Publications/fuSE_ACL20.md

@@ -5,7 +5,7 @@ Conference: 58th Annual Meeting of the Association for Computational Linguistics
 
 [Paper](https://www.aclweb.org/anthology/2020.acl-main.395/)  
 [Presentation (Video)](https://slideslive.com/38928791/programming-in-natural-language-with-fuse-synthesizing-methods-from-spoken-utterances-using-deep-natural-language-understanding)  
-[Slides]()
+[Slides](acl20_main.pdf)
 
 __Abstract__: The key to effortless end-user programming is natural language. We examine how to teach intelligent systems new functions, expressed in natural language. As a first step, we collected 3168 samples of teaching efforts in plain English. Then we built fuSE, a novel system that translates English function descriptions into code. Our approach is three-tiered and each task is evaluated separately. We first classify whether an intent to teach new functionality is present in the utterance (accuracy: 97.7% using BERT). Then we analyze the linguistic structure and construct a semantic model (accuracy: 97.6% using a BiLSTM). Finally, we synthesize the signature of the method, map the intermediate steps (instructions in the method body) to API calls and inject control structures (F1: 67.0% with information retrieval and knowledge-based methods). In an end-to-end evaluation on an unseen dataset fuSE synthesized 84.6% of the method signatures and 79.2% of the API calls correctly.
 
@@ -23,4 +23,4 @@ __Abstract__: The key to effortless end-user programming is natural language. We
   address = {{Online}},
   abstract = {The key to effortless end-user programming is natural language. We examine how to teach intelligent systems new functions, expressed in natural language. As a first step, we collected 3168 samples of teaching efforts in plain English. Then we built fuSE, a novel system that translates English function descriptions into code. Our approach is three-tiered and each task is evaluated separately. We first classify whether an intent to teach new functionality is present in the utterance (accuracy: 97.7\% using BERT). Then we analyze the linguistic structure and construct a semantic model (accuracy: 97.6\% using a BiLSTM). Finally, we synthesize the signature of the method, map the intermediate steps (instructions in the method body) to API calls and inject control structures (F1: 67.0\% with information retrieval and knowledge-based methods). In an end-to-end evaluation on an unseen dataset fuSE synthesized 84.6\% of the method signatures and 79.2\% of the API calls correctly.}
 }
-```
\ No newline at end of file
+```