Dependency-Based Answer Validation for German
نویسندگان
چکیده
This article describes the Heidelberg contribution to the CLEF 2011 QA4MRE task for German. We focus on the objective of not using any external resources, building a system that represents questions, answers and texts as formulae in propositional logic derived from dependency structure. Background knowledge is extracted from the background corpora using several knowledge extraction strategies. We answer questions by attempting to infer answers from the test documents complemented by background knowledge, with a distance measure as fall-back. The main challenge is to specify the translation from dependency structure into a logical representation. For this step, we suggest different rule sets and evaluate various configuration parameters that tune accuracy and coverage. All of runs exceed a random baseline, but show different coverage/accuracy profiles (accuracy up to 44%, coverage up to 65%).
منابع مشابه
Filtering and Fusion of Question-Answering Streams by Robust Textual Inference
The paper presents an answer validation system based on robust textual inference. The system is evaluated on the AVE06 test set for German. Ablation experiments are used to determine the contribution of functional components and knowledge sources to the achieved validation quality. We demonstrate the utility of the approach for filtering answers and for the fusion of several answer sources into...
متن کاملProjecting RMRS from TIGER Dependencies
We present a method for automatic RMRS semantics construction from dependency structures, following the semantic algebra of Copestake et al. (2001). We have applied this method to a subset of the TIGER Dependency Bank for German (Forst et al., 2004) to obtain a semantic treebank for (HPSG) parser evaluation. We describe the semantics construction mechanism and give evaluation figures from manua...
متن کاملUniversity of Hagen at CLEF 2007: Answer Validation Exercise
MAVE (Multinet-based Answer VErification) is an answer validation system based on deep linguistic processing and logical inference originally developed for AVE 2006. Robustness of the entailment check is obtained by embedding the theorem prover in a constraint relaxation loop. The system can also be used for answer selection, which is then guided by the joint evidence of all available text pass...
متن کاملJustification of Answers by Verification of Dependency Relations - The French AVE Task
This paper presents LIMSI results in Answer Validation Exercise (AVE) 2008 for French. We tested two approaches during this campaign: a syntax-based strategy and a machine learning strategy. Results of both approaches are presented and discussed.
متن کاملUniversity of Hagen at CLEF 2008: Answer Validation Exercise
RAVE (Real-time Answer Validation Engine) is a logic-based answer validator/selector designed for application in real-time question answering. RAVE uses the same toolchain for deep linguistic analysis and the same background knowledge as its predecessor (MAVE), which took part in the AVE 2007. However, a full logical answer check as in MAVE was not considered suitable for real-time answer valid...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2011