Semantic knowledge in word completion

We propose an integrated approach to interactive word-completion for users with linguistic disabilities in which semantic knowledge combines with n-gram probabilities to predict semantically moreappropriate words than n-gram methods alone. First, semantic relatives are found for English words, specifically for nouns, and they form the semantic knowledge base. The selection process for these semantically related words is first to rank the pointwise mutual information of co-occurring words in a large corpus and then to identify the semantic relatedness of these words by a Lesk-like filter. Then, the semantic knowledge is used to measure the semantic association of completion candidates with the context. Those that are semantically appropriate to the context are promoted to the top positions in prediction lists due to their high association with context. Experimental results show a performance improvement when using the integrated model for the completion of nouns. Categories and Subj...

• Type: Conference
• Year: 2005
• Where: ASSETS
• Authors: Jianhua Li, Graeme Hirst
• Keywords: ASSETS 2005, Emerging Technology, Pointwise Mutual Information, Semantic Knowledge, Semantic Knowledge Combines