create a personalized summer reading program website for …...step 1: create a free wordpress blog...

13
16 AI MAGAZINE Articles Copyright © 2008, Association for the Advancement of Artificial Intelligence. All rights reserved. ISSN 0738-4602 Networks and Natural Language Processing Dragomir R. Radev and Rada Mihalcea Over the last few years, a number of ar- eas of natural language processing have begun applying graph-based techniques. These include, among others, text sum- marization, syntactic parsing, word-sense disambiguation, ontology construction, sentiment and subjectivity analysis, and text clustering. In this paper, we present some of the most successful graph-based representations and algorithms used in language processing and try to explain how and why they work. edge types have been used. Text units of various sizes and characteristics can be added as vertices in the graph, for exam- ple, words, collocations, word senses, en- tire sentences, or even entire documents. Note that the graph nodes do not have to belong to the same category. For example, both sentences and words can be added as vertices in the same graph. Edges can rep- resent cooccurrence (such as two words that appear in the same sentence or in the same dictionary definition), collocation (for example, two words that appear im- mediately next to each other or that may be separated by a conjunction), syntactic structure (for example, the parent and child in a syntactic dependency), and lex- ical similarity (for example, cosine be- tween the vector representations of two sentences). In terms of graph-based algorithms, the main methods used so far can be classified into: (1) semisupervised classification (Zhu and Ghahramani 2002; Zhu and Laf- ferty 2005; Toutanova, Manning, and Ng 2004; Radev 2004; Otterbacher, Erkan, and Radev 2005), where random walks or relaxation are applied on mixed sets of la- beled and unlabeled nodes; (2) network analysis (Masucci and Rodgers 2006; , Caldeira et al. 2006), where network prop- erties such as diameter, centrality, and so on, are calculated; (3) graph-based cluster- ing methods (Pang and Lee 2004, Wid- dows and Dorow 2002), such as min-cut methods; (4) minimum spanning-tree al- gorithms (McDonald et al. 2005). In this article, we overview several I n a cohesive text, language units— whether they are words, phrases, or en- tire sentences—are connected through a variety of relations, which contribute to the overall meaning of the text and main- tain the cohesive structure of the text and the discourse unity. Since the early ages of artificial intelligence, associative or se- mantic networks have been proposed as representations that enable the storage of such language units and the relations that interconnect them and that allow for a va- riety of inference and reasoning processes, simulating some of the functionalities of the human mind. The symbolic structures that emerge from these representations correspond naturally to graphs—where text constituents are represented as ver- tices and their interconnecting relations form the edges in the graph. The last decade has brought on a num- ber of exciting research papers that apply graph-based methods to an increasingly large range of natural language problems, ranging from lexical acquisition to text summarization. In this article, we overview several of these methods and their application to natural language pro- cessing. To reflect the fact that the algo- rithms and representations originate in different communities—natural language processing and graph theory—we will be using a dual vocabulary to describe these methods: networks are graphs, nodes are vertices, and links are edges. In terms of graph-based representations, depending on the natural language-pro- cessing application, a variety of node and

Upload: others

Post on 21-May-2020

2 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: Create a Personalized Summer Reading Program Website for …...Step 1: Create a free WordPress Blog If you create a blog for the children’s program and a separate blog for the YA

Ideas from Sarah Lawton, Ilsley Public Library, Middlebury

Create a Personalized Summer Reading Program Website for Free

Setting up this website will require knowledge of using WordPress and Google Forms. For more information on Wordpress please visit http://en.support.wordpress.com/get-started/. For more information about creating Google Forms visit: http://support.google.com/drive/bin/answer.py?hl=en&answer=87809. The Dream Big, Read website created by Sarah Lawton, Ilsley Public Library, Middlebury, can be viewed here for inspiration: http://ilsleydreambig.wordpress.com/. Step 1: Create a free WordPress Blog

If you create a blog for the children’s program and a separate blog for the YA program you can brand each

with the specific clipart and slogan for that program.

Disable comments and timestamps - this will help the site look more like a website and less like a blog.

Suggested links to have: Summer Reading home (if your blog has more than one page), Library Catalog,

Teen Reading Program (if you have a separate site), Library Homepage

Step 2: Create a Google Form

You can have separate forms for the children’s and YA programs, but having just one form allows you to

keep all of the registration information together, as well as making it easier to spot duplicates if they

enter registration information on both sites.

Suggested form fields: First Name, Last Name, Email Address, School, Grade, Reading Goal

Add the registration form to the Summer Reading Program blog in one of the following ways:

o Copy the embed code from Google Drive to a new page in the blog. This will display the form on

your website.

o Add an image to the blog home page (such as a ‘Register here!’ picture) that links to the form

o Copy the embed code from Google Drive to a widget placed in the sidebar.

o Use the image widget to add a linked image in the sidebar. This will display the form in the

sidebar.

You can also use the same Google form to keep track of how many books each participant reads. Create a

new column in the spreadsheet generated by the form and update it whenever a new punchcard is

handed in or a new total is given to you.

Make sure to keep an up-to-date copy saved to your computer as backup!

Tips:

Another way to use Google Forms is to gather book reviews. Sarah Lawton from the Ilsley Public Library in

Middlebury gathers “Book Blurbs” from her readers. This form asks for the participants name, the book title and

author, a short review of the book, as well as asking permission to use their name and/or review on the website.

You can create another page in the WordPress blog to post these blurbs.

Page 2: Create a Personalized Summer Reading Program Website for …...Step 1: Create a free WordPress Blog If you create a blog for the children’s program and a separate blog for the YA

Ideas from Sarah Lawton, Ilsley Public Library, Middlebury

You can download the information from the Google form at any time, or view it in Google Drive. The email

addresses can be copied and used when sending out SRP newsletters or information about events and programs.

By asking users for their grade it is easy to sort the list and gather information specific to the children or YA

programs. Having all of this information in one place will make submitting SRP statistics at the end of the summer a

breeze!

Customize your WordPress site by adding sidebar widgets from sites like Goodreads and TeachingBooks.net as well

as adding any specific information about your library’s Summer Reading Program.

Once you have finished, simply put a link to the WordPress site on your library’s website.

If you have any questions please contact April Kelley at [email protected] or (802) 828-2721.