Learning alignments and leveraging natural logic

Chambers, Nathanael; Cer, Daniel; Grenager, Trond; Hall, David; Kiddon, Chloé; MacCartney, Bill; Marneffe, Marie-Catherine de; Ramage, Daniel; Yeh, Eric; Manning, Christopher D.

doi:10.3115/1654536.1654570

Cited by 64 publications

(46 citation statements)

References 5 publications

(1 reference statement)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, its precision is comparatively high, which suggests a strategy of hybridizing with a broad-coverage RTE system. We were able to show that adding NatLog as a component in the Stanford RTE system (Chambers et al 2007) led to accuracy gains of 4%.…”

Section: Implementation and Evaluationmentioning

confidence: 88%

An extended model of natural logic

MacCartney

Manning

2009

Proceedings of the Eighth International Conference on Computational Semantics - IWCS-8 '09

Self Cite

148

126

View full text Add to dashboard Cite

We propose a model of natural language inference which identifies valid inferences by their lexical and syntactic features, without full semantic interpretation. We extend past work in natural logic, which has focused on semantic containment and monotonicity, by incorporating both semantic exclusion and implicativity. Our model decomposes an inference problem into a sequence of atomic edits linking premise to hypothesis; predicts a lexical semantic relation for each edit; propagates these relations upward through a semantic composition tree according to properties of intermediate nodes; and joins the resulting semantic relations across the edit sequence. A computational implementation of the model achieves 70% accuracy and 89% precision on the FraCaS test suite. Moreover, including this model as a component in an existing system yields significant performance gains on the Recognizing Textual Entailment challenge.

show abstract

Section: Implementation and Evaluationmentioning

confidence: 88%

An extended model of natural logic

MacCartney

Manning

2009

Proceedings of the Eighth International Conference on Computational Semantics - IWCS-8 '09

Self Cite

148

126

View full text Add to dashboard Cite

show abstract

“…Training and is performed using a logistic regression classifier. Chambers et al [4] improve the alignment stage in [17] and combine it with a logical framework for the second stage [16]. The inference in the logical framework is expressed by a sequence of edits over texts expressions, where the edits represent operations that affect monotonicity over texts expressions.…”

Section: Resultsmentioning

confidence: 99%

Statistical Relational Learning to Recognise Textual Entailment

Rios

Specia

Gelbukh

et al. 2014

Computational Linguistics and Intelligent Text Processing

View full text Add to dashboard Cite

Abstract. We propose a novel approach to recognise textual entailment (RTE) following a two-stage architecture -alignment and decision -where both stages are based on semantic representations. In the alignment stage the entailment candidate pairs are represented and aligned using predicate-argument structures. In the decision stage, a Markov Logic Network (MLN) is learnt using rich relational information from the alignment stage to predict an entailment decision. We evaluate this approach using the RTE Challenge datasets. It achieves the best results for the RTE-3 dataset and shows comparable performance against the state of the art approaches for other datasets.

show abstract

“…The string representation of this tree, including the parts of speech for its words is as follows: To match patterns against dependency trees, we use Stanford's semgrex utility [25]. In the following, we explain some of the basics of semgrex patterns that help the reader understand patterns presented in this paper using descriptions and examples from the authors of [25]. Figure 1 can be:…”

Section: Background On Dependency Treesmentioning

confidence: 99%

Automatic Classification of Online Doctor Reviews: Evaluation of Text Classifier Algorithms (Preprint)

Rivas¹,

Montazeri²,

Le³

et al. 2018

Preprint

View full text Add to dashboard Cite

Background: An increasing number of doctor reviews are being generated by patients on the internet. These reviews address a diverse set of topics (features), including wait time, office staff, doctor's skills and bedside manner. Most previous work on automatic analysis of online customer reviews assumes that (a) product features are described unambiguously by a small number of keywords, e.g., "battery" for phones, and (b) the opinion for each feature has positive or negative sentiment. However, in the domain of doctor reviews, this setting is too restrictive: a feature such as "visit duration" for doctor reviews may be expressed in many ways, and does not necessarily have positive/negative sentiment.

show abstract

Learning alignments and leveraging natural logic

Cited by 64 publications

References 5 publications

An extended model of natural logic

An extended model of natural logic

Statistical Relational Learning to Recognise Textual Entailment

Automatic Classification of Online Doctor Reviews: Evaluation of Text Classifier Algorithms (Preprint)

Contact Info

Product

Resources

About