Update README.md

README.md

@@ -26,15 +26,27 @@ The above data archive mainly contains the following resource files:
 
 - **Type Embedding**: Adopted to compute type similarity between mention-entity pairs. We trained these type embedding using a typing system called [NFETC](https://arxiv.org/abs/1803.03378) model.
 
-- **Wikipedia inLinks and outLinks**: Surface names of inlinks and outlinks for a Wikipedia page (entity) are used to construct **dynamic context** in our model learning process.
+- **Wikipedia inLinks**: Surface names of inlinks for a Wikipedia page (entity) are used to construct **dynamic context** in our model learning process.
 
 ## Installation
 Requirements: Python 3.5 or 3.6, Pytorch 0.3, CUDA 7.5 or 8
 
 ## Important Parameters
+
 ```
-mode: train or eval
-order: three decision orders, that is, 1) *Offset* links all mentions by their natural orders in the original documen
+mode: train or eval mode.
+
+order: three decision orders -- offset / size / random. Please refer to our paper for their concrete definition.
+
+n_cands_before_rank: the number of candidates, the default value is 30.
+
+tok_top_n4inlink: the number of inlinks for a Wikipedia page (entity) would be considered as candidates for the dynamic context.
+
+tok_top_n4ent: the number of inlinks for a Wikipedia page (entity) would be added into the dynamic context.
+
+isDynamic: 2-hop DCA / 1-hop DCA / without DCA. Corresponding to the Table 4 in our paper.
+
+dca_method: soft+hard attention / soft attention / average sum. Corresponding to the Table 5 in our paper.
 ```
 
 ## Running