Determining semantic similarity of texts based on sub-sections thereof

Systems and methods are provided to compare a target sample of text 1102 to a set of textual records 1100, each textual record 1100 including a sample of text 1102 and an indication of one or more segments of text within the sample of text 1102. Semantic similarity values between the target sample of text and each of the textual records are determined. Determining a particular semantic similarity value between the target sample of text 1102 and a particular textual record 1100 of the corpus includes: (i) determining individual semantic similarity values between the target sample of text 1102 and each of the segments of text indicated by the particular textual record 1100, and (ii) generating the particular semantic similarity value between the target sample of text 1102 and the particular textual record 1100 based on the individual semantic similarity values. A textual record 1100 is then selected based on the semantic similarities.