The SAU Report for the 1st CIPS-SIGHAN-ParsEval-2010
نویسندگان
چکیده
This paper presents our work for participation in the 2010 CIPS-SIGHAN evaluation on two tasks which are Event Description Sub-sentence (EDSs) Analysis and Complete Sentence (CS) Parsing in Chinese Parsing. The paper describes the implementation of our system as well as the results we have achieved and the analysis.
منابع مشابه
Chinese Syntactic Parsing Evaluation
The paper introduced the task designing ideas, data preparation methods, evaluation metrics and results of the second Chinese syntactic parsing evaluation (CIPS-Bakeoff-ParsEval-2010) jointed with SIGHAN Bakeoff tasks.
متن کاملEvaluation Reportof the fourth Chinese Parsing Evaluation: CIPS-SIGHAN-ParsEval-2014
This paper gives the overview of the fourth Chinese parsing evaluation: CIPS-SIGHANParsEval-2014, including its parsing, evaluation metrics, training and test data. The detailed evaluation results and simple discussions will be given to show the difficulties in Chinese syntactic parsing.
متن کاملEvaluation Reportof the third Chinese Parsing Evaluation: CIPS-SIGHAN-ParsEval-2012
This paper gives the overview of the third Chinese parsing evaluation: CIPS-SIGHANParsEval-2012, including its parsing sub-tasks, evaluation metrics, training and test data. The detailed evaluation results and simple discussions will be given to show the difficulties in Chinese syntactic parsing.
متن کاملSelecting Optimal Feature Template Subset for CRFs
Conditional Random Fields (CRFs) are the state-of-the-art models for sequential labeling problems. A critical step is to select optimal feature template subset before employing CRFs, which is a tedious task. To improve the efficienc y of t his step, we propose a new method that adopts the maximum entropy (ME) model and maximum entropy Markov models (MEMMs) instead of CRFs considering the homolo...
متن کاملCRF-based Experiments for Cross-Domain Chinese Word Segmentation at CIPS-SIGHAN-2010
This paper describes our experiments on the cross-domain Chinese word segmentation task at the first CIPS-SIGHAN Joint Conference on Chinese Language Processing. Our system is based on the Conditional Random Fields (CRFs) model. Considering the particular properties of the out-of-domain data, we propose some novel steps to get some improvements for the special task.
متن کامل