Papers › Differentiable Reasoning on Large Knowledge Bases and Natural Language

Differentiable Reasoning on Large Knowledge Bases and Natural Language

17 Dec 2019arXiv:1912.10824archive 2025-07-28

Pasquale Minervini, Matko Bošnjak, Tim Rocktäschel, Sebastian Riedel, Edward Grefenstette

Reasoning with knowledge expressed in natural language and Knowledge Bases (KBs) is a major challenge for Artificial Intelligence, with applications in machine reading, dialogue, and question answering. General neural architectures that jointly learn representations and transformations of text are very data-inefficient, and it is hard to analyse their reasoning process. These issues are addressed by end-to-end differentiable reasoning systems such as Neural Theorem Provers (NTPs), although they can only be used with small-scale symbolic KBs. In this paper we first propose Greedy NTPs (GNTPs), an extension to NTPs addressing their complexity and scalability limitations, thus making them applicable to real-world datasets. This result is achieved by dynamically constructing the computation graph of NTPs and including only the most promising proof paths during inference, thus obtaining orders of magnitude more efficient models. Then, we propose a novel approach for jointly reasoning over KBs and textual mentions, by embedding logic facts and natural language sentences in a shared embedding space. We show that GNTPs perform on par with NTPs at a fraction of their cost while achieving competitive link prediction results on large datasets, providing explanations for predictions, and inducing interpretable models. Source code, datasets, and supplementary material are available online at https://github.com/uclnlp/gntp.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1912.10824")

Code

Syntology Ran 0 of 26 code samples harvested from 2 repositories linked to this paper; 26 have no recorded run.

By repository: official repository: 26 samples from 2 repositories, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

uclnlp/gntp officialmentioned in papertfMIT report
uclnlp/ntp officialmentioned in papertfApache-2.0 report
uclnlp/ctp officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

26 samples harvested; 0 ran; 0 honoured the contract we drafted; 26 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

26unverified

Licence: 0 of the 26 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

atom2string uclnlp/ntp/ntp/tp.py official repository unverified Apache-2.0 (permissive) · 842678021f43c382 · report
attention uclnlp/gntp/gntp/attention.py official repository unverified MIT (permissive) · 8ff6535b5f8688aa · report
bilstm_nosupport_reader_model_with_cands uclnlp/ntp/ntp/jtr/nn/models.py official repository unverified Apache-2.0 (permissive) · 9a713eefc8e66051 · report
bilstm_reader_model_with_cands uclnlp/ntp/ntp/jtr/nn/models.py official repository unverified Apache-2.0 (permissive) · 19db131ea10b3837 · report
boe_nosupport_cands_reader_model uclnlp/ntp/ntp/jtr/nn/models.py official repository unverified Apache-2.0 (permissive) · a3b949dcebbfa464 · report
check_checkpoint_finished uclnlp/gntp/bin/gntp-cli.py official repository unverified MIT (permissive) · 6ff9dbea90d5710f · report
clip uclnlp/gntp/gntp/losses.py official repository unverified MIT (permissive) · 504b918b060a4ed7 · report
create_mask uclnlp/gntp/gntp/masking.py official repository unverified MIT (permissive) · bd0230f569a312c8 · report
diff_k_max uclnlp/ntp/ntp/kmax.py official repository unverified Apache-2.0 (permissive) · 137ebc202f3a3a6e · report
diff_k_max_grad uclnlp/ntp/ntp/kmax.py official repository unverified Apache-2.0 (permissive) · 16b7fa57446bec19 · report
get_buckets uclnlp/ntp/ntp/jtr/preprocess/batch.py official repository unverified Apache-2.0 (permissive) · b6dbe45fcd29ec5e · report
iopen uclnlp/gntp/gntp/io.py official repository unverified MIT (permissive) · 805c610d7342febb · report
is_atom uclnlp/ntp/ntp/util.py official repository unverified Apache-2.0 (permissive) · 08da9620aade33aa · report
is_tensor uclnlp/ntp/ntp/prover.py official repository unverified Apache-2.0 (permissive) · 86a13149d6073483 · report
is_variable uclnlp/ntp/ntp/tp.py official repository unverified Apache-2.0 (permissive) · 35f3db77164bbce5 · report
is_variables_list uclnlp/ntp/ntp/prover.py official repository unverified Apache-2.0 (permissive) · ebf7f09a2e38dd00 · report
kb_ids2known_facts uclnlp/ntp/ntp/experiments/recover.py official repository unverified Apache-2.0 (permissive) · 7aff3f773673f361 · report
load_random_state uclnlp/gntp/bin/gntp-cli.py official repository unverified MIT (permissive) · b0f8f95117e6f32b · report
logistic_loss uclnlp/gntp/gntp/losses.py official repository unverified MIT (permissive) · 23981ea194ca5abd · report
my_py_func uclnlp/ntp/ntp/kmax.py official repository unverified Apache-2.0 (permissive) · 8025ce61959161a4 · report
read_mentions uclnlp/gntp/gntp/io.py official repository unverified MIT (permissive) · fd3cdc689950a17a · report
read_triples uclnlp/gntp/gntp/io.py official repository unverified MIT (permissive) · e918b6b61c80d29b · report
rep2string uclnlp/ntp/ntp/prover.py official repository unverified Apache-2.0 (permissive) · 1d05c029e1a88874 · report
representation_match uclnlp/ntp/ntp/nunify.py official repository unverified Apache-2.0 (permissive) · 68763b0b0695fd72 · report
sparse_softmax uclnlp/gntp/gntp/attention.py official repository unverified MIT (permissive) · a1c7a129b1ccd13a · report
trim uclnlp/ntp/ntp/util.py official repository unverified Apache-2.0 (permissive) · b6b34a3aaa5bb4e9 · report

Tasks

Link PredictionQuestion AnsweringReading Comprehension

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Link Prediction FB122 GNTPs HITS@3 69.2 #3 of 5 Archive leaderboard report
Link Prediction FB122 GNTPs Hits@10 73.2 #3 of 5 Archive leaderboard report
Link Prediction FB122 GNTPs Hits@5 71.1 #3 of 5 Archive leaderboard report
Link Prediction FB122 GNTPs MRR 67.8 #3 of 5 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections