Semantic inference is a core component of many natural language applications. In response, several researchers have developed algorithms for automatically learning inference rules...
This paper presents a novel automatic approach to partially integrate FrameNet and WordNet. In that way we expect to extend FrameNet coverage, to enrich WordNet with frame semanti...
Many traditional information retrieval models, such as BM25 and language modeling, give good retrieval effectiveness, but can be difficult to implement efficiently. Recently, docum...
Abstract. We investigate the potential of coherence-based scores to predict query difficulty. The coherence of a document set associated with each query word is used to capture the...
Predicting possible code-switching points can help develop more accurate methods for automatically processing mixed-language text, such as multilingual language models for speech ...