\'Evaluation intrins\`eque et extrins\`eque du nettoyage de pages Web
Le nettoyage de documents issus du web est une t{\^a}che importante pour le TAL en g{\'e}n{\'e}ral et pour la constitution de corpus en particulier. Cette phase est peu trait{\'e}e dans la litt{\'e}rature, pourtant elle n{'}est pas sans influence sur la qualit{\'e} des informations extraites des corpus. Nous proposons deux types d{'}{\'e}valuation de cette t{\^a}che de d{\'e}tourage : (I) une {\'e}valuation intrins{\e}que fond{\'e}e sur le contenu en mots, balises et caract{\e}res ; (II) une {\'e}valuation extrins{\e}que fond{\'e}e sur la t{\^a}che, en examinant l{'}effet du d{\'e}tourage des documents sur le syst{\e}me plac{\'e} en aval de la cha{\^\i}ne de traitement. Nous montrons que les r{\'e}sultats ne sont pas coh{\'e}rents entre ces deux {\'e}valuations ainsi qu{'}entre les diff{\'e}rentes langues. Ainsi, le choix d{'}un outil de d{\'e}tourage devrait {\^e}tre guid{\'e} par la t{\^a}che vis{\'e}e plut{\^o}t que par la simple {\'e}valuation intrins{\`e}que.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
How Far Can Machine Translation Quality Take You? Extrinsic Discourse Evaluation in Goal-Oriented Setups
Existing machine translation (MT) metrics and discourse-focused evaluations primarily assess translation quality intrinsically, without measuring the downstream consequences of translation errors. In this work, we focus …
Machine TranslationExtrinsic camera calibration method and its performance evaluation
This paper presents a method for extrinsic camera calibration (estimation of camera rotation and translation matrices) from a sequence of images. It is assumed camera intrinsic matrix and distortion coefficients are know…
Camera CalibrationTranslationUnified Data Collection for Visual-Inertial Calibration via Deep Reinforcement Learning
Visual-inertial sensors have a wide range of applications in robotics. However, good performance often requires different sophisticated motion routines to accurately calibrate camera intrinsics and inter-sensor extrinsic…
Deep Reinforcement Learningreinforcement-learningReinforcement Learning (RL)On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language Representations
Multiple metrics have been introduced to measure fairness in various natural language processing tasks. These metrics can be roughly categorized into two categories: 1) \emph{extrinsic metrics} for evaluating fairness in…
FairnessMC-NeRF: Multi-Camera Neural Radiance Fields for Multi-Camera Image Acquisition Systems
Neural Radiance Fields (NeRF) use multi-view images for 3D scene representation, demonstrating remarkable performance. As one of the primary sources of multi-view images, multi-camera systems encounter challenges such as…
NeRF