Anaphora in Natural Language Understanding: A Survey by Graeme Hirst (auth.)

By Graeme Hirst (auth.)

Show description

Read or Download Anaphora in Natural Language Understanding: A Survey PDF

Similar ai & machine learning books

Intelligent Systems

The sector of commercial electronics covers a plethora of difficulties which has to be solved in business perform. digital structures keep an eye on many approaches that start with the keep watch over of rather uncomplicated units like electrical cars, via extra complex units comparable to robots, to the keep watch over of whole fabrication techniques.

Predicting Prosody from Text for Text-to-Speech Synthesis

Predicting Prosody from textual content for Text-to-Speech Synthesis covers the explicit facets of prosody, normally targeting tips to are expecting the prosodic details from linguistic textual content, after which the best way to make the most the anticipated prosodic wisdom for varied speech functions. writer ok. Sreenivasa Rao discusses proposed equipment besides state of the art innovations for the purchase and incorporation of prosodic wisdom for constructing speech structures.

Automated Planning and Acting

Self reliant AI structures desire complicated computational suggestions for making plans and acting activities. making plans and appearing require major deliberation simply because an clever method needs to coordinate and combine those actions with the intention to act successfully within the actual global. This ebook offers a complete paradigm of making plans and appearing utilizing the newest and complex automated-planning suggestions.

Extra resources for Anaphora in Natural Language Understanding: A Survey

Example text

6 A m b i g u i t y i n a n a p h o r a a n d d e f a u l t a n t e c e d e n t s ANAPHORA 32 2 a m e t h o d of d e t e r m i n i n g d e f a u l t a n t e c e d e n t s ; a n d 4 i n f e r e n c e m e c h a n i s m s t o a p p l y to 1 - 3 a b o v e a n d t o t h e m e a n i n g of t h e d i s c o u r s e itself. 7. Summary and discussion In t h i s c h a p t e r , l have t r i e d to do t h e s e t h i n g s : 1 define with r e a s o n a b l e p r e c i s i o n w h a t a n a p h o r a a n d r e f e r e n c e are; 2 give e x a m p l e s of v a r i o u s t y p e s of a n a p h o r a ; 3 d e m o n s t r a t e t h a t a r e f e r e n t c a n be a l m o s t a n y t h i n g i n t h e l i s t e n e r ' s c o n s c i o u s n e s s , be it e x p l i c i t o r i m p l i c i t i n t h e d i s c o u r s e , o r n o t i n t h e d i s c o u r s e a t all; a n d 4 show how a n d why a n a p h o r a a n d r e f e r e n c e c a n b e a p r o b l e m for NLU b y c o m p u t e r , a n d how t h e y a r e i n t e r r e l a t e d with o t h e r p r o b l e m s i n NLU; 5 show t h a t a n a p h o r r e s o l u t i o n r e q u i r e s world k n o w l e d g e , word m e a n i n g , inference and default referents.

Klappholz and Lockman (1975) suggest MEMBER OF as a n o t h e r possible relation, b u t I am not convinced t h a t it differs in practice from PART OF. 52From: Hunter, J A H. Figure it out. The Canberra times, 26 October 1977, page 25. 2. 2 D e f i n i t e r e f e r e n c e 28 ANAPHORA w a s CaroL. B e t w e e n t h e e x t r e m e s of a fixed r e l a t i o n like ASPECT OF a n d i n f e r r e d r e l a t i o n like t h a t in (2-106) is t h e v a g u e r e l a t i o n CLOSELY ASSOCIATED WITH: (2-107) The m a n a g e r u s h e r e d embarrassment.

The p r i m a r y l i m i t a t i o n of LSNLIS is t h a t i n t r a s e n t e n t i a l a n a p h o r s c a n n o t be r e s o l v e d , b e c a u s e a n o u n p h r a s e is n o t a v a i l a b l e as a n a n t e c e d e n t u n t i l p r o c e s s i n g of t h e s e n t e n c e c o n t a i n i n g it is c o m p l e t e . 3. 4. MARGIE a n d SAM So far, the natural language systems based on conceptual dependency theory (Sehank 1973), MARGIE (Schank, Goldman, Rieger and Riesbeck 1975; Schank 1975) and SAM (Schank and the Yale AI Project 1975; Schank and Abelson 1977; Nelson 1978), have apparently not been able to handle any form of anaphor much beyond knowing that ]%e always refers to John (a pathetic victim of social brutalization) and she to Mary (a pathetic victim of John, who frequently beats and m u r d e r s her).

Download PDF sample

Rated 4.37 of 5 – based on 7 votes