In recent work, we proposed an alternative to parallel text as translation model (TM) training data: audio recordings of parallel speech (pSp), as it occurs in any communication s...
We present Promodes, an algorithm for unsupervised word decomposition, which is based on a probabilistic generative model. The model considers segment boundaries as hidden variable...
In this paper, we propose an information retrieval model called Latent Interest Semantic Map (LISM), which features retrieval composed of both Collaborative Filtering(CF) and Prob...
The task of identifying synonymous relations and objects, or Synonym Resolution (SR), is critical for high-quality information extraction. The bulk of previous SR work assumed str...
Answer patterns have been shown to improve the performance of open-domain factoid QA systems. Their use, however, requires either constructing the patterns manually or developing ...