name: F1-score    # Optional. Example: Test WER
 ---
 ** Work in progress **
 # 🔑 Keyphrase Extraction model: KBIR-inspec