Changes

==Overview Files location: E:\projects\Kauffman Incubator Project\03 Automate the extraction of Possible Methods==information\RajanLasya_ExtractionProtocols_03.21

There are two possible classification methods for === HTML Tree Structure Analysis === Structurally analyzing the processing HTML tree structure of a web page and expressing it in a DSL is the text most innovative method of target HTML pagesthe three. It would require more than simply adapting off-the-shelf models. The first is a "Bag of Words" approachFirst, which uses Term Frequency – Inverse Document Frequency the DSL itself would need to do basic natural language processing and select words or phrases which have discriminant capabilities. The second is a Word2Vec approach which uses shallow 2 layer neural networks to reduce descriptions be designed to optimize abstraction into the target domain, a vector with high discriminant potentialweb page. (See "Memo [[Domain Specific Language Research]].) Then, the DSL would need to be integrated into the machine learning pipeline by encoding the DSL into an appropriately formatted input, such as a vector or matrix, for Evan" in E:\mcnair\Projects\Incubators a neural network. Three proposed methods for further detailthis encoding are using an adjacency matrix, an edges to vertices matrix, or utilizing DFS (depth-first search) algorithms.)  ==== DFS Encoding ====

=== HTML Tree Structure Analysis = Adjacency Matrix ====

Structurally analyzing By interpreting the HTML tree structure of as a web page and expressing it in a DSL is graph, we can utilize an adjacency matrix to encode the most innovative method tree. The elements of the three. It would require more than simply adapting off-matrix represent whether their corresponding vertices are adjacent in the-shelf modelsgraphical representation. FirstIn its simplest form, for a set of V number of vertices, the DSL itself matrix would need to be designed to optimize abstraction into the target domain, a web pagesquare matrix of dimensions |V| x |V|. (See [[Domain Specific Language Research]].) Then, the DSL would need to be integrated into the machine learning pipeline by encoding the DSL into an appropriately formatted input, The diagonal elements of such as a vector or matrix, for a neural networkwould all be zero. Three proposed methods for this encoding are using This approach has an adjacency matrix, an edges to vertices approach, or utilizing DFS algorithmic efficiency of O(depth-first searchn^2) algorithms.

==== DFS Encoding Edges to Vertices Matrix ====

CurrentlyFor any given tree, we are leaning towards utilizing DFS algorithms. DFS algorithms operate by starting at the root node have n-1 (or an arbitrary node for a graphI'm assuming n = number of nodes) and traverses the longest branch fully before backtracking back to the last split before the branch terminatededges. A DFS algorithm could traverse any given tree and For every edge, we can record 1 when a new node is found, and 0 when that node is fully exploredthe two ending vertices. This creates will result in a numerical representation matrix of that tree that can then be entered into a vector or dimensions (n-1) x 2. This matrixapproach has an algorithmic efficiency of O(n).

==== Supervised Learning Approach (HTML to DSL) ====

Additionally, the HTML tree structure analysis method will require a subprocess by which to parse a complex HTML page into our DSL. An example of a similar process is Pix2Code, in which a DSL context and a GUI are feed into an architecture containing Long Short-Term Memory (LSTM ) layers and a CNN-based vision model(see imagebelow) which outputs a DSL token. After training with paired inputs is complete, this architecture can then take an empty context and a GUI input and output DSL code.

[[File:Pix2code.png|framethumb|center|upright=3|Image from "Project Goal V2"of Pix2Code architecture]]

:This paper discusses different methods of encoding graph structures into low-dimensional embeddings that can be exploited by machine learning models. Section 2.2.2 (Random walk approaches) specifically compares the accuracy of using the random walk approach to traverse a graph, as opposed to BFS and DFS approaches.

: node2vec was mentioned briefly in the above Hamilton et al. paper. node2vec is a scalable encoding algorithm that focuses on preserving network neighborhoods of nodes. The definition of a neighborhood can manipulated depending on the application context. In section 3.1 (Classic Search Strategies), node2vec is compared to BFS and DFS approaches.  * [http://www.ece.iastate.edu/snt/files/2018/03/v2v-graml18.pdf V2V: Vector Embedding of Graph and Applications (Nguyen, Tirthapura)]: V2V (Vector to Vertex) is a learning approach similar to node2vec, except that it takes the random-walk sequence results from graph data and encodes them using a Continous Bag of Word (CBOW) approach to create V2V vectors.  * [https://openreview.net/pdf?id=BkSqjHqxg Skip-Graph: Learning Graph Embeddings with an Encoder-Decoder Model (Lee, Kong)]: This paper explains how to apply the skip-gram model to learning node representations of graph-structured data. This new encoder-decoder model can be trained to generate representations for any arbitrary random walk sequence.  * [https://www.kdd.org/kdd2018/files/deep-learning-day/DLDay18_paper_27.pdf Learning Graph Representations with Recurrent Neural Network Autoencoders (Taheri, Gimpel, Berger-Wolf)]: In a similar process to other neural network encoders, this proposed architecture first generates sequential data from graphs, using BFS shortest path, and random walk algorithms. It then trains LSTM autoencoders to embed these graph sequences into a vector space.  * [https://arxiv.org/abs/1805.07683 Learning Graph Representations with Recurrent Neural Networks (Jin, JaJa)]:This article describes another approach to learning graph-level representations, except through a combination of supervised and unsupervised learning components.