电子科技大学 格拉斯哥学院 2017级 杨泽宇 Using Graph Theory to Improve Academic Paper Information Retrieval
Using Graph Theory to Improve Academic Paper Information Retrieval
Hello readers, I believe many people are often confused when reading academic papers. I think part of the reason is that the information that the reader wants in the paper is difficult to find quickly, or the information that the reader wants is not directly in the text. Mentioned, but hidden information formed through logical reasoning. In this article, I will discuss how to use graph theory to improve an academic search engine, so that the search engine has a certain “intelligence”, that is, certain logical reasoning and summarizing ability.
Introduction to Graph Theory
In mathematics, graph theory is the study of graphs, which are mathematical structures used to model pairwise relations between objects. A graph in this context is made up of vertices, nodes, or points which are connected by edges, arcs, or lines. A graph may be undirected, meaning that there is no distinction between the two vertices associated with each edge, or its edges may be directed from one vertex to another; see Graph (discrete mathematics) for more detailed definitions and for other variations in the types of graph that are commonly considered. Graphs are one of the prime objects of study in discrete mathematics.
About Computer Science and Linguistics
In computer science, graphs are used to represent networks of communication, data organization, computational devices, the flow of computation, etc. For instance, the link structure of a website can be represented by a directed graph, in which the vertices represent web pages and directed edges represent links from one page to another. A similar approach can be taken to problems in social media, travel, biology, computer chip design, mapping the progression of neurodegenerative diseases, and many other fields. The development of algorithms to handle graphs is therefore of major interest in computer science. The transformation of graphs is often formalized and represented by graph rewrite systems. Complementary to graph transformation systems focusing on rule-based in-memory manipulation of graphs are graph databases geared towards transaction-safe, persistent storing and querying of graph-structured data.
Graph-theoretic methods, in various forms, have proven particularly useful in linguistics, since natural language often lends itself well to discrete structure. Traditionally, syntax and compositional semantics follow tree-based structures, whose expressive power lies in the principle of compositionality, modeled in a hierarchical graph. More contemporary approaches such as head-driven phrase structure grammar model the syntax of natural language using typed feature structures, which are directed acyclic graphs. Within lexical semantics, especially as applied to computers, modeling word meaning is easier when a given word is understood in terms of related words; semantic networks are therefore important in computational linguistics. Still, other methods in phonology (e.g. optimality theory, which uses lattice graphs) and morphology (e.g. finite-state morphology, using finite-state transducers) are common in the analysis of language as a graph. Indeed, the usefulness of this area of mathematics to linguistics has borne organizations such as TextGraphs, as well as various ‘Net’ projects, such as WordNet, VerbNet, and others.
Academic Paper Information Retrieval
As I already have a basic understanding of graph theory, I want to use this technology to improve the efficiency of information retrieval, especially in academic area. The reasons of it are various.
First of all, the graph theory is highly related to information retrieval, because language information searching is one of an important fields fo computer science and linguistics. So I can just use the graph theory to accomplish the artificial intelligence of natural language processing. For example, it is stupid and inefficient to build a search engine by matching exact words, and apparently, it is much better if the engine can have an ability to be smart, that is, the searching system can learn the relationship inside between different words. The effect I want to accomplish is that the system can be as humanized as possible, like if he receives the information that A is B’s father and C is A’s father, then he can automatically figure out that C is B’s grandfather, which is one application of graph theory.
More importantly, academic paper follows a strict format so that I can get and classify the information more easily, because it is already clearly organized. So once the information can be easily gotten, it helps a lot with constructing a knowledge map.
Lastly, I believe that everybody need this technology when they are not familiar enough with their new research field.
Text Recognition and Network Training
If the graph theory and information retrieval and be combined perfectly, all I need to do is to find a lot of sample papers, and throw them into the neutral network. After the network learn enough information, they are supposed to construct the knowledge map. It is even possible that the machine can recognize graphic information as well as text with the technology of graph processing. So uses can firstly scan the scripts they have, and they can be helped to find more hidden information by the magic information retrieval.
Conclusion
Now I am just a year 2 undergraduate, and I never learned about graph theory and algorithms. But I always keep curious about it especially after I listened to professor Zen’s lecture about graph processing and I searched some relevant information about graphics and computer science. This passage is just my shallow understanding of graph theory, but I do wish I can build a useful application to improve the efficiency of academic paper information retrieval.
Reference
[1] website: https://en.wikipedia.org/wiki/Graph_theory
[2] Introduction to Graph Theory, Douglas B. West, University of Illinois - Urbana, PRENTICE HALL Upper Saddle River, NJ 07458
[3] Graph theory: An algorithmic approach (Computer science and applied mathematics), Nicos Christofides, Academic Press, Inc. Orlando, FL, USA ©1975 , ISBN:0121743500