Systems and methods for coreference resolution

A method for coreference resolution, comprising:

• identifying training data comprising training text, mention annotation data, and coreference annotation data;
• encoding a plurality of candidate spans from the training text using an encoder network of a machine learning model to obtain a plurality of span vectors;
• extracting a plurality of entity mentions from the training text based on the plurality of span vectors using a mention extractor network of the machine learning model, wherein each of the plurality of entity mentions corresponds to one of the plurality of candidate spans;
• updating parameters of the mention extractor network in a first training phase based on the plurality of entity mentions and the mention annotation data;
• extracting an updated plurality of entity mentions from the training text based on the plurality of span vectors using the mention extractor network with the updated parameters;
• generating coreference information based on the updated plurality of entity mentions using a mention linker network of the machine learning model, wherein the coreference information indicates that a pair of candidate spans of the plurality of candidate spans corresponds to a pair of entity mentions that refer to a same entity;
• and
• updating the mention linker network in a second training phase based on the coreference information and the coreference annotation data.

An apparatus for coreference resolution, comprising:

• a machine learning model comprising:
• an encoder network configured to encode a plurality of candidate spans from a text to obtain a plurality of span vectors;
• a mention extractor network configured to extract a plurality of entity mentions from the text based on the plurality of span vectors, wherein the mention extractor network is trained based on mention annotation data in a first training phase and based on coreference annotation data in a second training phase;
• and
• a mention linker network configured to generate coreference information for the text based on the plurality of entity mentions, wherein the coreference information indicates that a pair of candidate spans of the plurality of candidate spans corresponds to a pair of entity mentions that refer to a same entity, and wherein the mention linker network is trained jointly with the mention extractor network on the coreference annotation data in the second training phase.