Lecture: Introduction

Neural Machine Translation

• Sequence to Sequence Learning with Neural Networks Sutskever et al, NeurIPS 2014
• Neural machine translation by jointly learning to align and translate Bahdanau et al, ICLR 2015

Input / Output Representation

• Neural Machine Translation of Rare Words with Subword Units. Sennrich et al, ACL 2016
• A Character-Level Decoder without Explicit Segmentation for Neural Machine Translation. Chung et al, ACL 16

Decoding

• Non-Autoregressive Neural Machine Translation. Gu et al, ICLR 2018
• The curious case of neural text degeneration. Holtzman et al, ICLR 2020

• Consistency of a Recurrent Language Model With Respect to Incomplete Decoding. Welleck et al, ArXiV, 2020

Unsupervised

• Unsupervised Machine Translation Using Monolingual Corpora Only. Lample et al, 2018
• The Summary Loop: Learning to Write Abstractive Summaries Without Examples. Laban et al, ACL 2020

Summarization

• Get To The Point: Summarization with Pointer-Generator Networks. See et al, ACL 2017
• BART: Denoising Sequence-to-Sequence Pre-taining for Natural Language Generation, Translation, and Comprehension. Lewis et al, ACL 2020

Data-to-Text

• Challenges in Data-to Text Generation. Wiseman et al, EMNLP 2018
• ToTTo: A Controlled Table-To-Text Generation Dataset. Parikh et al, ArXiv, 2020

• A Global Model for Concept-to-Text Generation. Konstas et al, JAIR 2017

Models with Auxiliary Objective

• STACL: Simultaneous Translation with Implicit Anticipation and Controllable Latency using Prefix-to-Prefix Framework. Ma et al, ACL 2019
• Plug and play language models: a simple approach to controlled text generation. Sathathri et al, ICLR 2020

Evaluation

• Evaluation of Text Generation: A Survey. Celikyilmaz et al, ArXiv, 2020

Final Project Proposal Discussion

Image 1

• Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering. Goyal et al, CVPR 2017
• Generating Natural Questions About an Image. Mostafazadeh et al, ACL 2016

Image 2

• Clue: Cross-modal Coherence Modeling for Caption GenerationAlikhani et al, ACL 2020
• Grounded Situation Recognition Pratt et al, ArXiv, 2020

Action 1

• CHARTDIALOGS: Plotting from Natural Language Instructions Shao et al, ACL 2020
• Executing Instructions in Situated Collaborative Interactions. Suhr et al, EMNLP 2019

Action 2

• ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks. Shridhar et al, CVPR 2020
• Grounded Language in Play Lynch et al, ArXiv 2020

Speech

Guest Lecture: David Harwath

Navigation

• Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments. Andersen et al, CVPR 2018
• Grounded Language Learning in a Simulated 3D World Hermann et al,

Society 1

• Echoes of power: Language effects and power differences in social interaction. Danescu-Niculescu-Mizil et al, WWW, 2012.
• Language from police body camera footage shows racial disparities in officer respect. Voigt et al, PNAS 2017

Society 2

• Deal or No Deal? End-to-End Learning for Negotiation Dialogues. Lewis et al, EMNLP 2017
• SOCIAL BIAS FRAMES: Reasoning about Social and Power Implications of Language. Sap et al, ACL 2020

QA over KnowledgeBase

• Question Answering on Knowledge Bases and Text using Universal Schema and Memory Networks Das et al, ACL 17
• Facts As Experts Verga et al, ArXiv 2020

Reading Comprehension

• BI-DIRECTIONAL ATTENTION FLOW FOR MACHINE COMPREHENSION. Seo et al, ICLR 2017
• NEURAL MODULE NETWORKS FOR REASONING OVER TEXT. Gupta et al, ICLR 2020

Open domain

• REALM: Retrieval-Augmented Language Model Pre-Training. Lee et al, ICML 2020
• How Much Knowledge Can You Pack Into the Parameters of a Language Model?. Roberts et al, ArXiv 2020

Dataset

• DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs. Due et al, NAACL 2019
• SOCIAL IQA: Commonsense Reasoning about Social Interactions. Sap et al, EMNLP 2019

Question Generation / Evaluation

• Asking and Answering Questions to Evaluate the Factual Consistency of Summaries. Wang et al, ACL 2020
• Unsupervised Question Answering by Cloze Translation. Lewis et al, ACL 2019

Interpretability and Faithfulness

• Obtaining Faithful Interpretations from Compositional Neural Networks. Subramanian et al, ACL 2020
• QED: A Framework and Dataset for Explanations in Question Answering. Lamm et al, ArXiv

Reframing other problems as QA

• CorefQA: Coreference Resolution as Query-based Span Prediction. Wu et al, ACL 2020
• Zero-Shot Relation Extraction via Reading Comprehension. Levy et al, CoNLL 2017

Lecture - Unexplored Topics