Combining Natural Logic and Shallow Reasoning for Question Answering

By Gabor Angeli, Neha Nayak Kennard, Christopher D. Manning. 2016

34 citations recorded by the source corpus.

Broad domain question answering is often difﬁcult in the absence of structured knowledge bases, and can beneﬁt from shallow lexical methods (broad coverage) and logical reasoning (high precision). We propose an approach for incorporating both of these signals in a uniﬁed framework based on natural logic. We extend the breadth of inferences afforded by nat-ural logic to include relational entailment (e.g., buy → own ) and meronymy (e.g., a person born in a city is born the city’s country). Furthermore, we train an evaluation function – akin to gameplaying – to evaluate the expected truth of candidate premises on the ﬂy. We evaluate our approach on answering multiple choice science questions, achieving strong results on the dataset.

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

ProoFVer: Natural Logic Theorem Proving for Fact Verification (2021, methodology): “…Lakoff (1972), has been previously employed in several information extraction and NLU tasks such as Natural Language Inference (NLI, Angeli and Manning, 2014; Abzianidze, 2017a; Feng et al., 2020), question answering (Angeli et al., 2016) and open information extraction (Angeli, 2016, Chapter 5).”
Flexible Generation of Natural Language Deductions (2021, background): “Natural Logic (Bernardi, 2002; Zamansky et al., 2006; MacCartney and Manning, 2009; Angeli et al., 2016) is related to our approach in that it provides a framework for logical reasoning about statements in natural language.”
NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language (2019, methodology): “Angeli et al. (2016) employ a system based on Natural Logic to search a large KB for a single statement that entails the candidate answer.”
Exploring End-to-End Differentiable Natural Logic Modeling (2020, methodology): “For more details, we refer readers to (MacCartney and Manning, 2008; MacCartney and Manning, 2009; MacCartney, 2009; Angeli et al., 2016).”
Natural Language Inference with Monotonicity (2019, background): “Another difference is that in our system, replacement can happen in any order, and the results are the same, whereas in Angeli’s system only certain “mutating” orders lead to the correct inferences (see Section 3.1 of Angeli et al. (2016)).”
Natural Language Deduction through Search over Statement Compositions (2022, background): “Our work also relates to earlier efforts on natural logic (MacCartney and Manning, 2009; Angeli et al., 2016) but is able to cover far more phenomena by relaxing the strict constraints of this framework.”
A Monotonicity Calculus and Its Completeness (2017, background): “The calculus provides a mathematical foundation for a style of monotonicity reasoning that is often implicit in practical NLP work (e.g., MacCartney and Manning 2007; Angeli and Manning 2014; Angeli et al. 2016).”