iKernels

Machine Learning and NLP group at Trento.

Repository

Software

  • uSVM-TK: integration of SVM-Light-TK and Cutting Plane Algorithm with uniform sampling

  • ConvNet for question-answer matching: Implementation of the Convolution Neural Network for factoid QA on the answer sentence selection task (Severyn, A. and Moschitti, A. Learning to Rank Short Text Pairs with Convolutional Deep Neural Networks. SIGIR, 2015)

Corpora

  • Semantic Mapping Corpora: a dataset of NL questions and SQL queries together with their correct and incorrect pairs, detected using kernel methods along with SVMs

  • The SenTube corpus can be downloaded from here (16MB). Video files are available on request.

  • All the corpus versions for WebCrow, an automatic crossword solver, are available here.

  • Two corpora for clustering questions into user intent are available here.