Making the Implicit Explicit: Implicit Content as a First Class Citizen in NLP

by   Alexander Hoyle, et al.

Language is multifaceted. A given utterance can be re-expressed in equivalent forms, and its implicit and explicit content support various logical and pragmatic inferences. When processing an utterance, we consider these different aspects, as mediated by our interpretive goals – understanding that "it's dark in here" may be a veiled direction to turn on a light. Nonetheless, NLP methods typically operate over the surface form alone, eliding this nuance. In this work, we represent language with language, and direct an LLM to decompose utterances into logical and plausible inferences. The reduced complexity of the decompositions makes them easier to embed, opening up novel applications. Variations on our technique lead to state-of-the-art improvements on sentence embedding benchmarks, a substantive application in computational political science, and to a novel construct-discovery process, which we validate with human annotations.


page 1

page 2

page 3

page 4


Look-up and Adapt: A One-shot Semantic Parser

Computing devices have recently become capable of interacting with their...

Guessing What's Plausible But Remembering What's True: Accurate Neural Reasoning for Question-Answering

Neural approaches to natural language processing (NLP) often fail at the...

Inferring Logical Forms From Denotations

A core problem in learning semantic parsers from denotations is picking ...

A Type-coherent, Expressive Representation as an Initial Step to Language Understanding

A growing interest in tasks involving language understanding by the NLP ...

Challenges and Considerations with Code-Mixed NLP for Multilingual Societies

Multilingualism refers to the high degree of proficiency in two or more ...

Explicifying Neural Implicit Fields for Efficient Dynamic Human Avatar Modeling via a Neural Explicit Surface

This paper proposes a technique for efficiently modeling dynamic humans ...

Is a Question Decomposition Unit All We Need?

Large Language Models (LMs) have achieved state-of-the-art performance o...

Please sign up or login with your details

Forgot password? Click here to reset