Papers with formal representation

7 papers
PDDLEGO: Iterative Planning in Textual Environments (2024.starsem-1)

Copied to clipboard

Challenge: Existing methods to plan in textual environments rely on a fully-observed environment where all entity states are known, but are not interpretable.
Approach: They propose to use LLMs to generate a formal representation of the environment that can be solved by a symbolic planner.
Outcome: The proposed model outperforms existing methods in the Coin Collector simulation and Cooking World simulations.
An Annotation Language for Semantic Search of Legal Sources (L18-1)

Copied to clipboard

Challenge: formalizing legal sources is an important challenge, but the generation of a formal representation from legal texts has been less considered and requires considerable expertise.
Approach: They propose to experiment with annotations and the annotation process to improve uniformity and efficiency of legal annotation.
Outcome: The proposed method improves the richness and efficiency of legal annotations.
On the Limit of Language Models as Planning Formalizers (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models can create plans that are neither executable nor verifiable in grounded environments.
Approach: They use Large Language Models to generate a formal representation of the planning domain in some language, such as Planning Domain Definition Language (PDDL).
Outcome: The proposed model outperforms the models directly generating plans while being robust to lexical perturbation.
Mapping probability word problems to executable representations (2021.emnlp-main)

Copied to clipboard

Challenge: a recent paper addresses the problem of solving math word problems automatically . a number of approaches have been proposed for solving word problems .
Approach: They employ a sequence-to-sequence model to generate intermediate representations for word problems . they then use a probabilistic programming system to provide the answer . their best performing model incorporates general-domain contextualised word representations .
Outcome: The proposed model is the best performing on a declarative language and a probabilistic programming system.
Unifying Inference-Time Planning Language Generation (2026.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) are used to generate a formal representation of a plan in a planning language.
Approach: They propose a unifying organizational framework based on intermediate representations to unify the inference-time LLM-as-formalizer methodology for classical planning.
Outcome: The proposed framework subsumes most existing work and proposes new ones that involve syntactically similar but high-resource intermediate languages.
GRhOOT: Ontology of Rhetorical Figures in German (2022.lrec-1)

Copied to clipboard

Challenge: GRhOOT is a domain ontology of rhetorical figures in the German language . the goal is to allow for easier detection of non-literal language based tasks .
Approach: GRhOOT is a domain ontology of 110 rhetorical figures in the german language . the goal is to allow for easier detection and sentiment analysis .
Outcome: The ontology of rhetorical figures in the German language is based on 110 rhetorical figure domains . the goal is to make the ontologies more accurate and to allow for easier detection .
Mitigating Data Scarcity in Semantic Parsing across Languages with the Multilingual Semantic Layer and its Dataset (2024.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have advanced significantly in understanding human text, but semantic representations remain crucial for various applications.
Approach: They introduce a multilingual semantic layer which decouples from disambiguation and external inventories and simplifies the task.
Outcome: The proposed model reduces performance gap between languages and annotators by enabling them to understand semantic relations between concepts in any language.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations