Challenge Research- Cornell Neural Team 6

Cornell Neural Team 6 has thoroughly researched many papers in the process of creating our architecture proposal. The papers cited have been listed below in order of reference.

Our Proposal: Paper

Example Word Embedding: Embedding

Papers

1. Latent Dirichlet Allocation
2. [A Neural Network for Factoid Question Answering over Paragraphs](./research/NN factoid question answering over paragraphs.pdf)
3. [Text Categorization with Support Vector Machines: Learning with Many Relevant Features](./research/Text Categorization with SVM.pdf)
4. [Convolutional Neural Networks for Sentence Classification](./research/Text Classification with CNN.pdf)
5. [Ask Me Anything: Dynamic Memory Networks for Natural Language Processing](./research/Dynamic Memory Networks for Natural Language Processing.pdf)
6. A Persona-Based Neural Conversation Model
7. Deep Reinforcement Learning for Dialogue Generation
8. [Pointer Sentinel Mixture Model](./research/pointer sentinel mixture models.pdf)
9. [Text Categorization and Support Vector Machines](./research/Text Categorization with SVM more recent.pdf)
10. A Neural Network Approach to Context-Sensitive Generation of Conversational Responses
11. A Neural Conversational Model
12. [End-to-End LSTM-Based Dialog Control Optimized with Supervised and Reinforcement Learning](./research/end to end lstm-based dialogue with supervised and reinforcement learning.pdf)
13. Response Selection with Topic Clues for Retrieval-based Chatbots
14. Dynamic Memory Networks for Visual and Textual Question Answering
15. Freebase QA: Information Extraction or Semantic Parsing?
16. Information Extraction over Structured Data: Question Answering with Freebase
17. [Reinforcement Learning Neural Turing Machines](./research/reinforcement learning--neural turing machines.pdf)
18. [Question Answering over Knowledge Base with Neural Attention Combining Global Knowledge Information](./research/QA with KB and neural nets.pdf)
19. [Comparing Twitter and Traditional Media using Topic Models](./research/twitter topic models.pdf)
20. A Diversity-Promoting Objective Function for Neural Conversation Models
21. Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models