Benjamin Stone
University of Melbourne
11 Papers
18 Citations
Benjamin Stone is an academic researcher from University of Melbourne. The author has contributed to research in topics: Latent semantic analysis & Semantic similarity. The author has an hindex of 4, co-authored 10 publications. Previous affiliations of Benjamin Stone include Ohio State University & University of Adelaide.
Chat about Author
Papers
Comparing Methods for Single Paragraph Similarity Analysis
TL;DR: The results suggest that when single paragraphs are compared, simple nonreductive models can provide better similarity estimates than more complex models (LSA, Topic Model, SpNMF, and CSM).
55
Automatic Annotation of Daily Activity from Smartphone-Based Multisensory Streams
Jihun Hamm,Benjamin Stone,Mikhail Belkin,Simon Dennis +3 more
- 11 Oct 2012
TL;DR: A flexible framework for incorporating heterogeneous sensory modalities combined with state-of-the-art classifiers for sequence labeling is presented, and the accuracy and efficiency of the proposed system for practical lifelogging applications are evaluated.
Using LSA Semantic Fields to Predict Eye Movement on Web Pages
Benjamin Stone,Simon Dennis +1 more
- 01 Jan 2007
TL;DR: A new method for estimating the visual saliency different areas displayed on a web page is outlined, similar to the Bloodhound Project’s close relative SNIF-ACT, which is a model based on the ACT-R cognitive architecture.
The Fallacy of an Airtight Alibi: Understanding Human Memory for “Where” Using Experience Sampling:
TL;DR: In this article, the ground truth of real-world events of interest is established by using a smartphone app to record data on adult participa-mentionee's activities and then using this data for alibi generation.
Semantic models and corpora choice when using Semantic Fields to predict eye movement on web pages
Benjamin Stone,Simon Dennis +1 more
TL;DR: Ten models are compared in their ability to predict eye-tracking data that was collected from 49 participants' goal-oriented search tasks on a total of 1809 Web pages and Vectorspace was the best performing semantic model in this study.
6