Good news! We've added a new model to our product suite - Coreference Resolution. This model is designed to improve the downstream processing of your data by resolving coreferences in text.
Coreference resolution is the process of identifying and resolving references to the same entity in a text. For example, in the sentence "John and Mary went to the store", "John" and "Mary" refer to the same person. Coreference resolution is a challenging task because it requires an understanding of the semantic relationships between words.
An example of coreference resolution
Because content is analysed and parsed into triples sentence by sentence, coreference resolution allows you to resolve references to the same entity across multiple triples where the sentence might not include a name at all.
Later steps for entity resolution achieve better results because the triples are already pointing to the same entity.
No, coreference resolution is automatically integrated into all text processing. When you ingest a graph, our AI-based entity resolution model automatically identifies and links related mentions, handling both within-sentence references ("John picked up his coffee") and cross-sentence references ("John entered the room. He sat down."). This built-in functionality eliminates the need to implement a separate coreference resolution system.
