180 likes | 303 Vues
This text delves into the intricacies of pronoun resolution in language processing, emphasizing the importance of syntax, semantics, and world knowledge. It discusses various examples illustrating how grammatical roles and sentence structure affect interpretation. The text also references Hobbs’ seminal 1978 study on resolving pronoun references, highlighting the limitations of naive algorithms and advocating for more sophisticated, knowledge-based approaches. Ultimately, it argues that a thorough understanding of both syntax and semantics is essential for effective information extraction and summarization in natural language processing.
E N D
Why people care • Classic: "text understanding" • Information extraction, information retrieval, summarization…
What influences pronoun resolution? • Syntax • Semantics/world knowledge
Why syntax matters • John kicked Bill. Mary told him to go home. • Bill was kicked by John. Mary told him to go home. • John kicked Bill. Mary punched him.
Why syntax matters • John kicked Bill. Mary told him to go home. • Bill was kicked by John. Mary told him to go home. • John kicked Bill. Mary punched him. John
Why syntax matters • John kicked Bill. Mary told him to go home. • Bill was kicked by John. Mary told him to go home. • John kicked Bill. Mary punched him. Bill
Why syntax matters • John kicked Bill. Mary told him to go home. • Bill was kicked by John. Mary told him to go home. • John kicked Bill. Mary punched him. Bill
Why syntax matters • John kicked Bill. Mary told him to go home. • Bill was kicked by John. Mary told him to go home. • John kicked Bill. Mary punched him. Grammatical role hierarchy
Why syntax matters • John kicked Bill. Mary told him to go home. • Bill was kicked by John. Mary told him to go home. • John kicked Bill. Mary punched him. Grammatical role parallelism
Why semantics matters The city council denied the demonstrators a permit because they {feared|advocated} violence.
Why semantics matters The city council denied the demonstrators a permit because they {feared|advocated} violence.
Why semantics matters The city council denied the demonstrators a permit because they {feared|advocated} violence.
Why knowledge matters • John hit Bill. He was severely injured.
Margaret Thatcher admires Hillary Clinton, and George W. Bush absolutely worships her. Why Knowledge Matters
A search-based solution • Hobbs 1978: Resolving pronoun references
Hobbs 1978 • Assessment of difficulty of problem • Incidence of the phenomenon • A simple algorithm that has become a baseline
Hobbs’s point …the naïve approach is quite good. Computationally speaking, it will be a long time before a semantically based algorithm is sophisticated enough to perform as well, and these results set a very high standard for any other approach to aim for.
Hobbs’s point Yet there is every reason to pursue a semantically based approach. The naïve algorithm does not work. Any one can think of examples where it fails. In these cases it not only fails; it gives no indication that it has failed and offers no help in finding the real antecedent. (p. 345)