The semantic matching capabilities of neural information retrieval can ameliorate synonymy and polysemy problems of symbolic approaches.However, neural models' dense representations are more suitable for re-ranking, due to their inefficiency.Sparse representations, either in symbolic or latent form, are more efficient with an inverted index.Taking the merits of the sparse and dense representations, we propose an ultra-high dimensional (UHD) representation scheme equipped with directly controllable sparsity.UHD's large capacity and minimal noise and interference among the dimensions allow for binarized representations, which are highly efficient for storage and search.Also proposed is a bucketing method, where the embeddings from multiple layers of BERT are selected/merged to represent diverse linguistic aspects.We test our models with MS MARCO and TREC CAR, showing that our models outperforms other sparse models.

Information retrieval using word senses is emerging as a good research challenge on semantic information retrieval. In this paper, we propose a new method using word senses in information retrieval: root sense tagging method. This method assigns coarse-grained word senses defined in WordNet to query terms and document terms by unsupervised way using co-occurrence information constructed automatically. Our sense tagger is crude, but performs consistent disambiguation by considering only the single most informative word as evidence to disambiguate the target word. We also allow multiple-sense assignment to alleviate the problem caused by incorrect disambiguation.Experimental results on a large-scale TREC collection show that our approach to improve retrieval effectiveness is successful, while most of the previous work failed to improve performances even on small text collection. Our method also shows promising results when is combined with pseudo relevance feedback and state-of-the-art retrieval function such as BM25.