Recognizing Textual Entailment Using Sentence Similarity based on Dependency Tree Skeletons
By Rui Wang, Günter Neumann. 2007
64 citations recorded by the source corpus.
We present a novel approach to RTE that exploits a structure-oriented sentence representation followed by a similarity function. The structural features are automatically acquired from tree skeletons that are extracted and generalized from dependency trees. Our method makes use of a limited size of training data without any external knowledge bases (e.g. WordNet) or handcrafted inference rules. We have achieved an accuracy of 71.1% on the RTE-3 development set performing a 10-fold cross validation and 66.9% on the RTE-3 test data.
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
- Mohit Bansal
- Samuel R. Bowman
- Yonatan Belinkov
- Yoav Goldberg
- Noah A. Smith
- Yejin Choi
- Richard Socher
- Christopher D. Manning
In Natural Language Processing
- Mohit Bansal
- Samuel R. Bowman
- Richard Socher
- Yejin Choi
- Christopher D. Manning
- Douwe Kiela
- Noah A. Smith
- Caiming Xiong
Citations in the corpus
- A large annotated corpus for learning natural language inference (2015, methodology): “…addition to the base classifier-based system distributed with the platform, we train a variant which includes information from WordNet (Miller, 1995) and Verb-Ocean (Chklovski and Pantel, 2004), and makes use of features based on tree patterns and dependency tree skeletons (Wang and Neumann, 2007).”
- Reading and Thinking: Re-read LSTM Unit for Textual Entailment Recognition (2016, background): “…between sentences ( T and H ) and sentence pairs ( ( T 0 , H 0 ) and ( T 00 , H 00 ) )(Malakasiotis and Androutsopoulos, 2007; Jijkoun and de Rijke, 2005; Wan et al., 2006; Zanzotto and Moschitti, 2006; Wang and Neumann, 2007; Dinu and Wang, 2009; Nielsen et al., 2009; Malakasiotis, 2011).”
- Have You Lost the Thread? Discovering Ongoing Conversations in Scattered Dialog Blocks (2017, background): “…(1) learning models based on lexical features (Corley and Mihalcea 2005), on syntactic features (Kouylekov and Magnini 2005; Snow et al. 2006; Wang and Neumann 2007), on multiple linguistic levels (de Salvo Braz et al. 2005), and on more complex rules with variables (Zanzotto and Moschitti…”