yamlized: domain adaptation

_data/domain_adaptation.yaml

@@ -0,0 +1,48 @@
+-
+  model:       Multi-task tri-training
+  authors:     Ruder and Plank
+  year:        2018
+  DVD:         78.14
+  Books:       74.86
+  Electronics: 81.45
+  Kitchen:     82.14
+  Average:     79.15
+  paper:       Strong Baselines for Neural Semi-supervised Learning under Domain Shift
+  url:         https://arxiv.org/abs/1804.09530
+  code:        []
+-
+  model:       Asymmetric tri-training
+  authors:     Saito et al.
+  year:        2017
+  DVD:         76.17
+  Books:       72.97
+  Electronics: 80.47
+  Kitchen:     83.97
+  Average:     78.39
+  paper:       Asymmetric Tri-training for Unsupervised Domain Adaptation
+  url:         https://arxiv.org/abs/1702.08400
+  code:        []
+-
+  model:       VFAE
+  authors:     Louizos et al.
+  year:        2015
+  DVD:         76.57
+  Books:       73.4
+  Electronics: 80.53
+  Kitchen:     82.93
+  Average:     78.36
+  paper:       The Variational Fair Autoencoder
+  url:         https://arxiv.org/abs/1511.00830
+  code:        []
+-
+  model:       DANN
+  authors:     Ganin et al.
+  year:        2016
+  DVD:         75.4
+  Books:       71.43
+  Electronics: 77.67
+  Kitchen:     80.53
+  Average:     76.26
+  paper:       Domain-Adversarial Training of Neural Networks
+  url:         https://arxiv.org/abs/1505.07818
+  code:        []

domain_adaptation.md

@@ -1,6 +1,6 @@
 # Domain adaptation
 
-## Sentiment analysis 
+## Sentiment analysis
 
 ### Multi-Domain Sentiment Dataset
 
@@ -12,11 +12,8 @@ typically evaluated on a target domain that is different from the source domain
 having access to unlabeled examples of the target domain (unsupervised domain adaptation). The evaluation
 metric is accuracy and scores are averaged across each domain.
 
-| Model           | DVD | Books | Electronics | Kitchen | Average |  Paper / Source |
-| ------------- | :-----:| :-----:| :-----:| :-----:| :-----:| --- |
-| Multi-task tri-training (Ruder and Plank, 2018) | 78.14 | 74.86 | 81.45 | 82.14 | 79.15 | [Strong Baselines for Neural Semi-supervised Learning under Domain Shift](https://arxiv.org/abs/1804.09530) |
-| Asymmetric tri-training (Saito et al., 2017) | 76.17 | 72.97 | 80.47 | 83.97 | 78.39 | [Asymmetric Tri-training for Unsupervised Domain Adaptation](https://arxiv.org/abs/1702.08400) |
-| VFAE (Louizos et al., 2015) | 76.57 | 73.40 | 80.53 | 82.93 | 78.36 | [The Variational Fair Autoencoder](https://arxiv.org/abs/1511.00830) |
-| DANN (Ganin et al., 2016) | 75.40 | 71.43 | 77.67 | 80.53 | 76.26 | [Domain-Adversarial Training of Neural Networks](https://arxiv.org/abs/1505.07818) |
+{% include table.html
+   results=site.data.domain_adaptation
+   scores='DVD,Books,Electronics,Kitchen,Average' %}
 
 [Go back to the README](README.md)