An Accuracy-Oriented Divide-and-Conquer Strategy for Recognizing Textual Entailment

نویسندگان

  • Rui Wang
  • Günter Neumann
چکیده

The Two-Way Task: Run1: TAC-M, TS-M, and Tri-BM Run2: TAC-M, TS-M, and BoW-BM Run3: TAC-M, TS-M, NE-M, & Tri-BM, BoW-BM The Three-Way Task: Run1: TAC-M, TS-M, and Tri-BM, BoWBM Run2: TAC-M, TS-M, NE-M (partial), and Tri-BM, BoW-BM Run3: TAC-M, TS-M, NE-M, and Tri-BM, BoW-BM From Two-Way to Three-Way: If BoW-BM=YES & Tri-BM=NO then CONTRADICTION If BoW-BM=YES & Tri-BM=YES then ENTAILMENT Others UNKNOWN Tasks TAC-M TS-M NE-M BoW-BM Tri-BM Run1 Run2 Run3 IR(300) 75.0%/4 76.5%/85 61.0%/164 63.3% 54.3% 66.0% 72.3% 71.7% QA(200) 90.0%/10 73.2%/82 54.8%/93 49.0% 53.5% 73.0% 72.0% 74.0% SUM(200) 83.3%/6 74.5%/51 55.2%/67 63.5% 54.0% 64.0% 69.5% 71.5%

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Expanded Dependency Structure based Textual Entailment Recognition System of NTTDATA for NTCIR10-RITE2

This paper describes NTT DATA’s recognizing textual entailment(RTE) systems for NTCIR10 RITE2. We participate in four Japanese tasks, BC Subtask, Unit Test, Exam BC and Exam Search[5]. Our approach uses a ratio with the same semantic relations between words. It is necessary to recognize two semantic viewpoints, which are the semantic relation and the meaning between words in a sentence, in orde...

متن کامل

A Logic-Based Semantic Approach to Recognizing Textual Entailment

This paper proposes a knowledge representation model and a logic proving setting with axioms on demand successfully used for recognizing textual entailments. It also details a lexical inference system which boosts the performance of the deep semantic oriented approach on the RTE data. The linear combination of two slightly different logical systems with the third lexical inference system achiev...

متن کامل

A Joint Syntactic-Semantic Representation for Recognizing Textual Relatedness

This paper describes our participation in the Recognizing Textual Entailment challenge (RTE-5) in the Text Analysis Conference (TAC 2009). Following the two-stage binary classification strategy, our focus this year is to recognize related Text-Hypothesis pairs instead of entailment pairs. In particular, we propose a joint syntactic-semantic representation to better capture the key information s...

متن کامل

Recognizing Textual Entailment Using a Machine Learning Approach

We present our experiments on Recognizing Textual Entailment based on modeling the entailment relation as a classification problem. As features used to classify the entailment pairs we use a symmetric similarity measure and a non-symmetric similarity measure. Our system achieved an accuracy of 66% on the RTE-3 development dataset (with 10-fold cross validation) and accuracy of 63% on the RTE-3 ...

متن کامل

The Meaning Factory: Formal Semantics for Recognizing Textual Entailment and Determining Semantic Similarity

Shared Task 1 of SemEval-2014 comprised two subtasks on the same dataset of sentence pairs: recognizing textual entailment and determining textual similarity. We used an existing system based on formal semantics and logical inference to participate in the first subtask, reaching an accuracy of 82%, ranking in the top 5 of more than twenty participating systems. For determining semantic similari...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2008