An apparatus, comprising a device for displaying multi-language typesetting, wherein the device comprises:
- one or more processors;
- a storage device, configured to store one or more programs;
- wherein when the one or more programs are executed by the one or more processors, the one or more processors are configured to:
- obtain a text to be typeset;
- identify embedded language content in a principal language text of the text to be typeset, wherein the embedded language content comprises at least one non-principal language content embedded in the principal language text;
- determine replacement content of the embedded language content, wherein an embedded language corresponding to the embedded language content is different from a principal language corresponding to the principal language text, and the identifying the embedded language content in the principal language text of the text to be typeset comprises identifying a non-principal language text in the principal language text and identifying through translation whether the non-principal language text forms a first word pair with its adjacent principal language text, wherein the first word pair is composed of a non-principal language text and a principal language text corresponding to the non-principal language text and the replacement content comprises a principal language text corresponding to the embedded language content or an abbreviation of a non-principal language text in the embedded language content;
- and
- replace the embedded language content with the replacement content;
- wherein the identifying through translation whether the non-principal language text forms the first word pair with its adjacent principal language text comprises:
- translating the non-principal language text into the principal language text, or translating the adjacent principal language text into the non-principal language text;
- determining a matching degree between the non-principal language text and the adjacent principal language text, wherein the matching degree comprises editing distance data determined based on a translation result, a similarity of word vectors, and/or the number of co-occurrences in the text, the editing distance data comprises an editing distance between the translated text and the adjacent text, or a ratio of the editing distance to a length of the translated text;
- calculating a probability that the non-principal language text forms the first word pair with its adjacent principal language text according to the matching degree;
- and
- determining whether the non-principal language text forms the first word pair with its adjacent principal language text according to the probability.