The present application discloses a question answering method and language model training method, apparatus, device, and storage media, which relate to the field of natural language processing. A specific implementation is to: acquire at least one candidate table matching a question to be queried, where each candidate table includes a candidate answer corresponding to the question; process the at least one candidate table to obtain at least one table text, where the table text includes textual content of respective fields in the candidate table, and the fields include a title, a header and a cell; input the question and each table text into a preset language model respectively to obtain a degree of matching between the question and each candidate table; and output a reply table according to the degree of matching of each candidate table, where the reply table is a candidate table out of the at least one candidate table whose degree of matching with the question is greater than a preset value or a candidate table that corresponds to a maximum degree of matching. In the present application, a language model is used to perform semantic matching between a question and a text to improve the accuracy and recall rate of matching between the question and the table.
展开▼