We propose an alternative evaluation metric to Word Error Rate (WER) for the decision audit task of meeting recordings, which exemplifies how to evaluate speech recognition within a legitimate application context. Using machine learning on an initial seed of human-subject experimental data, our alternative metric handily outperforms WER, which correlates very poorly with human subjects' success in finding decisions given ASR transcripts with a range of WERs.

There are numerous studies suggesting that published news stories have an important effect on the direction of the stock market, its volatility, the volume of trades, and the value of individual stocks mentioned in the news. There is even some published research suggesting that automated sentiment analysis of news documents, quarterly reports, blogs and/or twitter data can be productively used as part of a trading strategy. This paper presents just such a family of trading strategies, and then uses this application to reexamine some of the tacit assumptions behind how sentiment analyzers are generally evaluated, in spite of the contexts of their application. This discrepancy comes at a cost.

This paper compares the performance of position-specific posterior lattices (PSPL) and confusion networks applied to spoken utterance retrieval, and tests these recent proposals against several baselines in two disparate domains. These lossy methods provide compact representations that generalize the original segment lattices and provide greater recall and robustness, but have yet to be evaluated against each other in multiple WER conditions for spoken utterance retrieval. Our comparisons suggest that while PSPL and confusion networks have comparable recall, the former is slightly more precise, although its merit appears to be coupled to the assumptions of low-frequency search queries and low-WER environments.

There are numerous studies suggesting that published news stories have an important effect on the direction of the stock market, its volatility, the volume of trades, and the value of individual stocks mentioned in the news. There is even some published research suggesting that automated sentiment analysis of news documents, quarterly reports, blogs and/or Twitter data can be productively used as part of a trading strategy. This paper presents just such a family of trading strategies, and then uses this application to re-examine some of the tacit assumptions behind how sentiment analyzers are generally evaluated, in spite of the contexts of their application. This discrepancy comes at a cost.

For the past 73 years, the CBC has disseminated a unique Canadian perspective across the world, producing a phenomenally rich multimedia record of the country and our social, political and cultural heritage and news. This project utilizes visualization and sonification of portions of an enormous historical CBC Newsworld data corpus to enable an "on this day" experience for viewers. The digitized collection of 24-hour news videos spans a 24-year period within an immersive multiscreen environment, to enable gesture-driven context-aware browsing, information seeking, and segment review. Employing natural language processing technologies, the interface displays keywords and key phrases identified in the transcripts, enabling serendipitous video search and display and offering a unique browsing opportunity within this rich "big data" corpus.