Paper-Reading

Paper reading list in natural language processing, with special emphasis on dialogue systems and text generation related topics. This repo will keep updating 🤗 ...

• Paper-Reading
  • Deep Learning in NLP
  • Pre-trained Language Models
  • Dialogue System
  • PTMs for Dialogue
  • Knowledge-grounded Dialogue
  • Task-oriented Dialogue
  • Open-domain Dialogue
  • Personalized Dialogue
  • Miscellaneous
  • Text Generation
  • Knowledge Representation Learning
  • Text Summarization
  • Topic Modeling
  • Machine Translation
  • Question Answering
  • Reading Comprehension
  • Image Captioning

Deep Learning in NLP

• CNM: "CNM: An Interpretable Complex-valued Network for Matching". NAACL(2019) [PDF] [code]
• word2vec: "word2vec Parameter Learning Explained". arXiv(2016) [PDF] :star::star::star::star::star:
• Glove: "GloVe: Global Vectors for Word Representation". EMNLP(2014) [PDF] [code]
• ELMo: "Deep contextualized word representations". NAACL(2018) [PDF] [code]
• VAE: "An Introduction to Variational Autoencoders". arXiv(2019) [PDF]
• Transformer: "Attention is All you Need". NeurIPS(2017) [PDF] [code-official] [code-tf] [code-py]
• Transformer-XL: "Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context". ACL(2019) [PDF] [code]
• ConvS2S: "Convolutional Sequence to Sequence Learning". ICML(2017) [PDF]
• Survey on Attention: "An Introductory Survey on Attention Mechanisms in NLP Problems". arXiv(2018) [PDF] :star::star::star::star::star:
• Additive Attention: "Neural Machine Translation by Jointly Learning to Align and Translate". ICLR(2015) [PDF]
• Multiplicative Attention: "Effective Approaches to Attention-based Neural Machine Translation". EMNLP(2015) [PDF]
• Memory Net: "End-To-End Memory Networks". NeurIPS(2015) [PDF]
• Pointer Net: "Pointer Networks". NeurIPS(2015) [PDF]
• Copying Mechanism: "Incorporating Copying Mechanism in Sequence-to-Sequence Learning". ACL(2016) [PDF]
• Coverage Mechanism: "Modeling Coverage for Neural Machine Translation". ACL(2016) [PDF]
• GAN: "Generative Adversarial Nets". NeurIPS(2014) [PDF]
• SeqGAN: "SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient". AAAI(2017) [PDF] [code]
• MacNet: "MacNet: Transferring Knowledge from Machine Comprehension to Sequence-to-Sequence Models". NeurIPS(2018) [PDF]
• Pretrained Seq2Seq: "Unsupervised Pretraining for Sequence to Sequence Learning". EMNLP(2017) [PDF]
• Multi-task Learning: "An Overview of Multi-Task Learning in Deep Neural Networks". arXiv(2017) [PDF]
• Gradient Descent: "An Overview of Gradient Descent Optimization Algorithms". arXiv(2016) [PDF] :star::star::star::star::star:

Pre-trained Language Models

• PTMs: "Pre-trained Models for Natural Language Processing: A Survey". arXiv(2020) [PDF]
• ERNIE-GEN: "ERNIE-GEN: An Enhanced Multi-Flow Pre-training and Fine-tuning Framework for Natural Language Generation". IJCAI(2020) [PDF] [code]
• Poly-encoder: "Poly-encoders: Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scorings". ICLR(2020) [PDF] :star::star::star::star::star:
• ALBERT: "ALBERT: A Lite BERT for Self-supervised Learning of Language Representations". ICLR(2020) [PDF]
• TinyBERT: "TinyBERT: Distilling BERT for Natural Language Understanding". arXiv(2019) [PDF] [code]
• Chinese BERT: "Pre-Training with Whole Word Masking for Chinese BERT". arXiv(2019) [PDF] [code]
• SpanBERT: "SpanBERT: Improving Pre-training by Representing and Predicting Spans". TACL(2020) [PDF] [code]
• RoBERTa: "RoBERTa: A Robustly Optimized BERT Pretraining Approach". arXiv(2019) [PDF] [code]
• ERNIE(Tsinghua): "ERNIE: Enhanced Language Representation with Informative Entities". ACL(2019) [PDF] [code]
• ERNIE(Baidu): "ERNIE: Enhanced Representation through Knowledge Integration". arXiv(2019) [PDF] [code]
• UniLM: "Unified Language Model Pre-training for Natural Language Understanding and Generation". NeurIPS(2019) [PDF] [code] :star::star::star::star::star:
• XLNet: "XLNet: Generalized Autoregressive Pretraining for Language Understanding". NeurIPS(2019) [PDF] [code]
• XLM: "Cross-lingual Language Model Pretraining". NeurIPS(2019) [PDF] [code]
• BERT: "BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding". NAACL(2019) [PDF] [code] :star::star::star::star::star:

Dialogue System

PTMs for Dialogue

• CDial-GPT: "A Large-Scale Chinese Short-Text Conversation Dataset". NLPCC(2020) [PDF] [code]
• ToD-BERT: "ToD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialogues". arXiv(2020) [PDF] [code]
• DialoGPT: "DialoGPT : Large-Scale Generative Pre-training for Conversational Response Generation". ACL(2020) [PDF] [code]
• PLATO: "PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable". ACL(2020) [PDF] [code]
• Guyu: "An Empirical Investigation of Pre-Trained Transformer Language Models for Open-Domain Dialogue Generation". arXiv(2020) [PDF] [code]

Knowledge-grounded Dialogue

• DiffKS: "Difference-aware Knowledge Selection for Knowledge-grounded Conversation Generation". EMNLP-Findings(2020) [PDF] [code]
• DukeNet: "DukeNet: A Dual Knowledge Interaction Network for Knowledge-Grounded Conversation". SIGIR(2020) [PDF] [code]
• CCN: "Cross Copy Network for Dialogue Generation". EMNLP(2020) [PDF] [code]
• PIPM: "Bridging the Gap between Prior and Posterior Knowledge Selection for Knowledge-Grounded Dialogue Generation". EMNLP(2020) [PDF]
• KIC: "Generating Informative Conversational Response using Recurrent Knowledge-Interaction and Knowledge-Copy". ACL(2020) [PDF]
• SKT: "Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue". ICLR(2020) [PDF] [code] :star::star::star::star:
• DuRecDial: "Towards Conversational Recommendation over Multi-Type Dialogs". ACL(2020) [PDF] [code]
• KdConv: "KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven Conversation". ACL(2020) [PDF] [data] :star::star::star:
• RefNet: "RefNet: A Reference-aware Network for Background Based Conversation". AAAI(2020) [PDF] [code]
• GLKS: "Thinking Globally, Acting Locally: Distantly Supervised Global-to-Local Knowledge Selection for Background Based Conversation". AAAI(2020) [PDF] [code]
• DuConv: "Proactive Human-Machine Conversation with Explicit Conversation Goals". ACL(2019) [PDF] [code]
• KBRD: "Towards Knowledge-Based Recommender Dialog System". EMNLP(2019) [PDF] [code] :star::star::star::star:
• ReDial: "Towards Deep Conversational Recommendations". NeurIPS(2018) [PDF] [data]
• Dual Fusion: "Smarter Response with Proactive Suggestion: A New Generative Neural Conversation Paradigm". IJCAI(2018) [PDF]

Task-oriented Dialogue

• DDMN: "Dual Dynamic Memory Network for End-to-End Multi-turn Task-oriented Dialog Systems". COLING(2020) [PDF] [code] :star::star::star:
• GraphDialog: "GraphDialog: Integrating Graph Knowledge into End-to-End Task-Oriented Dialogue Systems". EMNLP(2020) [PDF] [code]
• DF-Net: "Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented Dialog". ACL(2020) [PDF] [code]
• MALA: "MALA: Cross-Domain Dialogue Generation with Action Learning". AAAI(2020) [PDF]
• Neural Task-Oriented Dialogue: "Learning to Memorize in Neural Task-Oriented Dialogue Systems". MPhil Thesis(2019) [PDF] :star::star::star::star:
• GLMP: "Global-to-local Memory Pointer Networks for Task-Oriented Dialogue". ICLR(2019) [PDF] [code] :star::star::star::star::star:
• KB Retriever: "Entity-Consistent End-to-end Task-Oriented Dialogue System with KB Retriever". EMNLP(2019) [PDF] [data]
• TRADE: "Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems". ACL(2019) [PDF] [code]
• WMM2Seq: "A Working Memory Model for Task-oriented Dialog Response Generation". ACL(2019) [PDF]
• Pretrain-Fine-tune: "Training Neural Response Selection for Task-Oriented Dialogue Systems". ACL(2019) [PDF] [data]
• Multi-level Mem: "Multi-Level Memory for Task Oriented Dialogs". NAACL(2019) [PDF] [code] :star::star::star:
• BossNet: "Disentangling Language and Knowledge in Task-Oriented Dialogs ". NAACL(2019) [PDF] [code]
• SL+RL: "Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systems". NAACL(2018) [PDF]
• MAD: "Memory-augmented Dialogue Management for Task-oriented Dialogue Systems". TOIS(2018) [PDF] :star::star::star:
• TSCP: "Sequicity: Simplifying Task-oriented Dialogue Systems with Single Sequence-to-Sequence Architectures". ACL(2018) [PDF] [code]
• Mem2Seq: "Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems". ACL(2018) [PDF] [code] :star::star::star::star:
• Topic-Seg-Label: "A Weakly Supervised Method for Topic Segmentation and Labeling in Goal-oriented Dialogues via Reinforcement Learning". IJCAI(2018) [PDF] [code]
• AliMe: "AliMe Chat: A Sequence to Sequence and Rerank based Chatbot Engine". ACL(2017) [PDF]
• KVR Net: "Key-Value Retrieval Networks for Task-Oriented Dialogue". SIGDIAL(2017) [PDF] [data]

Open-domain Dialogue

• CL4Dialogue: "Group-wise Contrastive Learning for Neural Dialogue Generation". EMNLP-Findings(2020) [PDF] [code] :star::star::star:
• ConKADI: "Diverse and Informative Dialogue Generation with Context-Specific Commonsense Knowledge Awareness". ACL(2020) [PDF] [code] :star::star::star::star::star:
• Neg-train: "Negative Training for Neural Dialogue Response Generation". ACL(2020) [PDF] [code]
• HDSA: "Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attention". ACL(2019) [PDF] [code] :star::star::star:
• PostKS: "Learning to Select Knowledge for Response Generation in Dialog Systems". IJCAI(2019) [PDF]
• Two-Stage-Transformer: "Wizard of Wikipedia: Knowledge-Powered Conversational agents". ICLR(2019) [PDF]
• CAS: "Skeleton-to-Response: Dialogue Generation Guided by Retrieval Memory". NAACL(2019) [PDF] [code]
• Edit-N-Rerank: "Response Generation by Context-aware Prototype Editing". AAAI(2019) [PDF] [code] :star::star::star:
• HVMN: "Hierarchical Variational Memory Network for Dialogue Generation". WWW(2018) [PDF] [code]
• XiaoIce: "The Design and Implementation of XiaoIce, an Empathetic Social Chatbot". arXiv(2018) [PDF]
• D2A: "Dialog-to-Action: Conversational Question Answering Over a Large-Scale Knowledge Base". NeurIPS(2018) [PDF] [code]
• DAIM: "Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization". NeurIPS(2018) [PDF]
• MTask: "A Knowledge-Grounded Neural Conversation Model". AAAI(2018) [PDF]
• GenDS: "Flexible End-to-End Dialogue System for Knowledge Grounded Conversation". arXiv(2017) [PDF]
• REASON: "Dialog Generation Using Multi-turn Reasoning Neural Networks". NAACL(2018) [PDF]
• STD/HTD: "Learning to Ask Questions in Open-domain Conversational Systems with Typed Decoders". ACL(2018) [PDF] [code]
• CSF: "Generating Informative Responses with Controlled Sentence Function". ACL(2018) [PDF] [code]
• NKD: "Knowledge Diffusion for Neural Dialogue Generation". ACL(2018) [PDF] [data]
• DAWnet: "Chat More: Deepening and Widening the Chatting Topic via A Deep Model". SIGIR(2018) [PDF] [code]
• ZSDG: "Zero-Shot Dialog Generation with Cross-Domain Latent Actions". SIGDIAL(2018) [PDF] [code]
• DUA: "Modeling Multi-turn Conversation with Deep Utterance Aggregation". COLING(2018) [PDF] [code]
• Data-Aug: "Sequence-to-Sequence Data Augmentation for Dialogue Language Understanding". COLING(2018) [PDF] [code]
• DC-MMI: "Generating More Interesting Responses in Neural Conversation Models with Distributional Constraints". EMNLP(2018) [PDF] [code]
• cVAE-XGate/CGate: "Better Conversations by Modeling, Filtering, and Optimizing for Coherence and Diversity". EMNLP(2018) [PDF] [code]
• Tri-LSTM: "Augmenting End-to-End Dialogue Systems With Commonsense Knowledge". AAAI(2018) [PDF]
• CCM: "Commonsense Knowledge Aware Conversation Generation with Graph Attention". IJCAI(2018) [PDF] [code] :star::star::star::star::star:
• Retrieval+multi-seq2seq: "An Ensemble of Retrieval-Based and Generation-Based Human-Computer Conversation Systems". IJCAI(2018) [PDF]
• DAM: "Multi-Turn Response Selection for Chatbots with Deep Attention Matching Network". ACL(2018) [PDF] [code] :star::star::star::star:
• SMN: "Sequential Matching Network: A New Architecture for Multi-turn Response Selection in Retrieval-Based Chatbots". ACL(2017) [PDF] [code] :star::star::star:
• MMI: "A Diversity-Promoting Objective Function for Neural Conversation Models". NAACL-HLT(2016) [PDF] [code]
• RL-Dialogue: "Deep Reinforcement Learning for Dialogue Generation". EMNLP(2016) [PDF]
• TA-Seq2Seq: "Topic Aware Neural Response Generation". AAAI(2017) [PDF] [code]
• MA: "Mechanism-Aware Neural Machine for Dialogue Response Generation". AAAI(2017) [PDF]
• HRED: "Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models". AAAI(2016) [PDF] [code]
• VHRED: "A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues". AAAI(2017) [PDF] [code]
• CVAE/KgCVAE: "Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders". ACL(2017) [PDF] [code] :star::star::star:

Personalized Dialogue

• PAML: "Personalizing Dialogue Agents via Meta-Learning". ACL(2019) [PDF] [code]
• PCCM: "Assigning Personality/Profile to a Chatting Machine for Coherent Conversation Generation". IJCAI(2018) [PDF] [code]
• ECM: "Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory". AAAI(2018) [PDF] [code]

Miscellaneous

• CrossWOZ: "CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset". TACL(2020) [PDF] [code]
• MultiWOZ: "MultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling". EMNLP(2018) [PDF] [code]
• Survey of Dialogue: "A Survey on Dialogue Systems: Recent Advances and New Frontiers". SIGKDD Explorations(2017) [PDF]
• Survey of Dialogue Corpora: "A Survey of Available Corpora For Building Data-Driven Dialogue Systems: The Journal Version". Dialogue & Discourse(2018) [PDF]
• ADVMT: "One “Ruler” for All Languages: Multi-Lingual Dialogue Evaluation with Adversarial Multi-Task Learning". IJCAI(2018) [PDF]

Text Generation

• Nucleus Sampling: "The Curious Case of Neural Text Degeneration". ICLR(2020) [PDF] [code] :star::star::star:
• Cascaded Generation: "Cascaded Text Generation with Markov Transformers". arXiv(2020) [PDF] [code]
• Sequence Generation: "A Generalized Framework of Sequence Generation with Application to Undirected Sequence Models". arXiv(2019) [PDF] [code]
• Sparse-Seq2Seq: "Sparse Sequence-to-Sequence Models". ACL(2019) [PDF] [code]

Knowledge Representation Learning

• KEPLER: "KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation". TACL(2020) [PDF] [code]
• GNTP: "Differentiable Reasoning on Large Knowledge Bases and Natural Language". AAAI(2020) [PDF] [code]
• NTP: "End-to-End Differentiable Proving". NeurIPS(2017) [PDF] [code]

Text Summarization

• BERTSum: "Fine-tune BERT for Extractive Summarization". arXiv(2019) [PDF] [code]
• QASumm: "Guiding Extractive Summarization with Question-Answering Rewards". NAACL(2019) [PDF] [code]
• Re^3Sum: "Retrieve, Rerank and Rewrite: Soft Template Based Neural Summarization". ACL(2018) [PDF] [code]
• NeuSum: "Neural Document Summarization by Jointly Learning to Score and Select Sentences". ACL(2018) [PDF]
• rnn-ext+abs+RL+rerank: "Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting". ACL(2018) [PDF] [Notes] [code] :star::star::star::star::star:
• Seq2Seq+CGU: "Global Encoding for Abstractive Summarization". ACL(2018) [PDF] [code]
• ML+RL: "A Deep Reinforced Model for Abstractive Summarization". ICLR(2018) [PDF]
• T-ConvS2S: "Don’t Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization". EMNLP(2018) [PDF] [code]
• RL-Topic-ConvS2S: "A reinforced topic-aware convolutional sequence-to-sequence model for abstractive text summarization". IJCAI (2018) [PDF]
• GANsum: "Generative Adversarial Network for Abstractive Text Summarization". AAAI(2018) [PDF]
• FTSum: "Faithful to the Original: Fact Aware Neural Abstractive Summarization". AAAI(2018) [PDF]
• PGN: "Get To The Point: Summarization with Pointer-Generator Networks". ACL(2017) [PDF] [code] :star::star::star::star::star:
• ABS/ABS+: "A Neural Attention Model for Abstractive Sentence Summarization". EMNLP(2015) [PDF]
• RAS-Elman/RAS-LSTM: "Abstractive Sentence Summarization with Attentive Recurrent Neural Networks". NAACL(2016) [PDF] [code]

Topic Modeling

• LDA: "Latent Dirichlet Allocation". JMLR(2003) [PDF] [code] :star::star::star::star::star:
• Parameter Estimation: "Parameter estimation for text analysis". Technical report (2005). [PDF] :star::star::star:
• DTM: "Dynamic Topic Models". ICML(2006) [PDF] [code] :star::star::star::star:
• cDTM: "Continuous Time Dynamic Topic Models". UAI(2008) [PDF]
• iDocNADE: "Document Informed Neural Autoregressive Topic Models with Distributional Prior". AAAI(2019) [PDF] [code]
• NTM: "A Novel Neural Topic Model and Its Supervised Extension". AAAI(2015) [PDF]
• TWE: "Topical Word Embeddings". AAAI(2015) [PDF]
• RATM-D: "Recurrent Attentional Topic Model". AAAI(2017)[PDF]
• RIBS-TM: "Don't Forget the Quantifiable Relationship between Words: Using Recurrent Neural Network for Short Text Topic Discovery". AAAI(2017) [PDF]
• Topic coherence: "Optimizing Semantic Coherence in Topic Models". EMNLP(2011) [PDF]
• Topic coherence: "Automatic Evaluation of Topic Coherence". NAACL(2010) [PDF]
• DADT: "Authorship Attribution with Author-aware Topic Models". ACL(2012) [PDF]
• Gaussian-LDA: "Gaussian LDA for Topic Models with Word Embeddings". ACL(2015) [PDF] [code] :star::star::star:
• LFTM: "Improving Topic Models with Latent Feature Word Representations". TACL(2015) [PDF] [code]
• TopicVec: "Generative Topic Embedding: a Continuous Representation of Documents". ACL (2016) [PDF] [code]
• SLRTM: "Sentence Level Recurrent Topic Model: Letting Topics Speak for Themselves". arXiv(2016) [PDF]
• TopicRNN: "TopicRNN: A Recurrent Neural Network with Long-Range Semantic Dependency". ICLR(2017) [PDF] [code] :star::star::star::star::star:
• NMF boosted: "Stability of topic modeling via matrix factorization". Expert Syst. Appl. (2018) [PDF]
• Topic2Vec: "Topic2Vec: Learning distributed representations of topics". IALP(2015) [PDF]
• L-EnsNMF: "L-EnsNMF: Boosted Local Topic Discovery via Ensemble of Nonnegative Matrix Factorization". ICDM(2016) [PDF] [code] :star::star::star::star:
• DC-NMF: "DC-NMF: nonnegative matrix factorization based on divide-and-conquer for fast clustering and topic modeling". J. Global Optimization (2017) [PDF]
• cFTM: "The contextual focused topic model". KDD(2012) [PDF]
• CLM: "Collaboratively Improving Topic Discovery and Word Embeddings by Coordinating Global and Local Contexts". KDD(2017) [PDF] [code] :star::star::star::star::star:
• GMTM: "Unsupervised Topic Modeling for Short Texts Using Distributed Representations of Words". NAACL(2015) [PDF]
• GPU-PDMM: "Enhancing Topic Modeling for Short Texts with Auxiliary Word Embeddings". TOIS (2017) [PDF]
• BPT: "A Two-Level Topic Model Towards Knowledge Discovery from Citation Networks". TKDE (2014) [PDF]
• BTM: "A Biterm Topic Model for Short Texts". WWW(2013) [PDF] [code] :star::star::star::star:
• HGTM: "Using Hashtag Graph-Based Topic Model to Connect Semantically-Related Words Without Co-Occurrence in Microblogs". TKDE(2016) [PDF]

Machine Translation

• Multi-pass decoder: "Adaptive Multi-pass Decoder for Neural Machine Translation". EMNLP(2018) [PDF]
• Deliberation Networks: "Deliberation Networks: Sequence Generation Beyond One-Pass Decoding". NeurIPS(2017) [PDF] :star::star::star:
• KVMem-Attention: "Neural Machine Translation with Key-Value Memory-Augmented Attention". IJCAI(2018) [PDF] :star::star::star:
• Interactive-Attention: "Interactive Attention for Neural Machine Translation". COLING(2016) [PDF]

Question Answering

• CFC: "Coarse-grain Fine-grain Coattention Network for Multi-evidence Question Answering". ICLR(2019) [PDF]
• MTQA: "Multi-Task Learning with Multi-View Attention for Answer Selection and Knowledge Base Question Answering". AAAI(2019) [PDF] [code]
• CQG-KBQA: "Knowledge Base Question Answering via Encoding of Complex Query Graphs". EMNLP(2018) [PDF] [code] :star::star::star::star::star:
• HR-BiLSTM: "Improved Neural Relation Detection for Knowledge Base Question Answering". ACL(2017) [PDF]
• KBQA-CGK: "An End-to-End Model for Question Answering over Knowledge Base with Cross-Attention Combining Global Knowledge". ACL(2017) [PDF]
• KVMem: "Key-Value Memory Networks for Directly Reading Documents". EMNLP(2016) [PDF]

Reading Comprehension

• DecompRC: "Multi-hop Reading Comprehension through Question Decomposition and Rescoring". ACL(2019) [PDF] [code]
• FlowQA: "FlowQA: Grasping Flow in History for Conversational Machine Comprehension". ICLR(2019) [PDF] [code] :star::star::star::star:
• SDNet: "SDNet: Contextualized Attention-based Deep Network for Conversational Question Answering". arXiv(2018) [PDF] [code]

Image Captioning

• MLAIC: "A Multi-task Learning Approach for Image Captioning". IJCAI(2018) [PDF] [code]
• Up-Down Attention: "Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering". CVPR(2018) [PDF] :star::star::star:
• SCST: "Self-critical Sequence Training for Image Captioning". CVPR(2017) [PDF] :star::star::star: