A Word Embedding based Generalized Language Model for Information Retrieval

Word2vec, a word embedding technique, has gained significant interest among researchers in natural language processing (NLP) in recent years. The embedding of the word vectors helps to identify a list of words that are used in similar contexts with respect to a given word. In this paper, we focus on the use of word embeddings for enhancing retrieval effectiveness. In particular, we construct a generalized language model, where the mutual independence between a pair of words (say t and t') no longer holds. Instead, we make use of the vector embeddings of the words to derive the transformation probabilities between words. Specifically, the event of observing a term t in the query from a document d is modeled by two distinct events, that of generating a different term t', either from the document itself or from the collection, respectively, and then eventually transforming it to the observed query term t. The first event of generating an intermediate term from the document intends to capture how well a term fits contextually within a document, whereas the second one of generating it from the collection aims to address the vocabulary mismatch problem by taking into account other related terms in the collection. Our experiments, conducted on the standard TREC 6-8 ad hoc and Robust tasks, show that our proposed method yields significant improvements over language model (LM) and LDA-smoothed LM baselines.