Pith. sign in

REVIEW 1 cited by

Natural Language Decomposition and Interpretation of Complex Utterances

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2305.08677 v2 pith:PSELAT7U submitted 2023-05-15 cs.CL

classification cs.CL
keywords languagecomplexapproachnaturaluserutterancesdecompositioninterpretation
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Designing natural language interfaces has historically required collecting supervised data to translate user requests into carefully designed intent representations. This requires enumerating and labeling a long tail of user requests, which is challenging. At the same time, large language models (LLMs) encode knowledge about goals and plans that can help conversational assistants interpret user requests requiring numerous steps to complete. We introduce an approach to handle complex-intent-bearing utterances from a user via a process of hierarchical natural language decomposition and interpretation. Our approach uses a pre-trained language model to decompose a complex utterance into a sequence of simpler natural language steps and interprets each step using the language-to-program model designed for the interface. To test our approach, we collect and release DeCU -- a new NL-to-program benchmark to evaluate Decomposition of Complex Utterances. Experiments show that the proposed approach enables the interpretation of complex utterances with almost no complex training data, while outperforming standard few-shot prompting approaches.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Can we Retrieve Everything All at Once? ARM: An Alignment-Oriented LLM-based Retrieval Method

    cs.CL 2025-01 conditional novelty 5.0 of 10

    ARM retrieves all needed tables and passages for complex questions in one constrained LLM decoding pass by aligning keywords to corpus n-grams and using a MIP solver to connect related objects, beating RAG and ReAct o...

Pith tools