Syntactic Difference Based Approach for NTCIR-9 RITE Task.
Yuta Tsuboi, Hiroshi Kanayama, Masaki Ohno, Yuya Unno · 2011
This paper describes the IBM team's approach for the textual entailment recognition task (RITE) in NTCIR-9 [10] with experimental results for four Japanese subtasks: BC, MC, EXAM, and RITE4QA. To tackle the data set with complicated syntactic and semantic phenomena, the authors used a classi cation method to predict entailment relations between two di erent texts. These features were used for classi cation: (1) Tree edit distance and operations, (2) Word overlap ratios and word pairs, (3) Sentiment polarity matching, (4) Character overlap ratios, (5) Head comparisons, (6) Predicate-argument structure matching, and (7) Temporal expression matching. Feature (1) re ects the operations in the edit distance computation between the text and the hypothesis, which can capture the syntactic di erences between two sentences. In the RITE task, Feature (1) is e ective for the MCsubtask and Feature (7) is e ective for the EXAM subtask.