SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2004.03066 · ACL · 2020

Are Natural Language Inference Models IMPPRESsive? Learning IMPlicature and PRESupposition

Adina Williams, Alex Warstadt, Paloma Jeretič, Suvrat Bhooshan

arXiv · PDF · Open in the Atlas

Code that ran

2 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 0 failures of our instrument; 3 no recorded run), measured 2026-11-21; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2004.03066.json · badge: /api/ran/2004.03066.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
facebookresearch/ImpPres canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
0 ran · 3 no recorded run
FunctionStatusWhere it lives
accuracy Ran
ran, honoured the contract we drafted
facebookresearch/ImpPres/results/summarize_presupposition_results.py
pointer only (licence: NOASSERTION) · get_code("251024f2888d4ffc")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/ImpPres (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

correct_prediction Ran
ran, violated the contract we drafted
facebookresearch/ImpPres/results/summarize_presupposition_results.py
pointer only (licence: NOASSERTION) · get_code("4eef1f254009825d")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/ImpPres (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

conjugate Not yet run
unverified (harvested, no recorded run)
this paper's copy was not recorded; identical code first harvested from alexwarstadt/data_generation
pointer only; the stored copy get_code serves, from alexwarstadt/data_generation, is pointer only (licence: NONE) · get_code("b6aedf7ef5f4ef95")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

re_conjugate Not yet run
unverified (harvested, no recorded run)
this paper's copy was not recorded; identical code first harvested from alexwarstadt/data_generation
pointer only; the stored copy get_code serves, from alexwarstadt/data_generation, is pointer only (licence: NONE) · get_code("cbb2572646ec223f")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

return_aux Not yet run
unverified (harvested, no recorded run)
this paper's copy was not recorded; identical code first harvested from alexwarstadt/data_generation
pointer only; the stored copy get_code serves, from alexwarstadt/data_generation, is pointer only (licence: NONE) · get_code("1d4436a79b8a664b")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 0 later) and 2 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
conjugate 1 other paper
1 dated earlier
1909.02597 (2019-09)
Investigating BERT's Knowledge of Language: Five Analysis Methods with NPIs
re_conjugate 1 other paper
1 dated earlier
1909.02597 (2019-09)
Investigating BERT's Knowledge of Language: Five Analysis Methods with NPIs
return_aux 1 other paper
1 dated earlier
1909.02597 (2019-09)
Investigating BERT's Knowledge of Language: Five Analysis Methods with NPIs

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Natural language inference (NLI) is an increasingly important task for natural language understanding, which requires one to infer whether a sentence entails another. However, the ability of NLI models to make pragmatic inferences remains understudied. We create an IMPlicature and PRESupposition diagnostic dataset (IMPPRES), consisting of >25k semiautomatically generated sentence pairs illustrating well-studied pragmatic inference types. We use IMPPRES to evaluate whether BERT, InferSent, and BOW NLI models trained on MultiNLI (Williams et al., 2018) learn to make pragmatic inferences. Although MultiNLI appears to contain very few pairs illustrating these inference types, we find that BERT learns to draw pragmatic inferences. It reliably treats scalar implicatures triggered by "some" as entailments. For some presupposition triggers like only, BERT reliably recognizes the presupposition as an entailment, even when the trigger is embedded under an entailment canceling operator like negation. BOW and InferSent show weaker evidence of pragmatic reasoning. We conclude that NLI training encourages models to learn some, but not all, pragmatic inferences. 1 github.com/facebookresearch/ImpPres Type Example Trigger Jo's cat yawned. Presupposition Jo has a cat.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2004.03066")
get_code_for_paper("2004.03066")
have("2004.03066")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2004.03066.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2004.03066.svg)](https://syntology.ai/paper/2004.03066)

Connect an agent — have() is free.