What Knowledge is Needed to Solve the RTE5 Textual Entailment Challenge?
It highlights a critical bottleneck in NLP for researchers, emphasizing the need for knowledge-intensive approaches in tasks like RTE, though it is incremental as it builds on existing analysis without new solutions.
The paper analyzes examples from the RTE5 competition to identify the world knowledge required for textual entailment, focusing on cases where systems failed due to reliance on shallow matching rather than deeper reasoning.
This document gives a knowledge-oriented analysis of about 20 interesting Recognizing Textual Entailment (RTE) examples, drawn from the 2005 RTE5 competition test set. The analysis ignores shallow statistical matching techniques between T and H, and rather asks: What would it take to reasonably infer that T implies H? What world knowledge would be needed for this task? Although such knowledge-intensive techniques have not had much success in RTE evaluations, ultimately an intelligent system should be expected to know and deploy this kind of world knowledge required to perform this kind of reasoning. The selected examples are typically ones which our RTE system (called BLUE) got wrong and ones which require world knowledge to answer. In particular, the analysis covers cases where there was near-perfect lexical overlap between T and H, yet the entailment was NO, i.e., examples that most likely all current RTE systems will have got wrong. A nice example is #341 (page 26), that requires inferring from "a river floods" that "a river overflows its banks". Seems it should be easy, right? Enjoy!