no code implementations • ReInAct 2021 • Georgiy Platonov, Benjamin Kane, Lenhart Schubert
As AI reaches wider adoption, designing systems that are explainable and interpretable becomes a critical necessity.
no code implementations • ACL (NALOMA, IWCS) 2021 • Gene Kim, Mandar Juvekar, Junis Ekmekciu, Viet Duong, Lenhart Schubert
We implement the formalization of natural logic-like monotonic inference using Unscoped Episodic Logical Forms (ULFs) by Kim et al. (2020).
no code implementations • ACL (NALOMA, IWCS) 2021 • Gene Kim, Mandar Juvekar, Lenhart Schubert
We present a method of making natural logic inferences from Unscoped Logical Form of Episodic Logic.
no code implementations • ACL (NALOMA, IWCS) 2021 • Lane Lawley, Benjamin Kuehnert, Lenhart Schubert
We present a system for learning generalized, stereotypical patterns of events—or “schemas”—from natural language stories, and applying them to make predictions about other stories.
no code implementations • ACL (splurobonlp) 2021 • Georgiy Platonov, Yifei Yang, HaoYu Wu, Jonathan Waxman, Marcus Hill, Lenhart Schubert
Understanding spatial expressions and using them appropriately is necessary for seamless and natural human-machine interaction.
no code implementations • NAACL (DistCurate) 2022 • Lane Lawley, Lenhart Schubert
We propose a means of augmenting FrameNet parsers with a formal logic parser to obtain rich semantic representations of events.
no code implementations • 10 Oct 2023 • Benjamin Kane, Lenhart Schubert
In many NLP applications that involve interpreting sentences within a rich context -- for instance, information retrieval systems or dialogue systems -- it is desirable to be able to preserve the sentence in a form that can be readily understood without context, for later reuse -- a process known as ``decontextualization''.
1 code implementation • 10 Oct 2023 • Benjamin Kane, Lenhart Schubert
We capture such habitual knowledge using an explicit schema representation, and propose an approach to dialogue generation that retrieves relevant schemas to condition a large language model to generate persona-based responses.
no code implementations • 15 Jul 2022 • Benjamin Kane, Catherine Giugno, Lenhart Schubert, Kurtis Haut, Caleb Wohn, Ehsan Hoque
A schema-guided approach to dialogue management has been shown in recent work to be effective in creating robust customizable virtual agents capable of acting as friendly peers or task assistants.
no code implementations • ACL 2022 • Lane Lawley, Lenhart Schubert
We present NESL (the Neuro-Episodic Schema Learner), an event schema learning system that combines large language models, FrameNet parsing, a powerful logical representation of language, and a set of simple behavioral schemas meant to bootstrap the learning process.
1 code implementation • IWCS (ACL) 2021 • Gene Louis Kim, Viet Duong, Xin Lu, Lenhart Schubert
"Episodic Logic:Unscoped Logical Form" (EL-ULF) is a semantic representation capturing predicate-argument structure as well as more challenging aspects of language within the Episodic Logic formalism.
no code implementations • WS 2019 • Gene Kim, Benjamin Kane, Viet Duong, Muskaan Mendiratta, Graeme McGuire, Sophie Sackstein, Georgiy Platonov, Lenhart Schubert
Abstract Unscoped episodic logical form (ULF) is a semantic representation capturing the predicate-argument structure of English within the episodic logic formalism in relation to the syntactic structure, while leaving scope, word sense, and anaphora unresolved.
no code implementations • WS 2019 • Gene Louis Kim, Lane Lawley, Lenhart Schubert
The idea of our approach to this problem is to provide a learning system with a {``}head start{''} consisting of a semantic parser, some basic ontological knowledge, and most importantly, a small set of very general schemas about the kinds of patterns of events (often purposive, causal, or socially conventional) that even a one- or two-year-old could reasonably be presumed to possess.
no code implementations • WS 2019 • Gene Louis Kim, Lenhart Schubert
A growing interest in tasks involving language understanding by the NLP community has led to the need for effective semantic parsing and inference.
no code implementations • WS 2018 • Georgiy Platonov, Lenhart Schubert
However, what really matters pragmatically is not the accuracy of truth value judgments but whether, for instance, the computer models suffice for identifying objects described in terms of prepositional relations, (e. g., {``}the box to the left of the table{''}, where there are multiple boxes).
no code implementations • WS 2017 • Gene Kim, Lenhart Schubert
EL has proved competitive with other logical formulations in speed and inference-enablement, while expressing a wider array of natural language phenomena including intensional modification of predicates and sentences, propositional attitudes, and tense and aspect.