Proceedings of the 11th International Conference on Parsing Technologies
Notice bibliographique
Résumé
Welcome to the Eleventh International Conference on Parsing Technologies, IWPT’09, in the splendid \ncity of Paris. \nIWPT’09 continues the tradition of biennial conferences on parsing technology organized by SIGPARSE, \nthe Special Interest Group on Parsing of the Association for Computational Linguistics (ACL). The first \nconference, in 1989, took place in Pittsburgh and Hidden Valley, Pennsylvania. Subsequently, IWPT \nconferences were held in Cancun (Mexico) in 1991; Tilburg (Netherlands) and Durbuy (Belgium) in \n1993; Prague and Karlovy Vary (Czech Republic) in 1995; Boston/Cambridge (Massachusetts) in 1997; \nTrento (Italy) in 2000; Beijing (China) in 2001; Nancy (France) in 2003; Vancouver (Canada) in 2005; \nand Prague (Czech Republic) in 2007. \nOver the years the IWPT Workshops have become the major forum for researchers in natural language \nparsing. They have lead to the publication of four books on parsing technologies; a fifth one about to be \npublished. \nWhere the IWPT conferences from 1989 through 2003 were standalone conferences, the last two IWPTs \nwere organised as co-satellite event of large conferences: IWPT 2005 was co-loated with the HLT- \nEMNLP conference in Vancouver, and IWPT 2007 with the main ACL conference in Prague. This \nworked well from a logistic point of view, thanks to the support from ACL, but it was felt to lead to \nsomewhat less interesting events than in the past, sitting in the shadow of the larger conference and \ncompeting with other satellite events. It was therefore decided to return to the standalone format in 2009, \nwith INRIA Rocquencourt and the University of Paris 7 volunteering to take charge of the organisation. \nWe would like to thank Eric de la Clergerie, Laurence Danlos, Benoit Sagot and the support staff at \nINRIA and University of Paris 7 for their efforts to realize IWPT’09. \nIWPT’09 is fortunate to have three very distinguished invited speakers: John Carroll from the university \nof Sussex, Mark Johnson from Brown University, and Joakim Nivre from the University of Uppsala. \nI would like to thank all the programme committee members for their careful and timely work, especially \nthose that took up extra rewiewing obligations at very short notice and those who participated in \ndiscussions on diverging reviews. Special thanks go to Eric de la Clergerie, the programme chair, \nfor organising the reviewing, designing the workshop programme and producing the proceedings. The \nscientific programme includes 14 accepted full papers and 27 accepted short papers (the latter being an \nall-time high for IWPT), covering virtually all currently hot topics in parsing technology. Together with \nthe three invited talks by top experts in parsing, these papers provide a fascinating picture of the state of \nthe art in parsing natural language, that I hope you will enjoy and will find inspiring. \nHarry Bunt \nIWPT’09 General Chair
Récupéré en direct depuis OpenAlex et désinversé. Les résumés ne sont pas conservés dans cette base de données : les index inversés représentent 8,6 Go des 9,3 Go de texte de la base, et le serveur dispose de 13 Go libres.
Comment cette classification a été obtenuedéplier
Prédiction distillée sur la base complète
Imitation des enseignantsNi prévalence calibrée, ni vérité terrain. Validation humaine à venir. Apprise à partir de 10 348 étiquettes directes de Codex et de 10 348 étiquettes directes de Gemma. Le mode candidate est l'union des têtes enseignantes seuillées; le consensus est leur intersection. Ces sorties portent le statut machine_predicted_unvalidated et ne sont ni des étiquettes humaines ni des étiquettes directes de modèles de pointe.
Scores Codex et Gemma par catégorie
| Catégorie | Codex | Gemma |
|---|---|---|
| Métarecherche | 0,000 | 0,000 |
| Méta-épidémiologie (sens strict) | 0,000 | 0,000 |
| Méta-épidémiologie (sens large) | 0,000 | 0,000 |
| Bibliométrie | 0,000 | 0,000 |
| Études des sciences et des technologies | 0,000 | 0,000 |
| Communication savante | 0,000 | 0,000 |
| Science ouverte | 0,000 | 0,000 |
| Intégrité de la recherche | 0,000 | 0,000 |
| Charge utile insuffisante (le modèle a refusé de juger) | 0,000 | 0,000 |
Scores machine (provisoires)
Les deux têtes enseignantes du modèle étudiant, lues sur ce travail. Un score ordonne la base pour la relecture; il n'affirme jamais une catégorie, et le statut de validation accompagne chaque rangée tel quel.
Scores de référence d'un modèle non mature (critères de maturité non atteints, 7 itérations). Un score ordonne; il n'affirme jamais une catégorie.
score_only:v0-immature-baseline · tel quel depuis la passe de notation : score_only signifie que le nombre peut ordonner les travaux, et qu'aucune étiquette de catégorie n'en découleClassification
machine, non validéePrédiction automatique; un appel candidat d’une seule tête enseignante, pas un consensus.
Le détail, modèle par modèle et score par score, se trouve en fin de page sous « Comment cette classification a été obtenue ».