Programming by Example and Text-to-Code Translation for Conversational Code Generation

Eli Whitehouse; Marc Franco-Salvador; William Gerard; Yauhen Klimovich

RECORD

Programming by Example and Text-to-Code Translation for Conversational Code Generation

Eli Whitehouse, William Gerard, Yauhen Klimovich, Marc Franco-Salvador

Computation and Language · Submitted 21 Nov 2022

abstract compiled · 2026-09-23 · no language-model review

The authors' main claim We propose Modular Programs for Text-guided Hierarchical Synthesis (MPaTHS), a method for integrating Programming by Example and text-to-code systems which offers an accessible natural language interface for synthesizing general programs.

how it is stated · asserted 1.00 read the record →

Comment (0) Read on arXiv ↗

Cite ▾

arXiv ID2211.11554 (version 3)

Pith IDPNMWXB2N, Pith's permanent record of this paper and its review

CitationEli Whitehouse, Marc Franco-Salvador, William Gerard, Yauhen Klimovich. "Programming by Example and Text-to-Code Translation for Conversational Code Generation." arXiv:2211.11554 (2022). https://pith.science/paper/PNMWXB2N

Claim paper

The compiled record

The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.

Open the compiled record

Compiled by classifier-1.13.0 via TypeSafe API, question bank abstract-p1-20260923, 2026-09-23: 1 request, 4,912 input tokens.

What the abstract itself states, as probabilities: claims first 0.20 · states limitation 0.14 · human participants 0.09 · controlled comparison 0.04 · randomized assignment 0.01 · states quantitative result 0.03 · compares with prior results 0.52 · mentions code or data availability 0.04.

The abstract, sentence by sentence

arXiv listing abstract v3. Results and the main claim are underlined; show every role.

Dialogue systems is an increasingly popular task of natural language processing. However, the dialogue paths tend to be deterministic, restricted to the system rails, regardless of the given request or input text. Recent advances in program synthesis have led to systems which can synthesize programs from very general search spaces, e.g. Programming by Example, and to systems with very accessible interfaces for writing programs, e.g. text-to-code translation, but have not achieved both of these qualities in the same system. We propose Modular Programs for Text-guided Hierarchical Synthesis (MPaTHS), a method for integrating Programming by Example and text-to-code systems which offers an accessible natural language interface for synthesizing general programs. We present a program representation that allows our method to be applied to the problem of task-oriented dialogue. Finally, we demo MPaTHS using our program representation.

background contribution method result interpretation main claim

What the classifier reports for each sentence. The number is the probability it gave the label.
#	sentence	role	the authors' own work	states the main conclusion	strength
s0	Dialogue systems is an increasingly popular task of natural language processing.	background 1.00	0.04	0.02	asserted 1.00
s1	However, the dialogue paths tend to be deterministic, restricted to the system rails, regardless of the given request or input text.	background 0.74	0.05	0.02	asserted 1.00
s2	Recent advances in program synthesis have led to systems which can synthesize programs from very general search spaces, e.g. Programming by Example, and to systems with very accessible interfaces for writing programs, e.g. text-to-code translation, but have not achieved both of these qualities in the same system.	gap 0.95	0.04	0.07	asserted 1.00
s3	We propose Modular Programs for Text-guided Hierarchical Synthesis (MPaTHS), a method for integrating Programming by Example and text-to-code systems which offers an accessible natural language interface for synthesizing general programs.	contribution 0.93	0.93	0.58	asserted 1.00
s4	We present a program representation that allows our method to be applied to the problem of task-oriented dialogue.	contribution 0.65	0.89	0.08	asserted 0.99
s5	Finally, we demo MPaTHS using our program representation.	contribution 0.80	0.91	0.09	asserted 1.00

What kind of paper the classifier reports this is: method or tool 1.00 · evidence from argument 0.42.

What was examined, and what was not

sources read

arXiv listing abstract v3

not examined

full text
figures and tables
references and citing sentences
relations to other papers

levels run

P abstract

not run

S sections
T body sentences
C citations
R cross-paper relations

Every quoted sentence on this record is the authors'. Every label is from Pith's closed vocabulary, with the probability shown beside it. Every number in the measurements table is the authors', checked by code. Record as JSON

The paper

Original abstract

Dialogue systems is an increasingly popular task of natural language processing. However, the dialogue paths tend to be deterministic, restricted to the system rails, regardless of the given request or input text. Recent advances in program synthesis have led to systems which can synthesize programs from very general search spaces, e.g. Programming by Example, and to systems with very accessible interfaces for writing programs, e.g. text-to-code translation, but have not achieved both of these qualities in the same system. We propose Modular Programs for Text-guided Hierarchical Synthesis (MPaTHS), a method for integrating Programming by Example and text-to-code systems which offers an accessible natural language interface for synthesizing general programs. We present a program representation that allows our method to be applied to the problem of task-oriented dialogue. Finally, we demo MPaTHS using our program representation.

Human review

How Pith checks papers → · Full audit of this paper →

How the literature uses it

What this paper does with the arXiv papers it cites

Each citing sentence is taken from the citing paper's LaTeX source and typed by Pith's classifier. A label appears at probability 0.8 or more (0.95 for support), a contest at 0.7 or more; the quoted words are the citing authors'. How each label was checked · JSON

What it cites

Cites as support 1 paper

We suggest that to accomplish this, a program synthesis system must combine the strengths of both approaches, allowing natural language to inform the search space of programs that it explores [ref] .

Communicating Natural Programs to Humans and Machines · Introduction · 0.99

Cites as background 4 papers

Program Synthesis Systems Recent literature has explored text-to-code translation with large language models as a path to program synthesis [ref] .

Unified Pre-training for Program Understanding and Generation · Related Work · 0.99
Program Synthesis Systems Recent literature has explored text-to-code translation with large language models as a path to program synthesis [ref] .

Program Synthesis with Large Language Models · Related Work · 0.99
Program Synthesis Systems Recent literature has explored text-to-code translation with large language models as a path to program synthesis [ref] .

A Systematic Evaluation of Large Language Models of Code · Related Work · 0.99

Discussion

Know something about this paper? Leave a comment, or highlight any passage above to comment on it.