Natural Logic and Natural Language Inference

MacCartney, Bill; Manning, Christopher D.

doi:10.1007/978-94-007-7284-7_8

Cited by 100 publications

(127 citation statements)

References 11 publications

Supporting

Mentioning

126

Contrasting

Order By: Relevance

“…3 Background 3.1 Natural Language Inference NLI, or RTE, is the task of inferring whether a natural language sentence (hypothesis) is entailed by another natural language sentence (premise) (Maccartney, 2009;Dagan et al, 2009;Dagan and Glickman, 2004).…”

Section: Behavior Analysismentioning

confidence: 99%

“…Solving this task is challenging since it requires linguistic and semantic knowledge, such as co-reference, hypernymy, and antonymy (LoBue and Yates, 2011), as well as pragmatic knowledge and informal reasoning (Maccartney, 2009). …”

Section: Behavior Analysismentioning

confidence: 99%

“…Such results are impressive due to the linguistic knowledge required to solve the task (LoBue and Yates, 2011;Maccartney, 2009). However, the ever-growing complexity of these models inhibits a full understanding of the phenomena that they capture.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Behavior Analysis of NLI Models: Uncovering the Influence of Three Factors on Robustness

Sánchez¹,

Mitchell²,

Riedel³

2018

Proceedings of the 2018 Conference of the North American Chapter Of the Association for Computational Linguistics: Hu

View full text Add to dashboard Cite

Natural Language Inference is a challenging task that has received substantial attention, and state-of-the-art models now achieve impressive test set performance in the form of accuracy scores. Here, we go beyond this single evaluation metric to examine robustness to semantically-valid alterations to the input data. We identify three factors -insensitivity, polarity and unseen pairs -and compare their impact on three SNLI models under a variety of conditions. Our results demonstrate a number of strengths and weaknesses in the models' ability to generalise to new in-domain instances. In particular, while strong performance is possible on unseen hypernyms, unseen antonyms are more challenging for all the models. More generally, the models suffer from an insensitivity to certain small but semantically significant alterations, and are also often influenced by simple statistical correlations between words and training labels. Overall, we show that evaluations of NLI models can benefit from studying the influence of factors intrinsic to the models or found in the dataset used.

show abstract

Section: Behavior Analysismentioning

confidence: 99%

Section: Behavior Analysismentioning

confidence: 99%

See 1 more Smart Citation

Behavior Analysis of NLI Models: Uncovering the Influence of Three Factors on Robustness

Sánchez¹,

Mitchell²,

Riedel³

2018

Proceedings of the 2018 Conference of the North American Chapter Of the Association for Computational Linguistics: Hu

View full text Add to dashboard Cite

show abstract

“…Reasoning in Natural Logic has been studied by several researchers, including MacCartney's work in implementing an NLI system based on monotonicity reasoning [18]. Embedding monotonicity reasoning in MTTs allows simpler ways of reasoning in many cases and its automation in proof assistants is expected.…”

Section: Discussionmentioning

confidence: 99%

Monotonicity Reasoning in Formal Semantics Based on Modern Type Theories

Lungu

Zhang

2014

Logical Aspects of Computational Linguistics

View full text Add to dashboard Cite

Abstract. Modern type theories (MTTs) have been developed as a powerful foundation for formal semantics. In particular, it provides a useful platform for natural language inference (NLI) where proof assistants can be used for inference on computers. In this paper, we consider how monotonicity reasoning can be dealt in MTTs, so that it can contribute to NLI based on the MTT-semantics. We show that subtyping is crucial in monotonicity reasoning in MTTs because CNs are interpreted as types and therefore the monotonicity relations between CNs should be represented by the subtyping relations. In the past, monotonicity reasoning has only been considered for the arrow-types in the Montagovian setting of simple type theory. In MTT-semantics, richer type constructors involving dependent types and inductive types are employed in semantic representations. We show how to consider monotonicity reasoning that involve such type constructors and how this offers new useful mechanisms in monotonicity reasoning in MTTs.

show abstract

“…By combining DNNs for scene recognition with statistical NLP methods, they relate objects in a scene to sentences that describe the scene -for example, the sen -tence A small crowd quietly enters the historic church and the corresponding parts of the scene [25]. But to derive implications of the sentences or the scenes, they use a variation of logic-based methods that have been used in AI for over 40 years [9]. Some of those methods are as old as Aristotle and Euclid.…”

Section: Deep Learningmentioning

confidence: 99%

The Cognitive Cycle

Sowa¹

2015

Annals of Computer Science and Information Systems

View full text Add to dashboard Cite

Abstract-In the twenty years from first grade to a PhD, students never learn any subject by the methods for which machine-learning algorithms have been designed. Those algorithms are useful for analyzing large volumes of data. But they don't enable a computer system to learn a language as quickly and accurately as a three-year-old child. They're not even as effective as a mother raccoon teaching her babies how to find the best garbage cans. For all animals, learning is integrated with the cognitive cycle from perception to purposeful action. Many algorithms are needed to support that cycle. But an intelligent system must be more than a collection of algorithms. It must integrate them in a cognitive cycle of perception, learning, reasoning, and action. That cycle is key to designing intelligent systems.

show abstract

Natural Logic and Natural Language Inference

Cited by 100 publications

References 11 publications

Behavior Analysis of NLI Models: Uncovering the Influence of Three Factors on Robustness

Behavior Analysis of NLI Models: Uncovering the Influence of Three Factors on Robustness

Monotonicity Reasoning in Formal Semantics Based on Modern Type Theories

The Cognitive Cycle

Contact Info

Product

Resources

About