How deeply does Knowledge Graphs and LLMs in Action cover coreference resolution?

Defines pronoun reference through an ambiguity example and notes shortened-name failures; stops short of specifying a resolution algorithm.

Coreference resolution

As explained in Knowledge Graphs and LLMs in Action

Coreference resolution is the technique of determining which entity or expression a referring phrase, such as a pronoun or shortened name, denotes.

Coreference resolution determines which entity a referring expression denotes. It is essential for interpreting text accurately and extracting consistent knowledge-graph facts. section 1.1 section 6.1

Pronoun ambiguity

In “John saw Bob and he waved,” “he” may refer to John or Bob. Real archives add harder cases: abbreviations such as “S.” or “U.Cal.” may need resolution to canonical names, which tested off-the-shelf models could not provide. section 1.1 section 6.1

Resolution operates alongside named entity recognition, entity resolution, disambiguation, and relation extraction. In specialized archives, prompted GPT successfully performed these tasks implicitly, while custom entity models and clustering may be needed for domain-specific terms. section 6.1 section 1.1

How Knowledge Graphs and LLMs in Action covers it

Cover of Knowledge Graphs and LLMs in Action

liveBook manning.com

Read Knowledge Graphs and LLMs in Action on liveBook Get the book at manning.com

Also explained in

liveBook manning.com

Natural Language Processing in Action, Second EditionCoreference resolution is the task of determining which entity or expression a referring expression, such as a pronoun, denotes in text.
liveBook manning.com

Graph Algorithms for Data ScienceCoreference resolution is the task of identifying expressions in text that refer to the same entity and linking them to that entity.

Compare how 3 books explain coreference resolution →

Related concepts

Corefereeimplemented by · Coreferee is an open-source spaCy extension for resolving coreferences in text.
structured extractionpart of · Structured extraction is the process of identifying specified information in source content and representing it as organized data in a defined structure.

This explainer was generated by Manning's knowledge graph from the text of Knowledge Graphs and LLMs in Action. The section links point to the parts of the book it draws on.