Neural relation extraction within and across sentence boundaries

A computer-implemented method for inter-sententially determining a semantic relationship between a first entity and a second entity in a natural language document, comprising at least the steps of:

• generating a first dependency parse tree, DPT, for a first origin sentence of the document which comprises the first entity, wherein each DPT comprises at least a root node;
• generating a second DPT for a second origin sentence of the document which mentions the second entity;
• linking the root nodes of the first DPT and the second DPT so as to create a chain of words, COW, from the first entity to the second entity;
• determining for each word in the COW a subtree comprising the word itself as well as, if applicable, all words depending as nodes from said words as a root;
• generating for each word in the COW a subtree embedding vector cw which, in case the word in the COW has a subtree, is based at least on word embedding vectors xw of the words of the subtree;
• generating a representation vector pw for each word in the COW, wherein the representation vector pw for each word comprises a word embedding vector xw for said word itself as well as its subtree embedding vector cw;
• inputting the representation vectors pw for each word in the COW into a recurrent neural network;
• and
• classifying, using the recurrent neural network, the semantic relationship between the first entity and the second entity, based on the input representation vectors pw.