TY  - CONF
AU  - Mollá, Diego
AU  - Hutchinson, Ben
A2  - 
T1  - Intrinsic versus Extrinsic Evaluations of Parsing Systems
T2  - Proc. European Association for Computational Linguistics (EACL), workshop on Evaluation Initiatives in Natural Language Processing
PB  - ACL
CY  - Budapest
PY  - 2003/04
M2  - 
IS  - 
SP  - 43
EP  - 50
UR  - 
M3  - 
KW  - parsers evaluation AnswerFinder gram_rels molla_publication
L1  - 
SN  - 
N1  - 
N1  - 
AB  - A wide range of parser and/or grammar evaluation methods have been reported in the literature. However, in most cases these evaluations take the parsers independently (intrinsic evaluations), and only in a few cases has the effect of different parsers in real applications been measured (extrinsic evaluations). This paper compares two evaluations of the Link Grammar parser and the Conexor Functional Dependency Grammar parser. The parsing systems, despite both being dependency-based, return different types of dependencies, making a direct comparison impossible. In the intrinsic evaluation, the accuracy of the parsers is compared independently by converting the dependencies into grammatical relations and using the methodology of Carroll:1998 for parser comparison. In the extrinsic evaluation, the parsers' impact in a practical application is compared within the context of answer extraction. The differences in the results are significant.
ER  -

TY  - UNPB
AU  - Mollá, Diego
AU  - Hutchinson, Ben
A2  - 
T1  - In Vitro and In Vivo Evaluations of Parsing Systems Within the Context of Answer Extraction
PY  - 2002/
SP  - 
EP  - 
UR  - 
M3  - 
KW  - AnswerFinder parsers evaluation gram_rels molla_publication
L1  - 
N1  - 
N1  - 
AB  - A wide variety of parser and/or grammar evaluation methods have been reported in the literature. However, in most cases these evaluations take the parsers independently (in vitro evaluations), and only in a few cases has the effect of different parsers in real applications been measured (in vivo evaluations). This paper compares two evaluations of the Link Grammar parser and the Conexor Functional Dependency Grammar parser. The parsing systems, despite both being dependency-based, return different types of dependencies, making a direct comparison impossible. In the first evaluation, the accuracy of the parsers is compared in vitro by converting the dependencies into grammatical relations and using the methodology of Carroll:1998 for parser comparison. In the second evaluation, the parsers' impact in a practical application is compared in vivo within the context of answer extraction. The differences in the results are significant and raise questions on the usefulness of purely in vitro evaluations.
ER  -

TY  - GEN
AU  - Briscoe, Ted
AU  - Carroll, John
A2  - 
T1  - Grammatical Relation annotation
JO  - 
PB  - 
AD  - 
PY  - 2000/
VL  - 
IS  - 
SP  - 
EP  - 
UR  - http://www.cogs.susx.ac.uk/lab/nlp/carroll/grdescription/index.html
M3  - 
KW  - parsers gram_rels
L1  - 
N1  - 
N1  - 
AB  - 
ER  -

TY  - CONF
AU  - Buchholz, Walter Daelemans Sabine
A2  - 
T1  - Cascaded Grammatical Relation Assignment
T2  - Proceedings of EMNLP/VLC-99
PB  - 
CY  - 
PY  - 1999/
M2  - 
IS  - 
SP  - 239
EP  - 246
UR  - http://ilk.kub.nl/~sabine/
M3  - 
KW  - gram_rels
L1  - 
SN  - 
N1  - 
N1  - 
AB  - In this paper we discuss cascaded Memory-Based grammatical relations assignment. In the first stages of the cascade, we find chunks of several types (NP,VP,ADJP,ADVP,PP) and label them with their adverbial function (e.g. local, temporal). In the last stage, we assign grammatical relations to pairs of chunks. We studied the effect of adding several levels to this cascaded classifier and we found that even the less performing chunkers enhanced the performance of the relation finder.
ER  -

TY  - CONF
AU  - Carroll, John
AU  - Briscoe, Ted
AU  - Sanfilippo, Antonio
A2  - 
T1  - Parser Evaluation: a Survey and a New Proposal
T2  - Proc. LREC98
PB  - 
CY  - 
PY  - 1998/
M2  - 
IS  - 
SP  - 
EP  - 
UR  - http://citeseer.nj.nec.com/carroll98parser.html
M3  - 
KW  - parsers evaluation gram_rels
L1  - 
SN  - 
N1  - 
N1  - 
AB  - We present a critical overview of the state-of-the-art in parser evaluation methodologies and metrics. A discussion of their relative strengths and weaknesses motivates a new --- and we claim more informative and generally applicable --- technique of measuring parser accuracy, based on the use of grammatical relations. We conclude with some preliminary results of experiments in which we use this new scheme to evaluate a robust parser of English.
ER  -