MonaLog: a Lightweight System for Natural Language Inference Based on Monotonicity
By Hai Hu, Qi Chen, Kyle Richardson, Atreyee Mukherjee, Larry Moss, Sandra Kübler. 2019
46 citations recorded by the source corpus.
We present a new logic-based inference engine for natural language inference (NLI) called MonaLog, which is based on natural logic and the monotonicity calculus. In contrast to existing logic-based approaches, our system is intentionally designed to be as lightweight as possible, and operates using a small set of well-known (surface-level) monotonicity facts about quantifiers, lexical items and tokenlevel polarity information. Despite its simplicity, we find our approach to be competitive with other logic-based NLI models on the SICK benchmark. We also use MonaLog in combination with the current state-of-the-art model BERT in a variety of settings, including for compositional data augmentation. We show that MonaLog is capable of generating large amounts of high-quality training data for BERT, improving its accuracy on SICK.
Subfields: 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 Natural Language Processing
- Kyle Richardson
- Ashish Sabharwal
- Hai Hu
- Larry Moss
- Sandra Kübler
- Greg Durrett
- Swarat Chaudhuri
- Kaj Bostrom
Citations in the corpus
- Flexible Generation of Natural Language Deductions (2021, background): “While annotated resources already exist for certain domains (Khot et al., 2020; Hwang et al., 2021), this is not the case for most types of reasoning.”
- Probing Natural Language Inference Models through Semantic Fragments (2019, methodology): “To construct these datasets, we build on recent work on automatic polarity projection (Hu and Moss 2018; Hu, Chen, and Moss 2019; Hu et al. 2019).”
- OCNLI: Original Chinese Natural Language Inference (2020, methodology): “Systems: As inference is closely related to logic, there has always been a line of research building logic-based or logic-and-machine-learning hybrid models for NLI/RTE problems (e.g. MacCartney, 2009; Abzianidze, 2015; Mart´ınez-G´omez et al., 2017; Yanaka et al., 2018; Hu et al., 2020).”
- Natural Language Deduction through Search over Statement Compositions (2022, background): “Hu et al. (2020) and Chen et al. (2021) propose systems which perform single-sentence natural language inference through proof search in the natural logic space.”