Relation discovery from web data for competency management

In current organizations, valuable enterprise knowledge is often buried under rapidly expanding huge amount of unstructured information in the form of web pages, blogs, and other forms of human text communications. We present a novel unsupervised machine learning method called CORDER (COmmunity Relation Discovery by named Entity Recognition) to turn these unstructured data into structured information for knowledge management in these organizations. CORDER exploits named entity recognition and co-occurrence data to associate individuals in an organization with their expertise and associates. We discuss the problems associated with evaluating unsupervised learners and report our initial evaluation experiments in an expert evaluation, a quantitative benchmarking, and an application of CORDER in a social networking tool called BuddyFinder.

ESpotter : adaptive named entity recognition for web browsing

Browsing constitutes an important part of the user information searching process on the Web. In this paper, we present a browser plug-in called ESpotter, which recognizes entities of various types on Web pages and highlights them according to their types to assist user browsing. ESpotter uses a range of standard named entity recognition techniques. In addition, a key new feature of ESpotter is that it addresses the problem of multiple domains on the Web by adapting lexicon and patterns to these domains.

Community relation discovery by named entities

Discovering who works with whom, on which projects and with which customers is a key task in knowledge management. Although most organizations keep models of organizational structures, these models do not necessarily accurately reflect the reality on the ground. In this paper we present a text mining method called CORDER which first recognizes named entities (NEs) of various types from Web pages, and then discovers relations from a target NE to other NEs which co-occur with it. We evaluated the method on our departmental Website. We used the CORDER method to first find related NEs of four types (organizations, people, projects, and research areas) from Web pages on the Website and then rank them according to their co-occurrence with each of the people in our department. 20 representative people were selected and each of them was presented with ranked lists of each type of NE. Each person specified whether these NEs were related to him/her and changed or confirmed their rankings. Our results indicate that the method can find the NEs with which these people are closely related and provide accurate rankings.

Browsing for information by highlighting automatically generated annotations:a user study and evaluation

The realization of the Semantic Web is constrained by a knowledge acquisition bottleneck, i.e. the problem of how to add RDF mark-up to the millions of ordinary web pages that already exist. Information Extraction (IE) has been proposed as a solution to the annotation bottleneck. In the task based evaluation reported here, we compared the performance of users without access to annotation, users working with annotations which had been produced from manually constructed knowledge bases, and users working with annotations augmented using IE. We looked at retrieval performance, overlap between retrieved items and the two sets of annotations, and usage of annotation options. Automatically generated annotations were found to add value to the browsing experience in the scenario investigated. Copyright 2005 ACM.

Do educators need educating?

Actual text: I was recently at the Spanish College of Optometry biennial conference and attended a meeting of contact lens lecturers from around Spain and Portugal. We discussed various ideas, mainly about how to share good practice and improve standards. What came to my mind was ‘is there a blueprint for training trainers?’ Well probably not but there are many things that we need to acknowledge such as the way students learn for example. Many educators themselves were taught by lecturers who would write on a blackboard or use acetate on an overhead projector, then came the 35 mm slide era followed by the Powerpoint era. More recently there is a move towards a much more integrated approach of various teaching methods. At my university our contact lens and anterior eye lectures generally follow a format where a narrated Powerpoint lecture is uploaded onto our internal virtual learning environment. This narrated version of the slides is designed to give the didactic element of the topic. The students listen to that before attending an interactive seminar on that topic. The seminar is also recorded so that students can listen to that afterwards. The seminar is designed to give additional information, such as case reports, or to clarify key points or for live demonstrations. It is a good way of doubling the contact time with the students without imposing further on an already packed formal timetable as the students can work in their own time. One problem that we noticed with this approach was that attendance can vary. If the students feel that they will gain something from the interactive seminar then they are more likely to attend – exam tips usually win them over! At the Spanish meeting the educators decided that they wanted to have regular meetings. The industry colleagues in attendance said that they were happy to help but could not necessarily give money, but they could offer meeting rooms, pay for lunch and evening meals. They even said that that they were happy to host meetings and invite other companies too (except to manufacturing plants). In the UK the British Committee of Contact Lens Educators (BUCCLE) meets for one day on three occasions in the year. The American Optometric Contact Lens Educators (AOCLE) meets annually at a three day event. Both these organisations get some help from industry. BUCCLE usually has one of its meetings at a university, one at a company training centre/manufacturing plant/national headquarters and one meeting the day before the BCLA annual conference. BUCCLE usually has its pre-BCLA meeting in conjunction with the International Association of Contact Lens Educators (IACLE). So when educators meet what would they discuss; well probably the focus should be on education rather than actual contact lens knowledge. For example sharing ideas on how to teach toric lens fitting would be better than discussing the actual topic of toric lenses itself. Most universities will have an education department with an expert who could share ideas on how to use the internet in teaching or how to structure lectures or assessments etc. In the past I have helped with similar training programmes in other countries and sharing good practice in pedagogy is always a popular topic. Anyone who is involved in education in the field of contact lenses should look at the IACLE web page and look out for the IACLE World Congress in 2015 in the days preceding the BCLA. Finally, IACLE, AOCLE and BUCCLE all exist as a result of generous educational grants from contact lens companies and anyone interested in finding out more about should refer to their respective web pages.

Connecting social media to e-commerce:cold-start product recommendation using microblogging information

In recent years, the boundaries between e-commerce and social networking have become increasingly blurred. Many e-commerce websites support the mechanism of social login where users can sign on the websites using their social network identities such as their Facebook or Twitter accounts. Users can also post their newly purchased products on microblogs with links to the e-commerce product web pages. In this paper, we propose a novel solution for cross-site cold-start product recommendation, which aims to recommend products from e-commerce websites to users at social networking sites in 'cold-start' situations, a problem which has rarely been explored before. A major challenge is how to leverage knowledge extracted from social networking sites for cross-site cold-start product recommendation. We propose to use the linked users across social networking sites and e-commerce websites (users who have social networking accounts and have made purchases on e-commerce websites) as a bridge to map users' social networking features to another feature representation for product recommendation. In specific, we propose learning both users' and products' feature representations (called user embeddings and product embeddings, respectively) from data collected from e-commerce websites using recurrent neural networks and then apply a modified gradient boosting trees method to transform users' social networking features into user embeddings. We then develop a feature-based matrix factorization approach which can leverage the learnt user embeddings for cold-start product recommendation. Experimental results on a large dataset constructed from the largest Chinese microblogging service Sina Weibo and the largest Chinese B2C e-commerce website JingDong have shown the effectiveness of our proposed framework.