Anthony Aue

Pulse: mining customer opinions from free text

We present a prototype system, code-named Pulse, for mining topics and sentiment orientation jointly from free text customer feedback. We describe the application of the prototype system to a database of car reviews. Pulse enables the exploration of large quantities of customer free text. The user can examine customer opinion “at a glance” or explore the data at a finer level of detail. We describe a simple but effective technique for clustering sentences, the application of a bootstrapping approach to sentiment classification, and a novel user-interface.

Automatic Identification of Sentiment Vocabulary: Exploiting Low Association with Known Sentiment Terms

We describe an extension to the technique for the automatic identification and labeling of sentiment terms described in Turney (2002) and Turney and Littman (2002). Their basic assumption is that sentiment terms of similar orientation tend to co-occur at the document level. We add a second assumption, namely that sentiment terms of opposite orientation tend not to co-occur at the sentence level. This additional assumption allows us to identify sentiment-bearing terms very reliably. We then use these newly identified terms in various scenarios for the sentiment classification of sentences. We show that our approach outperforms Turneys original approach. Combining our approach with a Naive Bayes bootstrapping method yields a further small improvement of classifier performance. We finally compare our results to precision and recall figures that can be obtained on the same data set with labeled data.

Multilingual Dependency Parsing using Bayes Point Machines

We develop dependency parsers for Arabic, English, Chinese, and Czech using Bayes Point Machines, a training algorithm which is as easy to implement as the perceptron yet competitive with large margin methods. We achieve results comparable to state-of-the-art in English and Czech, and report the first directed dependency parsing accuracies for Arabic and Chinese. Given the multilingual nature of our experiments, we discuss some issues regarding the comparison of dependency parsers for different languages.

English-Japanese example-based machine translation using abstract linguistic representations

This presentation describes an example-based English-Japanese machine translation system in which an abstract linguistic representation layer is used to extract and store bilingual translation knowledge, transfer patterns between languages, and generate output strings. Abstraction permits structural neutralizations that facilitate learning of translation examples across languages with radically different surface structure characteristics, and allows MT development to proceed within a largely language-independent NLP architecture. Comparative evaluation indicates that after training in a domain the English-Japanese system is statistically indistinguishable from a non-customized commercially available MT system in the same domain.