This work investigates whether the development of ideas in writing can be captured by graph properties derived from the text. Focusing on student essays, we represent the essay as a graph, and encode a variety of graph properties including PageRank as features for modeling essay scores related to quality of development. We demonstrate that our approach improves on a stateof-the-art system on th...

This paper investigates the use of promptbased content features for the automated assessment of spontaneous speech in a spoken language proficiency assessment. The results show that single highest performing promptbased content feature measures the number of unique lexical types that overlap with the listening materials and are not contained in either the reading materials or a sample response,...

We present a compositional framework for modelling entity-level sentiment (sub)contexts, and demonstrate how holistic multi-entity polarity scoring emerges as a by-product of compositional sentiment parsing. A data set of five annotators’ multi-entity judgements is presented, and a human ceiling is established for the challenging new task. The accuracy of an initial implementation, which includ...

Existing speaking tests only require nonnative speakers to engage in dialogue when the assessment is done by humans. This paper examines the viability of using off-the-shelf systems for spoken dialogue and for speech grading to automate the holistic scoring of the conversational speech of non-native speakers of English.

The purpose of the current study was to analyze the relationship between automated essay scoring (AES) and human scoring in order to determine the validity and usefulness of AES for large-scale placement tests. Specifically, a correlational research design was used to examine the correlations between AES performance and human raters’ performance. Spearman rank correlation coefficient tests were...

The automated scoring of second-language (L2) learner text along various writing dimensions is an increasingly active research area. In this paper, we focus on determining the topical relevance of an essay to the prompt that elicited it. Given the burden involved in manually assigning scores for use in training supervised prompt-relevance models, we develop unsupervised models and show that the...

We compared three term scoring methods in their ability to extract descriptive terms from a knowledge worker’s document collection. We compared the methods in two different evaluation scenarios, both from the perspective of the user: a per-term evaluation, and a holistic (term cloud) evaluation. We found that users tend to prefer a term scoring method that gives a higher score to multi-word ter...

The purpose of this family-focused, grounded-theory study was to develop a substantive theory that explains how individual family members heal in the aftermath of youth suicide. Individual healing following youth suicide is conceptualized as a process of "journeying toward wholeness." In response to youth suicide, survivors characteristically tap into their innate strengths and coping capabilit...