Papers › Entities as Experts: Sparse Memory Access with Entity Supervision

Entities as Experts: Sparse Memory Access with Entity Supervision

15 Apr 2020EMNLP 2020 11arXiv:2004.07202archive 2025-07-28

Thibault Févry, Livio Baldini Soares, Nicholas FitzGerald, Eunsol Choi, Tom Kwiatkowski

We focus on the problem of capturing declarative knowledge about entities in the learned parameters of a language model. We introduce a new model - Entities as Experts (EAE) - that can access distinct memories of the entities mentioned in a piece of text. Unlike previous efforts to integrate entity knowledge into sequence models, EAE's entity representations are learned directly from text. We show that EAE's learned representations capture sufficient knowledge to answer TriviaQA questions such as "Which Dr. Who villain has been played by Roger Delgado, Anthony Ainley, Eric Roberts?", outperforming an encoder-generator Transformer model with 10x the parameters. According to the LAMA knowledge probes, EAE contains more factual knowledge than a similarly sized BERT, as well as previous approaches that integrate external sources of entity knowledge. Because EAE associates parameters with specific entities, it only needs to access a fraction of its parameters at inference time, and we show that the correct identification and representation of entities is essential to EAE's performance.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 14 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 14 samples from 1 repository, 11 ran (11 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

erolm-a/colla-framework pytorchSyntology: 14 samples, 11 ran (0 instrument-failed) · 3 unverified 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

14 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

11ran
3unverified

Licence: 14 of the 14 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 erolm-a/colla-framework. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

erolm-a/colla-framework community (archive-listed) 14 samples, 11 ran (0 instrument-failed) · 3 unverified
BioClassifier src/models/entities_as_experts.py ran no licence file found · pointer only · 9aac70e1d1b8c20d · report fixture: signature last_hidden_state:Tensor/3/float, attention_mask:Tensor/2/int, labels:Tensor/2/int · returned tuple · level recorded 2026-09-24
EaELinearWithLayerNorm src/models/entities_as_experts.py ran fingerprinted no licence file found · pointer only · cf73b2167981e1af · report fixture: signature hidden_states:Tensor/3/float · returned Tensor · level recorded 2026-09-24
EaEPredictionHead src/models/entities_as_experts.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 99e7bea3063859c4 · report fixture: signature hidden_states:Tensor/2/float · returned Tensor · level recorded 2026-09-22
EntityMemory src/models/entities_as_experts.py ran no licence file found · pointer only · 55b3f7e6ffe06fbf · report fixture: signature X:Tensor/3/float, bio_output:Tensor/2/int, entities_output:Tensor/2/int, k:int/0/int · returned tuple · level recorded 2026-09-24
EntityPred src/models/entities_as_experts.py ran · metamorphic tier: deterministic no licence file found · pointer only · 8dd59405e934df62 · report fixture: signature sequence_output:Tensor/3/float, labels:Tensor/2/int · returned tuple · level recorded 2026-09-22
TokenPred src/models/entities_as_experts.py ran · metamorphic tier: deterministic no licence file found · pointer only · c632e3ec57a98e51 · report fixture: signature sequence_output:Tensor/3/float, labels:Tensor/2/int · returned tuple · level recorded 2026-09-22
TokenPredHead src/models/entities_as_experts.py ran · metamorphic tier: deterministic no licence file found · pointer only · 002200250a4b148a · report fixture: signature sequence_output:Tensor/3/float, labels:Tensor/2/int · returned tuple · level recorded 2026-09-22
TruncatedEncoder src/models/entities_as_experts.py ran no licence file found · pointer only · b933236b7948121b · report fixture: signature hidden_states:Tensor/3/float, attention_mask:NoneType/0/? · returned Tensor · level recorded 2026-09-24
TruncatedModel src/models/entities_as_experts.py ran no licence file found · pointer only · 8d4043133ca63339 · report fixture: signature input_ids:Tensor/3/float, attention_mask:Tensor/2/float · returned Tensor · level recorded 2026-09-24
TruncatedModelSecond src/models/entities_as_experts.py ran fingerprinted no licence file found · pointer only · 247a61525da9ac3d · report fixture: signature hidden_states:Tensor/3/float, attention_mask:NoneType/0/? · returned tuple · level recorded 2026-09-24
get_available_device src/models/entities_as_experts.py ran no licence file found · pointer only · a9888b3fd01b6e64 · report fixture: returned device · level recorded 2026-09-22
EntitiesAsExperts src/models/entities_as_experts.py unverified no licence file found · pointer only · 8e19913b399a8cf0 · report
EntitiesAsExpertsOutputs src/models/entities_as_experts.py unverified no licence file found · pointer only · 0590c6e9d6a71ea8 · report
TorchScriptDumpable src/models/entities_as_experts.py unverified no licence file found · pointer only · 9409b589470c9e13 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Entities as Experts (EAE) (graph method: Entities as Experts (EAE)). 14 bricks; individually on a fixture: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

  1. EntitiesAsExperts entry · level 0 · unverified · 8e19913b399a8cf0
  2. BioClassifier model · level 1 · ran · 9aac70e1d1b8c20d
  3. EntitiesAsExpertsOutputs helper · level 0 · unverified · 0590c6e9d6a71ea8
  4. EntityMemory model · level 1 · ran · 55b3f7e6ffe06fbf
  5. EntityPred model · level 1 · ran · 8dd59405e934df62
  6. TokenPred model · level 1 · ran · c632e3ec57a98e51
  7. TorchScriptDumpable helper · level 0 · unverified · 9409b589470c9e13
  8. TruncatedModel helper · level 1 · ran · 8d4043133ca63339
  9. TruncatedModelSecond helper · level 1 · ran · 247a61525da9ac3d
  10. TokenPredHead model · level 1 · ran · 002200250a4b148a
  11. TruncatedEncoder helper · level 1 · ran · b933236b7948121b
  12. EaEPredictionHead model · level 1 · ran · 99e7bea3063859c4
  13. EaELinearWithLayerNorm helper · level 1 · ran · cf73b2167981e1af
  14. get_available_device helper · level 1 · ran · a9888b3fd01b6e64

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2004.07202") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Language ModelingLanguage ModellingTriviaQA

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionAttention DropoutBERTBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionPosition-Wise Feed-Forward LayerReLUResidual ConnectionSoftmaxTransformerWeight DecayWordPiece

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