Assessing student understanding by evaluating their free text answers to posed questions is a very important task. However, manually, it is time-consuming and computationally, it is difficult. This paper details our shallow NLP approach to computationally assessing student free text answers when a reference answer is provided. For four out of the five test sets, our system achieved an overall accuracy above the median and mean.

A key challenge facing educational technology researchers is how to provide structure and guidance when learners use unstructured and open tools such as digital libraries for their own learning. This work attempts to use computational methods to identify that structure in a domain independent way and support learners as they navigate and interpret the information they find. This article highlights a computational methodology for generating a pedagogical sequence through core learning goals extracted from a collection of resources which in this case, are resources from the Digital Library for Earth System Education (DLESE). This article describes how we use the technique of multi-document summarization to extract the core learning goals from the digital library resources and how we create a supervised classifier that performs a pair-wise classification of the core learning goals; the judgments from these classifications are used to automatically generate pedagogical sequences. Results show that we can extract good core learning goals and make pair-wise classifications that are up to 76% similar to the pair-wise classifications generated from pedagogical sequences created by two science education experts. Thus we can dynamically generate pedagogically meaningful learning paths through digital library resources.

Recommender systems have become part of the standard toolkit of web personalization. These same tools and techniques are now making their way into educational and adaptive e-learning systems. In this chapter, we will discuss aspects of a prototype system, the Customized Learning Service for Concept Knowledge (CLICK), an application designed to provide digital library resources recommendations based on user’s concept knowledge demonstrated through automated evaluation and approximation of their knowledge state from essay writing. We present the underlying concepts behind recommender systems, review learner models as they are designed within the CLICK environment, and review the lessons learned. We will discuss aspects of how CLICK supports intentional learning as well as extensions to the existing technology to improve such support. Future challenges and directions for CLICK and related technologies are also discussed.

This paper describes the results of a study designed to assess human expert ratings of educational concept features for use in automatic core concept extraction systems. Digital library resources provided the content base for human experts to annotate automatically extracted concepts on seven dimensions: coreness, local importance, topic, content, phrasing, structure, and function. The annotated concepts were used as training data to build a machine learning classifier as part of a tool used to predict the core concepts in the document. These predictions were compared with the experts' judgment of concept coreness.

We present initial steps towards an interactive essay writing tutor that improves science knowledge by analyzing student essays for misconceptions and recommending science webpages that help correct those misconceptions. We describe the five components in this system: identifying core science concepts, determining appropriate pedagogical sequences for the science concepts, identifying student misconceptions in essays, aligning student misconceptions to science concepts, and recommending webpages to address misconceptions. We provide initial models and evaluations of the models for each component.

With all the information available on the web, there is a growing need to provide mobile access to this information for the large, growing population of mobile internet users. In this paper, we propose a solution to the problem of open web mobile information retrieval, by conducting a dialogue with the user over a simple text-based interface. Using techniques from NLP, web page analysis, and information extraction, our approach automatically navigates web sites on the user's behalf and extracts specific information from those sites to present to the user textually. Empirical evaluation shows that our approach to open web information retrieval is feasible, and a qualitative evaluation validates that such a system meets user needs for mobile information access.

This paper presents preliminary results on a generalizability study that was carried out to evaluate the robustness of a knowledge extraction algorithm.

This paper presents an empirical learning study using a prototype system designed to provide fully automatic, domain-independent conceptual personalization algorithms. The prototype system, the Customized Learning Service for Concept Knowledge (CLICK), was implemented as an adaptive essay writing environment in a scientific domain. Results demonstrate that conceptual personalization promotes deep metacognitive strategies during online learning, and these strategies correlate with deep domain understanding.

In this paper we presented an approach to question generation based on syntactic and keyword modeling. In particular, we use parse tree manipulation, named entity recognition, and Up-Keys (significant phrases in a document) to generate factoid and definitional questions from input documents. We describe how to generate different types of question from a single input sentence, including Yes-No, Who, What, Where and How questions. We present evaluation for our factoid question generation method, and we discuss our plans to use question generation for question