Andrew B. Goldberg

Improving Reading to Improve Math

Reading provides information across the curriculum. Thus, to the extent that fundamental (i.e., generalizable) reading comprehension strategies can be taught, the benefits should be found in multiple domains. To test this claim, children in the third and fourth grades read by simulating text content using the two-part, embodied Moved by Reading intervention. While reading six initial texts, children literally manipulated pictures on a computer screen to simulate sentence content; next, for additional texts the children imagined the manipulation of the pictures. These additional texts were in the form of mathematical story problems. Compared to a control condition, children using Moved by Reading solved more problems correctly, and this improvement is mainly attributed to a 35% reduction in the use of irrelevant numerical information in solution attempts. Thus, Moved by Reading teaches a fundamental strategy that encourages the sense-making that can aid mathematical story problem solution.

Improving classification accuracy using automatically extracted training data

Classification is a core task in knowledge discovery and data mining, and there has been substantial research effort in developing sophisticated classification models. In a parallel thread, recent work from the NLP community suggests that for tasks such as natural language disambiguation even a simple algorithm can outperform a sophisticated one, if it is provided with large quantities of high quality training data. In those applications, training data occurs naturally in text corpora, and high quality training data sets running into billions of words have been reportedly used. We explore how we can apply the lessons from the NLP community to KDD tasks. Specifically, we investigate how to identify data sources that can yield training data at low cost and study whether the quantity of the automatically extracted training data can compensate for its lower quality. We carry out this investigation for the specific task of inferring whether a search query has commercial intent. We mine toolbar and click logs to extract queries from sites that are predominantly commercial (e.g., Amazon) and non-commercial (e.g., Wikipedia). We compare the accuracy obtained using such training data against manually labeled training data. Our results show that we can have large accuracy gains using automatically extracted training data at much lower cost.

Some new directions in graph-based semi-supervised learning

In this position paper, we first review the state-of-the-art in graph-based semi-supervised learning, and point out three limitations that are particularly relevant to multimedia analysis: (1) rich data is restricted to live on a single manifold; (2) learning must happen in batch mode; and (3) the target label is assumed smooth on the manifold. We then discuss new directions in semi-supervised learning research that can potentially overcome these limitations: (i) modeling data as a mixture of multiple manifolds that may intersect or overlap; (ii) online semi-supervised learning that learns incrementally with low computation and memory needs; and (iii) learning spectrally sparse but non-smooth labels with compressive sensing. We give concrete examples in each new direction. We hope this article will inspire new research that makes semi-supervised learning an even more valuable tool for multimedia analysis.