NaturalLI: Natural Logic Inference for Common Sense Reasoning

By Gabor Angeli, Christopher D. Manning. 2014

131 citations recorded by the source corpus.

Common-sense reasoning is important for AI applications, both in NLP and many vision and robotics tasks. We propose NaturalLI: a Natural Logic inference system for inferring common sense facts ‐ for instance, that cats have tails or tomatoes are round ‐ from a very large database of known facts. In addition to being able to provide strictly valid derivations, the system is also able to produce derivations which are only likely valid, accompanied by an associated confidence. We both show that our system is able to capture strict Natural Logic inferences on the FraCaS test suite, and demonstrate its ability to predict common sense facts with 49% recall and 91% precision.

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

In Natural Language Processing

Citations in the corpus

FEVER: a Large-scale Dataset for Fact Extraction and VERification (2018, methodology): “For instance, it would be interesting to test how approaches similar to natural logic inference (Angeli and Manning, 2014) can be applied, where a knowledge base/graph is constructed by reading the textual sources and then a reasoning process over the claim is applied, possibly using recent…”
ProoFVer: Natural Logic Theorem Proving for Fact Verification (2021, methodology): “NaturalLi is a proof system formulated for the NLI task.”
Reasoning about Entailment with Neural Attention (2015, methodology): “To ensure a comparable number of parameters to Bowman et al.’s model that encodes the premise and hypothesis independently using one LSTM, we also run experiments for conditional encoding where the parameters of both LSTMs are shared (“Conditional encoding, shared” with k = 100 ) as opposed to using”
Question Answering via Integer Programming over Semi-Structured Knowledge (2016, background): “Recent work on Natural Logic [ Angeli and Manning, 2014; MacCartney, 2009 ] has extended RTE to account for the logical structure within language.”
Commonsense Knowledge Base Completion (2016, background): “Several researchers have developed techniques for discovering commonsense knowledge from text (Gordon et al., 2010; Gordon and Schu-bert, 2012; Gordon, 2014; Angeli and Manning, 2014).”
EQUATE: A Benchmark Evaluation Framework for Quantitative Reasoning in Natural Language Inference (2019, background): “…Haghighi et al., 2005; Harabagiu and Hickl, 2006; Romano et al., 2006; Dagan et al., 2006; Giampiccolo et al., 2007; Zanzotto et al., 2006; Malakasiotis and Androutsopoulos, 2007; MacCartney, 2009; de Marneffe et al., 2009; Da-gan et al., 2010; Angeli and Manning, 2014; Ma-relli et al., 2014).”
Automated Fact Checking: Task Formulations, Methods and Future Directions (2018, neutral): “Angeli and Manning (2014) proposed a method of extracting common sense knowledge from WordNet for reasoning about common sense knowledge us-ing Natural Logic and evaluated their approach on a subset of textual entailment problems in the FraCaS test suite (Cooper et al., 1996).”
Combining Natural Logic and Shallow Reasoning for Question Answering (2016, methodology): “We build our extensions within the framework of NaturalLI, introduced by Angeli and Manning (2014). NaturalLI casts inference as a search problem: given a hypothesis and an arbitrarily large corpus of text, it searches through the space of lexical mutations (e.”
TwoWingOS: A Two-Wing Optimization Strategy for Evidential Claim Verification (2018, background): “, (Angeli and Manning, 2014) – given a database of true facts as premises, predicting whether an unseen fact is true and should belong to the database by natural logic inference.”
Advances in natural language processing (2015, background): “Even with all of our textextraction techniques, any knowledge base will only be partial and incomplete; some recent work explores how it can be probabilistically completed to deliver a form of common-sense reasoning (48).”
Natural Language Inference with Monotonicity (2019, methodology): “This paper is a contribution to the third category, as are Abzianidze (2015, 2017); MacCartney and Manning (2009); Angeli and Manning (2014); Angeli et al. (2016); Hu et al. (2018); Mineshima et al. (2015).”
A Monotonicity Calculus and Its Completeness (2017, background): “…Icard, 2012; Moss, 2012; Icard and Moss, 2013; Tune, 2016), and much of this work has made its way into psycholinguists (Geurts, 2003; Geurts and van der Slik, 2005) and natural language processing (MacCartney and Manning, 2007; Angeli and Manning, 2014; Bowman et al., 2015; Abzianidze, 2015).”
Most “babies” are “little” and most “problems” are “huge”: Compositional Entailment in Adjective-Nouns (2016, background): “Natural logic enables both light-weight representation and robust inference, and is an increas- ingly popular choice for NLU tasks (Angeli and Manning, 2014; Bowman et al., 2015b; Pavlick et al., 2015).”
Exploring End-to-End Differentiable Natural Logic Modeling (2020, background): “, 2006), which is a state-of-the-art natural logic formalism that has been used for multiple NLP tasks (MacCartney, 2009; Angeli and Manning, 2014).”