ECE594: Mathematical models of Language (Evolving Schedule)

 

Date Topic/Paper Presenter(s) Readings Feedback providers Assignment due
01/26/21 Introduction Suma Bhat      
01/28/21 Word-level models (slides) Suma Bhat

JM_2 Chapter 2; JM_3 Chapter 6Linguistic fundamentals (Chapter 2) 

 Heting  
02/02/21 Word-level models (slides) Suma Bhat GloVe: Global Vectors for Word Representation    
JM_3 Chapters 4 and 5  
   
   
02/04/21 Analysis Methods in Neural Language Processing: A Survey Emily   Razan  
Probing Pretrained Language Models for Lexical Semantics John Heting  
   
02/09 Sequence-level models (slides) Suma Bhat JM_3 Chapter 3    
JM_3 Chapter 8  
R3  
R4  
02/11/21 Exploring and Predicting Transferability across NLP Tasks Ziheng   F1  
Do We Really Need Fully Unsupervised Cross-Lingual Embeddings? Heting F2

Assignment 1 posted

colab link (due 2/20/21)

F3  
02/16/21 Modeling meaning (slides) Suma Bhat JM_3 Chapter 14    
JM_3 Chapter 19  
   
   
02/18/21
SentiLARE: Sentiment-Aware Language Representation Learning with Linguistic Knowledge
John   Brianna  
What Kind of Language is Hard to Language-Model? Razan Liming  
Heting  
02/23/21 Low-Resource NLP (slides) Suma Bhat      
   
   
   
02/25/21 Deep Semantic Role Labeling: What Works and What’s Next Liming   John  
Linguistically-Informed Self-Attention for Semantic Role Labeling Jerome Mahir  
 

Project Proposal 

due (extended to 2/26)

03/02/21 Summarization (slides) Suma Bhat JM_2 23.3-23.6    
   
   
   
03/04/21 A systematic comparison of methods for low-resource dependency parsing on genuinely low-resource languages Mahir   Ziheng

 

Neural Unsupervised Domain Adaptation in NLP—A Survey Jerome Jianing  
Emily  
03/09/21 Dialog (slides) Suma Bhat JM_3 Chapter 24    

Recent Neural Methods on Slot Filling and Intent Classification for Task-Oriented Dialogue Systems: A Survey

 

Survey on evaluation methods for dialogue systems

 

What Makes a Good Conversation?: Challenges in Designing Truly Conversational Agents

 
03/11/21 On Faithfulness and Factuality in Abstractive Summarization Brianna   Jerome  
Searching for Effective Neural Extractive Summarization: What Works and What’s Next Heting Emily

Assignment 2 posted

(due 03/25/21)

Chenyang  
03/16/21 Question Answering (slides) (video) Suma Bhat JM_3 Chapter 23    
   
   
   
03/18 Can You Put it All Together: Evaluating Conversational Agents’ Ability to Blend Skills Jianing   Ziheng  
DyKgChat: Benchmarking Dialogue Generation Grounding on Dynamic Knowledge Graphs Yuchen Chenyang  
   
03/23/21 Commonsense Reasoning (slides)        
   
   
   
03/25/21 Natural Questions: A Benchmark for Question Answering Research Emily   Mahir  
Towards Medical Machine Reading Comprehension with Structural Knowledge and Plain Text Razan Liming  
   
03/30/21 Project Updates (~8 minute presentation per project)        
   
   
 

Assignment 3 posted

(due 04/15/21)

04/01/21 COMET: Commonsense Transformers for Automatic Knowledge Graph Construction Mahir   Yuchen  
Diverse and Informative Dialogue Generation with Context-Specific Commonsense Knowledge Awareness Brianna ChenYang  
   
04/06/21 Ethics, Bias, and Abusive Language   R1    
R2  
R3  
R4  
04/08/21 Double-Hard Debias: Tailoring Word Embeddings for Gender Bias Mitigation Ziheng   F1  
Facilitating the Communication of Politeness through Fine-Grained Paraphrasing Jianing F2  
F3  
04/13/21 BREAK (no lecture)   R1    
R2  
R3  
R4  
04/15/21

Language from police body camera footage shows racial disparities in officer respect

Relevant Document Discovery for Fact-Checking Articles

 

ChenYang

Yuchen

R1    
R2  
R3  
R4  
04/20/21 Interpreting Euphemisms and Countering Hatespeech Wanzheng Zhu R1    
R2  
R3  
R4  
04/22/21 The spread of true and false news online ChenYang   F1  
Adapting and Extending a Typology to Identify Vaccine Misinformation on Twitter Liming F2  
F3  
04/27/21 Project Presentations        
04/29/21 Project Presentations        
05/04/21 Project Presentations