update readme

README.md

@@ -9,7 +9,8 @@ In this paper, we propose DictBERT, which is a novel pre-trained language model
 
 ## Evaluation results
 
-When fine-tuned BERT and our DictBERT on GLEU benchmarks tasks. CoLA is evaluated by matthews, STS-B is evaluated by pearson, and others are evaluated by accuracy. DictBERT model achieves the following results:
+We show performance of fine-tuning BERT and DictBERT on the GLEU benchmarks tasks. CoLA is evaluated by matthews, STS-B is evaluated by pearson, and other tasks are evaluated by accuracy. The models achieve the following results:
+
 
 | | MNLI | QNLI | QQP | SST-2 | CoLA | MRPC | RTE | STS-B | Average |
 |:----:|:-----------:|:----:|:----:|:-----:|:----:|:-----:|:----:|:----:|:-------:|
@@ -18,6 +19,13 @@ When fine-tuned BERT and our DictBERT on GLEU benchmarks tasks. CoLA is evaluate
 
 HF: huggingface checkpoint for BERT-base uncased
 
+If no dictionary if provided during fine-tuning, DictBERT can still achieve better performance than BERT. 
+
+| | MNLI | QNLI | QQP | SST-2 | CoLA | MRPC | RTE | STS-B | Average |
+|:----:|:-----------:|:----:|:----:|:-----:|:----:|:-----:|:----:|:----:|:-------:|
+| w/o dict | 84.24 | 90.99 | 90.80 | 92.51 | 60.50 | 87.04 | 73.75 | 89.37 | 83.69 |
+
+
 ### BibTeX entry and citation info
 
 ```bibtex