No abstract

This paper explores different approaches to multilingual intent classification in a low resource setting. Recent advances in multilingual text representations promise crosslingual transfer for classifiers. We investigate the potential for this transfer in an applied industrial setting and compare to multilingual classification using machine translated text. Our results show that while the recently developed methods show promise, practical application calls for a combination of techniques for useful results.

No abstract

This paper describes our participation in the SemEval-2016 task 5, Aspect Based Sentiment Analysis (ABSA). We participated in two slots in the sentence level ABSA (Subtask 1) namely: aspect category extraction (Slot 1) and sentiment polarity extraction (Slot 3) in English Restaurants and Laptops reviews. For Slot 1, we applied different models for each domain. In the restaurants domain, we used an ensemble classifier for each aspect which is a combination of a Convolutional Neural Network (CNN) classifier initialized with pretrained word vectors, and a Support Vector Machine (SVM) classifier based on the bag of words model. For the Laptops domain, we used only one CNN classifier that predicts the aspects based on a probability threshold. For Slot 3, we incorporated domain and aspect knowledge in one ensemble CNN classifier initialized with fine-tuned word vectors and used it in both domains. In the Restaurants domain, our system achieved the 2 nd and the 3 rd places in Slot 1 and Slot 3 respectively. However, we ranked the 8 th in Slot 1 and the 5 th in Slot 3 in the Laptops domain. Our extended experiments show our system could have ranked 2 nd in the Laptops domain in Slot 1 and Slot 3, had we followed the same approach we followed in the Restaurants domain in slot 1 and trained each domain separately in Slot 3.