TransModal: Translating from Multiple Modalities into Text

Computer Science

1. Annotation 25%
2. Answer Question 8%
3. Argument Structure 8%
4. Art Performance 8%
5. Attention (Machine Learning) 12%
6. Attention Score 8%
7. Candidate Tree 8%
8. Coder 8%
9. Confidence Estimation 8%
10. Confidence Score 8%
11. Content Analysis 8%
12. Content Structure 8%
13. Convolutional Neural Network 20%
14. Data Representation 8%
15. Decision-Making 8%
16. Deep Reinforcement Learning 8%
17. Dependency Graph 8%
18. Directed Acyclic Graph 8%
19. Disambiguation 8%
20. Discourse Representation Structure 25%
21. Document Representation 16%
22. Driven Approach 8%
23. Experimental Result 68%
24. External Source 8%
25. Extractive Summarization 41%
26. Generative Model 6%
27. Gold Standard 6%
28. Group Identifier 8%
29. Input Attribute 8%
30. Input Utterance 12%
31. Instance Learning 20%
32. Iterative Refinement 10%
33. Knowledge Graph 8%
34. Language Modeling 25%
35. Learning Network 8%
36. Linguistic Input 8%
37. Long Short-Term Memory Network 16%
38. Lstm 8%
39. Machine Translation 27%
40. Memory Architecture 8%
41. Model Compression 8%
42. Model Prediction 8%
43. Modeling Framework 16%
44. Multiple Instance 12%
45. Natural Language Processing 8%
46. Natural-Language Understanding 8%
47. Neural Network 25%
48. Neural Network Architecture 8%
49. Neural Network Model 8%
50. Opinion Summarization 8%
51. Output Sequence 8%
52. Parsing 100%
53. Posterior Probability 8%
54. Published Research 8%
55. question answering system 8%
56. Recognition Algorithm 8%
57. Recurrent Neural Network 20%
58. Reinforcement Learning 8%
59. Representation Language 8%
60. Representing Set 8%
61. Semantic Role Labeling 8%
62. Sentence Structure 8%
63. Sentiment Analysis 16%
64. Sentiment Prediction 8%
65. Seq2Seq 14%
66. Sequence Model 13%
67. Sequential Decoder 8%
68. Signal Content 8%
69. Statistical Data 8%
70. Structured Data 16%
71. Structured Text 8%
72. Summarizing Opinion 8%
73. Superior Performance 6%
74. Syntactics 25%
75. TensorFlow 8%
76. Text Representation 8%
77. Text Segment 6%
78. Textual Semantic Similarity 8%
79. Training Data 22%
80. Training Objective 8%
81. Variational Autoencoder 14%