The Role of Sentence Structure in Recognizing Textual Entailment
By Catherine Blake. 2007
18 citations recorded by the source corpus.
Recent research suggests that sentence structure can improve the accuracy of recognizing textual entailments and paraphrasing. Although background knowledge such as gazetteers, WordNet and custom built knowledge bases are also likely to improve performance, our goal in this paper is to characterize the syntactic features alone that aid in accurate entailment prediction. We describe candidate features, the role of machine learning, and two final decision rules. These rules resulted in an accuracy of 60.50 and 65.87% and average precision of 58.97 and 60.96% in RTE3Test and suggest that sentence structure alone can improve entailment accuracy by 9.25 to 14.62% over the baseline majority class.
Subfields: Artificial Intelligence, Natural Language Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Rachel Rudinger
- Benjamin Van Durme
- Adam Poliak
- Yejin Choi
- Aparajita Haldar
- Yonatan Belinkov
- Ellie Pavlick
- Samuel R. Bowman
In Natural Language Processing
- Rachel Rudinger
- Benjamin Van Durme
- Adam Poliak
- Aparajita Haldar
- Yejin Choi
- Ellie Pavlick
- Yonatan Belinkov
- Samuel R. Bowman
Citations in the corpus
- Hypothesis Only Baselines in Natural Language Inference (2018, background): “Vanderwende and Dolan (2006) and Blake (2007) demonstrate how sentence structure alone can provide a high signal for NLI.”