2000 character limit reached
Table2Vec: Neural Word and Entity Embeddings for Table Population and Retrieval (1906.00041v1)
Published 31 May 2019 in cs.IR, cs.CL, and cs.LG
Abstract: Tables contain valuable knowledge in a structured form. We employ neural LLMing approaches to embed tabular data into vector spaces. Specifically, we consider different table elements, such caption, column headings, and cells, for training word and entity embeddings. These embeddings are then utilized in three particular table-related tasks, row population, column population, and table retrieval, by incorporating them into existing retrieval models as additional semantic similarity signals. Evaluation results show that table embeddings can significantly improve upon the performance of state-of-the-art baselines.