Learning Parse-Free Event-Based Features for Textual Entailment Recognition
نویسندگان
چکیده
We propose new parse-free event-based features to be used in conjunction with lexical, syntactic, and semantic features of texts and hypotheses for Machine Learning-based Recognizing Textual Entailment. Our new similarity features are extracted without using shallow semantic parsers, but still lexical and compositional semantics are not left out. Our experimental results demonstrate that these features can improve the effectiveness of the identification of entailment and no-entailment relationships.
منابع مشابه
UB.dmirg: Learning Textual Entailment Relationships Using Lexical Semantic Features
This paper describes our Recognizing Textual Entailment (RTE) system developed at University of Ballarat, Australia for participation in the Text Analysis Conference RTE 2010 competition. This year, we participated in the Main task and used a machine learning approach for learning textual entailment relationships using parse-free lexical semantic features. For this, we employed FrameNet and Wor...
متن کاملNTTCS Textual Entailment Recognition System for NTCIR-9 RITE
This paper describes initial Japanese Textual Entailment Recognition (RTE) systems that participated Japanese Binaryclass (BC) and Multi-class (MC) subtasks of NTCIR-9 RITE. Our approaches are based on supervised learning techniques: Decision Tree (DT) and Support Vector Machine (SVM) learners. The employed features for the learners include text fragment based features such as lexical, syntacti...
متن کاملSemantic Inference at the Lexical-Syntactic Level for Textual Entailment Recognition
We present a new framework for textual entailment, which provides a modular integration between knowledge-based exact inference and cost-based approximate matching. Diverse types of knowledge are uniformly represented as entailment rules, which were acquired both manually and automatically. Our proof system operates directly on parse trees, and infers new trees by applying entailment rules, aim...
متن کاملAn Approach for Textual Entailment Recognition Based on Stacking and Voting
This paper presents a machine-learning approach for the recognition of textual entailment. For our approach we model lexical and semantic features. We study the effect of stacking and voting joint classifier combination techniques which boost the final performance of the system. In an exhaustive experimental evaluation, the performance of the developed approach is measured. The obtained results...
متن کاملCYUT Chinese Textual Entailment Recognition System for NTCIR-10 RITE-2
ABSTRACT Textual Entailment (TE) is a critical issue in natural language processing (NLP). In this paper we report our approach to the Chinese textual entailment and the system result on NTCIR-10 RITE-2 both simplified and traditional Chinese dataset. Our approach is based on more observation on training data and finding more types of linguistic features. The approach is a complement to the tra...
متن کامل