Create README.md

README.md

@@ -0,0 +1,38 @@
+# Text Summarization
+This is a assignment of Applied Deep Learning which is a course of National Taiwan University(NTU).
+### Task Description：Chinese News Summarization (Title Generation)
+input(news content)：
+```
+從小就很會念書的李悅寧， 在眾人殷殷期盼下，以榜首之姿進入臺大醫學院， 但始終忘不了對天文的熱情。大學四年級一場遠行後，她決心遠赴法國攻讀天文博士。 從小沒想過當老師的她，再度跌破眾人眼鏡返台任教，......
+```
+output(news title)：
+```
+榜首進台大醫科卻休學 、27歲拿到法國天文博士 李悅寧跌破眾人眼鏡返台任教
+```
+### Objective
+- Fine-tune a pre-trained model：[google/mt5-small](https://huggingface.co/google/mt5-small) to pass the baseline.
+- Compare the difference between beam search, top k sampling, top p sampling, temperature.
+  ```
+  Baseline(f1-score)：rouge-1: 22.0, rouge-2: 8.5, rouge-L: 20.5
+  ```
+### Experiments
+- Greedy   
+  After the model generate the probility of every token as result, Greedy is the simplest way to choose the next word with most probable word(argmax).
+  However, there is a problem that it's easy to choose the duplicate word with Greedy strategy.
+  ```
+  Greedy Result(f1-score)：rouge-1: 15.7, rouge-2: 4.9, rouge-L: 14.8  
+  ``` 
+- Beam Search  
+  Beam Search strategy is keeping track of the k most probable sentences and finding the best one as a result.
+  Therefore, if beam size is setting as 1, it becomes Greedy. We can say that beam search kind of solves the problem of Greedy.
+  However, if beam size is too large, the result will turn into too generic and less relevant though the result is safe and "correct".
+  For example
+  ```
+  I love to listen Taylor Swift's songs so I decide to participate the concert of Taylor.
+  ```
+- Top k Sampling  
+  
+- Top p Sampling  
+  
+- Temperature  
+