TY - JOUR
T1 - Anaphora in natural language processing and information retrieval
AU - Liddy, Elizabeth Du Ross
N1 - Funding Information:
The moste xtensivest udyo f anaphoraa nd its potentialf or impacto n IR hasb eenc on-ducteda t SyracuseU niversity’sS chool of Information Studiesc ommencingin 1983a nd continuingt o this date.T hesei nvestigationcso vered:t he basicl inguistica ssumptionu nder-lying the use of anaphorai n texts [20];d evelopmenot f a taxonomyo f anaphorict erms; writing of rules for distinguishinga naphoric from nonanaphoric uses of a potential anaphor;d escriptives tatisticos n occurrenceo f anaphorict ermsi n documenta bstracts[2 1]; impacto f resolvinga naphorao n a varietyo f term-weightingsc hemes[2 2];a nd the effect of resolvinga naphorao n the ranked output of an IR system[ 23].T he primary research was conductedd uring a two-yearp roject (1984-86)f undedb y the National ScienceF oun-dation. The major goals of that effort were:
PY - 1990
Y1 - 1990
N2 - Anaphora is the discourse-level linguistic phenomenon of abbreviated subsequent reference, pronouns being the most commonly used anaphors. In that anaphora plays an essential role in human processors' production and understanding of texts, its appropriate recognition and resolution is essential to information retrieval systems that manipulate natural language texts. The approaches to anaphora undertaken in theoretical linguistics and NLP are surveyed and the results of research on anaphora as it impacts on information processes are presented with specific attention to the detailed studies conducted at Syracuse University. These studies have provided essential baseline data on the extent to which anaphora occur, their likelihood of referring to concepts integral to the toplc, their effect on a variety of term-weighting schemes, and their impact on retrieval results. Although the most effective means of processing anaphora may not have yet been determined, it is suggested that improved retrieval systems will need to represent the full meaning of natural language documents, including anaphoric references as well as all other discourse linguistic phenomena.
AB - Anaphora is the discourse-level linguistic phenomenon of abbreviated subsequent reference, pronouns being the most commonly used anaphors. In that anaphora plays an essential role in human processors' production and understanding of texts, its appropriate recognition and resolution is essential to information retrieval systems that manipulate natural language texts. The approaches to anaphora undertaken in theoretical linguistics and NLP are surveyed and the results of research on anaphora as it impacts on information processes are presented with specific attention to the detailed studies conducted at Syracuse University. These studies have provided essential baseline data on the extent to which anaphora occur, their likelihood of referring to concepts integral to the toplc, their effect on a variety of term-weighting schemes, and their impact on retrieval results. Although the most effective means of processing anaphora may not have yet been determined, it is suggested that improved retrieval systems will need to represent the full meaning of natural language documents, including anaphoric references as well as all other discourse linguistic phenomena.
UR - http://www.scopus.com/inward/record.url?scp=0025594371&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0025594371&partnerID=8YFLogxK
U2 - 10.1016/0306-4573(90)90008-P
DO - 10.1016/0306-4573(90)90008-P
M3 - Article
AN - SCOPUS:0025594371
SN - 0306-4573
VL - 26
SP - 39
EP - 52
JO - Information Processing and Management
JF - Information Processing and Management
IS - 1
ER -