add all links to concepts

concepts.md

@@ -24,163 +24,164 @@ and no other tags need to be applied.
 * Adam: [`optim-adam`](http://pfliu.com/pl-nlp2019/bs/optim-adam.html) (implies `optim-sgd`)
 * Adagrad: [`optim-adagrad`](http://pfliu.com/pl-nlp2019/bs/optim-adagrad.html) (implies `optim-sgd`)
 * Adadelta: [`optim-adadelta`](http://pfliu.com/pl-nlp2019/bs/optim-adadelta.html) (implies `optim-sgd`)
-* Adam with Specialized Transformer Learning Rate ("Noam" Schedule): `optim-noam` (implies `optim-adam`)
-* SGD with Momentum: `optim-momentum` (implies `optim-sgd`)
-* AMS: `optim-amsgrad` (implies `optim-sgd`)
+* Adam with Specialized Transformer Learning Rate ("Noam" Schedule): [`optim-noam`](http://pfliu.com/pl-nlp2019/bs/optim-noam.html) (implies `optim-adam`)
+* SGD with Momentum: [`optim-momentum`](http://pfliu.com/pl-nlp2019/bs/optim-momentum.html) (implies `optim-sgd`)
+* AMS: [`optim-amsgrad`](http://pfliu.com/pl-nlp2019/bs/optim-amsgrad.html) (implies `optim-sgd`)
 
 ### Initialization
 
-* Glorot/Xavier Initialization: `init-glorot`
-* He Initialization: `init-he`
+* Glorot/Xavier Initialization: [`init-glorot`](http://pfliu.com/pl-nlp2019/bs/init-glorot.html)
+* He Initialization: [`init-he`](http://pfliu.com/pl-nlp2019/bs/init-he.html)
 
 ### Regularization
 
-* Dropout: `reg-dropout`
-* Word Dropout: `reg-worddropout` (implies `reg-dropout`)
-* Norm (L1/L2) Regularization: `reg-norm`
-* Early Stopping: `reg-stopping`
-* Patience: `reg-patience` (implies `reg-stopping`)
-* Weight Decay: `reg-decay`
-* Label Smoothing: `reg-labelsmooth`
+* Dropout: [`reg-dropout`]
+* Word Dropout: [`reg-worddropout`](http://pfliu.com/pl-nlp2019/bs/reg-worddropout.html) (implies `reg-dropout`)
+* Norm (L1/L2) Regularization: [`reg-norm`](http://pfliu.com/pl-nlp2019/bs/reg-norm.html)
+* Early Stopping: [`reg-stopping`](http://pfliu.com/pl-nlp2019/bs/reg-stopping.html)
+* Patience: [`reg-patience`](http://pfliu.com/pl-nlp2019/bs/reg-patience.html) (implies `reg-stopping`)
+* Weight Decay: [`reg-decay`](http://pfliu.com/pl-nlp2019/bs/reg-decay.html)
+* Label Smoothing: [`reg-labelsmooth`](http://pfliu.com/pl-nlp2019/bs/reg-labelsmooth.html)
 
 ### Normalization
 
-* Layer Normalization: `norm-layer`
-* Batch Normalization: `norm-batch`
-* Gradient Clipping: `norm-gradient`
+* Layer Normalization: [`norm-layer`](http://pfliu.com/pl-nlp2019/bs/norm-layer.html)
+* Batch Normalization: [`norm-batch`](http://pfliu.com/pl-nlp2019/bs/norm-batch.html)
+* Gradient Clipping: [`norm-gradient`](http://pfliu.com/pl-nlp2019/bs/norm-gradient.html)
 
 ### Loss Functions (other than cross-entropy)
 
-* Canonical Correlation Analysis (CCA): `loss-cca`
-* Singular Value Decomposition (SVD): `loss-svd`
-* Margin-based Loss Functions: `loss-margin`
-* Contrastive Loss: `loss-cons`
-* Noise Contrastive Estimation (NCE): `loss-nce` (implies `loss-cons`)
-* Triplet loss: `loss-triplet` (implies `loss-cons`)
+* Canonical Correlation Analysis (CCA): [`loss-cca`](http://pfliu.com/pl-nlp2019/bs/loss-cca.html)
+* Singular Value Decomposition (SVD): [`loss-svd`](http://pfliu.com/pl-nlp2019/bs/loss-svd.html)
+* Margin-based Loss Functions: [`loss-margin`](http://pfliu.com/pl-nlp2019/bs/loss-margin.html)
+* Contrastive Loss: [`loss-cons`](http://pfliu.com/pl-nlp2019/bs/loss-cons.html)
+* Noise Contrastive Estimation (NCE): [`loss-nce`](http://pfliu.com/pl-nlp2019/bs/loss-nce.html) (implies `loss-cons`)
+* Triplet loss: [`loss-triplet`](http://pfliu.com/pl-nlp2019/bs/loss-triplet.html) (implies `loss-cons`)
 
 ### Training Paradigms
 
-* Multi-task Learning (MTL): `train-mtl`
-* Multi-lingual Learning (MLL): `train-mll` (implies `train-mtl`)
-* Transfer Learning: `train-transfer`
-* Active Learning: `train-active`
-* Data Augmentation: `train-augment`
+* Multi-task Learning (MTL): [`train-mtl`](http://pfliu.com/pl-nlp2019/bs/train-mtl.html)
+* Multi-lingual Learning (MLL): [`train-mll`](http://pfliu.com/pl-nlp2019/bs/train-mll.html) (implies `train-mtl`)
+* Transfer Learning: [`train-transfer`](http://pfliu.com/pl-nlp2019/bs/train-transfer.html)
+* Active Learning: [`train-active`](http://pfliu.com/pl-nlp2019/bs/train-active.html)
+* Data Augmentation: [`train-augment`](http://pfliu.com/pl-nlp2019/bs/train-augment.html)
+
 
 ## Sequence Modeling Architectures
 
 ### Activation Functions
 
-* Hyperbolic Tangent (tanh): `activ-tanh`
-* Rectified Linear Units (RelU): `activ-relu`
+* Hyperbolic Tangent (tanh): [`activ-tanh`](http://pfliu.com/pl-nlp2019/bs/activ-tanh.html)
+* Rectified Linear Units (RelU): [`activ-relu`](http://pfliu.com/pl-nlp2019/bs/activ-relu.html)
 
 ### Pooling Operations
 
-* Max Pooling: `pool-max`
-* Mean Pooling: `pool-mean`
-* k-Max Pooling: `pool-kmax`
+* Max Pooling: [`pool-max`](http://pfliu.com/pl-nlp2019/bs/pool-max.html)
+* Mean Pooling: [`pool-mean`](http://pfliu.com/pl-nlp2019/bs/pool-mean.html)
+* k-Max Pooling: [`pool-kmax`](http://pfliu.com/pl-nlp2019/bs/pool-kmax.html)
 
 ### Recurrent Architectures
 
-* Recurrent Neural Network (RNN): `arch-rnn`
-* Bi-directional Recurrent Neural Network (Bi-RNN): `arch-birnn` (implies `arch-rnn`)
-* Long Short-term Memory (LSTM): `arch-lstm` (implies `arch-rnn`)
-* Bi-directional Long Short-term Memory (LSTM): `arch-bilstm` (implies `arch-birnn`, `arch-lstm`)
-* Gated Recurrent Units (GRU): `arch-gru` (implies `arch-rnn`)
-* Bi-directional Gated Recurrent Units (GRU): `arch-bigru` (implies `arch-birnn`, `arch-gru`)
-* Recursive Neural Network (RecNN): `arch-recnn`
-* Tree-structured Long Short-term Memory (TreeLSTM): `arch-treelstm` (implies `arch-recnn`)
-* Graph Neural Network (GNN): `arch-gnn`
-* Graph Convolutional Neural Network (GCNN): `arch-gcnn` (implies `arch-gnn`)
+* Recurrent Neural Network (RNN): [`arch-rnn`](http://pfliu.com/pl-nlp2019/bs/arch-rnn.html)
+* Bi-directional Recurrent Neural Network (Bi-RNN): [`arch-birnn`](http://pfliu.com/pl-nlp2019/bs/arch-birnn.html) (implies `arch-rnn`)
+* Long Short-term Memory (LSTM): [`arch-lstm`](http://pfliu.com/pl-nlp2019/bs/arch-lstm.html) (implies `arch-rnn`)
+* Bi-directional Long Short-term Memory (LSTM): [`arch-bilstm`](http://pfliu.com/pl-nlp2019/bs/arch-bilstm.html) (implies `arch-birnn`, `arch-lstm`)
+* Gated Recurrent Units (GRU): [`arch-gru`](http://pfliu.com/pl-nlp2019/bs/arch-gru.html) (implies `arch-rnn`)
+* Bi-directional Gated Recurrent Units (GRU): [`arch-bigru`](http://pfliu.com/pl-nlp2019/bs/arch-bigru.html) (implies `arch-birnn`, `arch-gru`)
+* Recursive Neural Network (RecNN): [`arch-recnn`](http://pfliu.com/pl-nlp2019/bs/arch-recnn.html)
+* Tree-structured Long Short-term Memory (TreeLSTM): [`arch-treelstm`](http://pfliu.com/pl-nlp2019/bs/arch-treelstm.html) (implies `arch-recnn`)
+* Graph Neural Network (GNN): [`arch-gnn`](http://pfliu.com/pl-nlp2019/bs/arch-gnn.html)
+* Graph Convolutional Neural Network (GCNN): [`arch-gcnn`](http://pfliu.com/pl-nlp2019/bs/arch-gcnn.html) (implies `arch-gnn`)
 
 ### Other Sequential Architectures
 
-* Convolutional Neural Networks (CNN): `arch-cnn`
-* Attention: `arch-att`
-* Self Attention: `arch-selfatt` (implies `arch-att`)
+* Convolutional Neural Networks (CNN): [`arch-cnn`](http://pfliu.com/pl-nlp2019/bs/arch-cnn.html)
+* Attention: [`arch-att`](http://pfliu.com/pl-nlp2019/bs/arch-att.html)
+* Self Attention: [`arch-selfatt`](http://pfliu.com/pl-nlp2019/bs/arch-selfatt.html) (implies `arch-att`)
 
 ### Architectural Techniques
 
-* Residual Connections (ResNet): `arch-residual`
-* Gating Connections, Highway Connections: `arch-gating`
-* Memory: `arch-memo`
-* Copy Mechanism: `arch-copy`
-* Bilinear, Biaffine Models: `arch-bilinear`
+* Residual Connections (ResNet): [`arch-residual`](http://pfliu.com/pl-nlp2019/bs/arch-residual.html)
+* Gating Connections, Highway Connections: [`arch-gating`](http://pfliu.com/pl-nlp2019/bs/arch-gating.html)
+* Memory: [`arch-memo`](http://pfliu.com/pl-nlp2019/bs/arch-memo.html)
+* Copy Mechanism: [`arch-copy`](http://pfliu.com/pl-nlp2019/bs/arch-copy.html)
+* Bilinear, Biaffine Models: [`arch-bilinear`](http://pfliu.com/pl-nlp2019/bs/arch-bilinear.html)
 
 ### Standard Composite Architectures
 
-* Transformer: `arch-transformer` (implies `arch-selfatt`, `arch-residual`, `arch-layernorm`, `optim-noam`)
+* Transformer: [`arch-transformer`](http://pfliu.com/pl-nlp2019/bs/arch-transformer.html) (implies `arch-selfatt`, `arch-residual`, `arch-layernorm`, `optim-noam`)
 
 
 ## Model Combination
 
-* Ensembling: `comb-ensemble`
+* Ensembling: [`comb-ensemble`](http://pfliu.com/pl-nlp2019/bs/comb-ensemble.html)
 
 ## Search Algorithms
 
-* Greedy Search: `search-greedy`
-* Beam Search: `search-beam`
-* A* Search: `search-astar`
-* Viterbi Algorithm: `search-viterbi`
-* Ancestral Sampling: `search-sampling`
-* Gumbel Max: `search-gumbel` (implies `search-sampling`)
+* Greedy Search: [`search-greedy`](http://pfliu.com/pl-nlp2019/bs/search-greedy.html)
+* Beam Search: [`search-beam`](http://pfliu.com/pl-nlp2019/bs/search-beam.html)
+* A* Search: [`search-astar`](http://pfliu.com/pl-nlp2019/bs/search-astar.html)
+* Viterbi Algorithm: [`search-viterbi`](http://pfliu.com/pl-nlp2019/bs/search-viterbi.html)
+* Ancestral Sampling: [`search-sampling`](http://pfliu.com/pl-nlp2019/bs/search-sampling.html)
+* Gumbel Max: [`search-gumbel`](http://pfliu.com/pl-nlp2019/bs/search-gumbel.html) (implies `search-sampling`)
 
 ## Prediction Tasks
 
-* Text Classification (text -> label): `task-textclass`
-* Text Pair Classification (two texts -> label: `task-textpair`
-* Sequence Labeling (text -> one label per token): `task-seqlab`
-* Extractive Summarization (text -> subset of text): `task-extractive` (implies `text-seqlab`)
-* Span Labeling (text -> labels on spans): `task-spanlab`
-* Language Modeling (predict probability of text): `task-lm`
-* Conditioned Language Modeling (some input -> text): `task-condlm` (implies `task-lm`)
-* Sequence-to-sequence Tasks (text -> text, including MT): `task-seq2seq` (implies `task-condlm`)
-* Cloze-style Prediction, Masked Language Modeling (right and left context -> word): `task-cloze`
-* Context Prediction (as in word2vec) (word -> right and left context): `task-context`
-* Relation Prediction (text -> graph of relations between words, including dependency parsing): `task-relation`
-* Tree Prediction (text -> tree, including syntactic and some semantic semantic parsing): `task-tree`
-* Graph Prediction (text -> graph not necessarily between nodes): `task-graph`
-* Lexicon Induction/Embedding Alignment (text/embeddings -> bi- or multi-lingual lexicon): `task-lexicon`
-* Word Alignment (parallel text -> alignment between words): `task-alignment`
+* Text Classification (text -> label): [`task-textclass`](http://pfliu.com/pl-nlp2019/bs/task-textclass.html)
+* Text Pair Classification (two texts -> label: [`task-textpair`](http://pfliu.com/pl-nlp2019/bs/task-textpair.html)
+* Sequence Labeling (text -> one label per token): [`task-seqlab`](http://pfliu.com/pl-nlp2019/bs/task-seqlab.html)
+* Extractive Summarization (text -> subset of text): [`task-extractive`](http://pfliu.com/pl-nlp2019/bs/task-extractive.html) (implies `text-seqlab`)
+* Span Labeling (text -> labels on spans): [`task-spanlab`](http://pfliu.com/pl-nlp2019/bs/task-spanlab.html)
+* Language Modeling (predict probability of text): [`task-lm`](http://pfliu.com/pl-nlp2019/bs/task-lm.html)
+* Conditioned Language Modeling (some input -> text): [`task-condlm`](http://pfliu.com/pl-nlp2019/bs/task-condlm.html) (implies `task-lm`)
+* Sequence-to-sequence Tasks (text -> text, including MT): [`task-seq2seq`](http://pfliu.com/pl-nlp2019/bs/task-seq2seq.html) (implies `task-condlm`)
+* Cloze-style Prediction, Masked Language Modeling (right and left context -> word): [`task-cloze`](http://pfliu.com/pl-nlp2019/bs/task-cloze.html)
+* Context Prediction (as in word2vec) (word -> right and left context): [`task-context`](http://pfliu.com/pl-nlp2019/bs/task-context.html)
+* Relation Prediction (text -> graph of relations between words, including dependency parsing): [`task-relation`](http://pfliu.com/pl-nlp2019/bs/task-relation.html)
+* Tree Prediction (text -> tree, including syntactic and some semantic semantic parsing): [`task-tree`
+* Graph Prediction (text -> graph not necessarily between nodes): [`task-graph`](http://pfliu.com/pl-nlp2019/bs/task-graph.html)
+* Lexicon Induction/Embedding Alignment (text/embeddings -> bi- or multi-lingual lexicon): [`task-lexicon`](http://pfliu.com/pl-nlp2019/bs/task-lexicon.html)
+* Word Alignment (parallel text -> alignment between words): [`task-alignment`](http://pfliu.com/pl-nlp2019/bs/task-alignment.html)
 
 ## Composite Pre-trained Embedding Techniques
 
-* word2vec: `pre-word2vec` (implies `arch-cbow`, `task-cloze`, `task-context`)
-* GloVe: `pre-glove`
-* Paragraph Vector (ParaVec): `pre-paravec`
-* Skip-thought: `pre-skipthought` (implies `arch-lstm`, `task-seq2seq`)
-* ELMo: `pre-elmo` (implies `arch-bilstm`, `task-lm`)
-* BERT: `pre-bert` (implies `arch-transformer`, `task-cloze`, `task-textpair`)
+* word2vec: [`pre-word2vec`](http://pfliu.com/pl-nlp2019/bs/pre-word2vec.html) (implies `arch-cbow`, `task-cloze`, `task-context`)
+* GloVe: [`pre-glove`](http://pfliu.com/pl-nlp2019/bs/pre-glove.html)
+* Paragraph Vector (ParaVec): [`pre-paravec`](http://pfliu.com/pl-nlp2019/bs/pre-paravec.html)
+* Skip-thought: [`pre-skipthought`](http://pfliu.com/pl-nlp2019/bs/pre-skipthought.html) (implies `arch-lstm`, `task-seq2seq`)
+* ELMo: [`pre-elmo`](http://pfliu.com/pl-nlp2019/bs/pre-elmo.html) (implies `arch-bilstm`, `task-lm`)
+* BERT: [`pre-bert`](http://pfliu.com/pl-nlp2019/bs/pre-bert.html) (implies `arch-transformer`, `task-cloze`, `task-textpair`)
 
 ## Structured Models/Algorithms
 
-* Hidden Markov Models (HMM): `struct-hmm`
-* Conditional Random Fields (CRF): `struct-crf`
-* Context-free Grammar (CFG): `struct-cfg`
-* Combinatorial Categorical Grammar (CCG): `struct-ccg`
+* Hidden Markov Models (HMM): [`struct-hmm`](http://pfliu.com/pl-nlp2019/bs/struct-hmm.html)
+* Conditional Random Fields (CRF): [`struct-crf`](http://pfliu.com/pl-nlp2019/bs/struct-crf.html)
+* Context-free Grammar (CFG): [`struct-cfg`](http://pfliu.com/pl-nlp2019/bs/struct-cfg.html)
+* Combinatorial Categorical Grammar (CCG): [`struct-ccg`](http://pfliu.com/pl-nlp2019/bs/struct-ccg.html)
 
 ## Relaxation/Training Methods for Non-differentiable Functions
 
-* Complete Enumeration: `nondif-enum`
-* Straight-through Estimator: `nondif-straightthrough`
-* Gumbel Softmax: `nondif-gumbelsoftmax`
-* Minimum Risk Training: `nondif-minrisk` 
-* REINFORCE: `nondif-reinforce` 
+* Complete Enumeration: [`nondif-enum`](http://pfliu.com/pl-nlp2019/bs/nondif-enum.html)
+* Straight-through Estimator: [`nondif-straightthrough`](http://pfliu.com/pl-nlp2019/bs/nondif-straightthrough.html)
+* Gumbel Softmax: [`nondif-gumbelsoftmax`](http://pfliu.com/pl-nlp2019/bs/nondif-gumbelsoftmax.html)
+* Minimum Risk Training: [`nondif-minrisk` ](http://pfliu.com/pl-nlp2019/bs/nondif-minrisk.html)
+* REINFORCE: [`nondif-reinforce` ](http://pfliu.com/pl-nlp2019/bs/nondif-reinforce.html)
 
 ## Adversarial Methods
 
-* Generative Adversarial Networks (GAN): `adv-gan`
-* Adversarial Feature Learning: `adv-feat`
-* Adversarial Examples: `adv-examp`
-* Adversarial Training: `adv-train` (implies `adv-examp`)
+* Generative Adversarial Networks (GAN): [`adv-gan`](http://pfliu.com/pl-nlp2019/bs/adv-gan.html)
+* Adversarial Feature Learning: [`adv-feat`](http://pfliu.com/pl-nlp2019/bs/adv-feat.html)
+* Adversarial Examples: [`adv-examp`](http://pfliu.com/pl-nlp2019/bs/adv-examp.html)
+* Adversarial Training: [`adv-train`](http://pfliu.com/pl-nlp2019/bs/adv-train.html) (implies `adv-examp`)
 
 ## Latent Variable Models
 
-* Variational Auto-encoder (VAE): `latent-vae`
-* Topic Model: `latent-topic`
+* Variational Auto-encoder (VAE): [`latent-vae`](http://pfliu.com/pl-nlp2019/bs/latent-vae.html)
+* Topic Model: [`latent-topic`](http://pfliu.com/pl-nlp2019/bs/latent-topic.html)
 
 ## Meta Learning
 
-* Meta-learning Initialization: `meta-init`
-* Meta-learning Optimizers: `meta-optim`
-* Meta-learning Loss functions: `meta-loss`
-* Neural Architecture Search: `meta-arch`
+* Meta-learning Initialization: [`meta-init`](http://pfliu.com/pl-nlp2019/bs/meta-init.html)
+* Meta-learning Optimizers: [`meta-optim`](http://pfliu.com/pl-nlp2019/bs/meta-optim.html)
+* Meta-learning Loss functions: [`meta-loss`](http://pfliu.com/pl-nlp2019/bs/meta-loss.html)
+* Neural Architecture Search: [`meta-arch`](http://pfliu.com/pl-nlp2019/bs/meta-arch.html)