Filtering by
- All Subjects: Evaluation
- All Subjects: Information Technology
- Creators: Baral, Chitta
- Creators: Anselin, Luc
- Status: Published
Choropleth maps are a common form of online cartographic visualization. They reveal patterns in spatial distributions of a variable by associating colors with data values measured at areal units. Although this capability of pattern revelation has popularized the use of choropleth maps, existing methods for their online delivery are limited in supporting dynamic map generation from large areal data. This limitation has become increasingly problematic in online choropleth mapping as access to small area statistics, such as high-resolution census data and real-time aggregates of geospatial data streams, has never been easier due to advances in geospatial web technologies. The current literature shows that the challenge of large areal data can be mitigated through tiled maps where pre-processed map data are hierarchically partitioned into tiny rectangular images or map chunks for efficient data transmission. Various approaches have emerged lately to enable this tile-based choropleth mapping, yet little empirical evidence exists on their ability to handle spatial data with large numbers of areal units, thus complicating technical decision making in the development of online choropleth mapping applications. To fill this knowledge gap, this dissertation study conducts a scalability evaluation of three tile-based methods discussed in the literature: raster, scalable vector graphics (SVG), and HTML5 Canvas. For the evaluation, the study develops two test applications, generates map tiles from five different boundaries of the United States, and measures the response times of the applications under multiple test operations. While specific to the experimental setups of the study, the evaluation results show that the raster method scales better across various types of user interaction than the other methods. Empirical evidence also points to the superior scalability of Canvas to SVG in dynamic rendering of vector tiles, but not necessarily for partial updates of the tiles. These findings indicate that the raster method is better suited for dynamic choropleth rendering from large areal data, while Canvas would be more suitable than SVG when such rendering frequently involves complete updates of vector shapes.
To boost students’ learning experience, adaptive selection was built on the generated questions. Bayesian Knowledge Tracing was used as embedded assessment of the student’s current competence so that a suitable question could be selected based on the student’s previous performance. A between-subjects experiment with 42 participants was performed, where half of the participants studied with adaptive selected questions and the rest studied with mal-adaptive order of questions. Both groups significantly improved their test scores, and the participants in adaptive group registered larger learning gains than participants in the control group.
To explore the possibility of generating rich instructional feedback for machine-generated questions, a question-paragraph mapping task was identified. Given a set of questions and a list of paragraphs for a textbook, the goal of the task was to map the related paragraphs to each question. An algorithm was developed whose performance was comparable to human annotators.
A multiple-choice question with high quality distractors (incorrect answers) can be pedagogically valuable as well as being much easier to grade than open-response questions. Thus, an algorithm was developed to generate good distractors for multiple-choice questions. The machine-generated multiple-choice questions were compared to human-generated questions in terms of three measures: question difficulty, question discrimination and distractor usefulness. By recruiting 200 participants from Amazon Mechanical Turk, it turned out that the two types of questions performed very closely on all the three measures.
The task of NLI is to determine the possibility of a sentence referred to as “Hypothesis” being true given that another sentence referred to as “Premise” is true. In other words, the task is to identify whether the “Premise” entails, contradicts or remains neutral with regards to the “Hypothesis”. NLI is a precursor to solving many Natural Language Processing (NLP) tasks such as Question Answering and Semantic Search. For example, in Question Answering systems, the question is paraphrased to form a declarative statement which is treated as the hypothesis. The options are treated as the premise. The option with the maximum entailment score is considered as the answer. Considering the applications of NLI, the importance of having a strong NLI system can't be stressed enough.
Many large-scale datasets and models have been released in order to advance the field of NLI. While all of these models do get good accuracy on the test sets of the datasets they were trained on, they fail to capture the basic understanding of “Entities” and “Roles”. They often make the mistake of inferring that “John went to the market.” from “Peter went to the market.” failing to capture the notion of “Entities”. In other cases, these models don't understand the difference in the “Roles” played by the same entities in “Premise” and “Hypothesis” sentences and end up wrongly inferring that “Peter drove John to the stadium.” from “John drove Peter to the stadium.”
The lack of understanding of “Roles” can be attributed to the lack of such examples in the various existing datasets. The reason for the existing model’s failure in capturing the notion of “Entities” is not just due to the lack of such examples in the existing NLI datasets. It can also be attributed to the strict use of vector similarity in the “word-to-word” attention mechanism being used in the existing architectures.
To overcome these issues, I present two new datasets to help make the NLI systems capture the notion of “Entities” and “Roles”. The “NER Changed” (NC) dataset and the “Role-Switched” (RS) dataset contains examples of Premise-Hypothesis pairs that require the understanding of “Entities” and “Roles” respectively in order to be able to make correct inferences. This work shows how the existing architectures perform poorly on the “NER Changed” (NC) dataset even after being trained on the new datasets. In order to help the existing architectures, understand the notion of “Entities”, this work proposes a modification to the “word-to-word” attention mechanism. Instead of relying on vector similarity alone, the modified architectures learn to incorporate the “Symbolic Similarity” as well by using the Named-Entity features of the Premise and Hypothesis sentences. The new modified architectures not only perform significantly better than the unmodified architectures on the “NER Changed” (NC) dataset but also performs as well on the existing datasets.