Statistical Machine Translation (SMT) is based on alignment models which learn from bilingual corpora the word correspondences between source and target language. These models are...
We propose a novel approach to crosslingual language model (LM) adaptation based on bilingual Latent Semantic Analysis (bLSA). A bLSA model is introduced which enables latent topi...
In this study we will discuss our cross language text retrieval (CLIR) experiments of Persian ad hoc track at CLEF 2008. Two teams from University of Tehran were involved in cross...
Long-span features, such as syntax, can improve language models for tasks such as speech recognition and machine translation. However, these language models can be difficult to u...
Abstract--Until quite recently, extending Phrase-based Statistical Machine Translation (PBSMT) with syntactic knowledge caused system performance to deteriorate. The most recent su...