SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2005.05806 · ACL · 2020

Document Modeling with Graph Attention Networks for Multi-grained Machine Reading Comprehension

Ming Zhou, Ting Liu, Nan Duan, Bo Zheng, Daxin Jiang, Yaobo Liang, Wanxiang Che, Haoyang Wen

arXiv · PDF · Open in the Atlas

Code that ran

8 of 16 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (8 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 8 have no contract verdict; 0 failures of our instrument; 8 no recorded run), measured 2026-11-22; 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/2005.05806.json · badge: /api/ran/2005.05806.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
DancingSoul/NQ_BERT-DM community
Papers with Code archive
8 ran · 8 no recorded run
FunctionStatusWhere it lives
AttentionOutputLayer Ran
ran on a synthesized input · constructed an object; no result was computed
DancingSoul/NQ_BERT-DM/modules/graph_encoder.py
pointer only (licence: NONE) · get_code("eb406f6707a00ab5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DancingSoul/NQ_BERT-DM when it was checked. 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.

Config Ran
ran on a synthesized input · constructed an object; no result was computed
DancingSoul/NQ_BERT-DM/modules/graph_encoder.py
pointer only (licence: NONE) · get_code("5ee54f32fd891520")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DancingSoul/NQ_BERT-DM when it was checked. 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.

Embeddings Ran
ran on a synthesized input · constructed an object; no result was computed
DancingSoul/NQ_BERT-DM/modules/graph_encoder.py
pointer only (licence: NONE) · get_code("285c454ad1551507")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DancingSoul/NQ_BERT-DM when it was checked. 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.

Initializer Ran
ran on a synthesized input · constructed an object; no result was computed
DancingSoul/NQ_BERT-DM/modules/graph_encoder.py
pointer only (licence: NONE) · get_code("e44a2df8a877baba")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DancingSoul/NQ_BERT-DM when it was checked. 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.

IntegrationLayer Ran
ran on a synthesized input · constructed an object; no result was computed
DancingSoul/NQ_BERT-DM/modules/graph_encoder.py
pointer only (licence: NONE) · get_code("8421424641c58fe2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DancingSoul/NQ_BERT-DM when it was checked. 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.

IntermediateLayer Ran
ran on a synthesized input · constructed an object; no result was computed
DancingSoul/NQ_BERT-DM/modules/graph_encoder.py
pointer only (licence: NONE) · get_code("5293729cc460256c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DancingSoul/NQ_BERT-DM when it was checked. 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.

LayerNorm Ran
ran on a synthesized input · constructed an object; no result was computed
DancingSoul/NQ_BERT-DM/modules/graph_encoder.py
pointer only (licence: NONE) · get_code("7d637db54b1f2f78")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DancingSoul/NQ_BERT-DM when it was checked. 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.

OutputLayer Ran
ran on a synthesized input · constructed an object; no result was computed
DancingSoul/NQ_BERT-DM/modules/graph_encoder.py
pointer only (licence: NONE) · get_code("4ef4d15f103a2b67")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DancingSoul/NQ_BERT-DM when it was checked. 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.

EdgeType Not yet run
unverified (harvested, no recorded run)
DancingSoul/NQ_BERT-DM/modules/graph_encoder.py
pointer only (licence: NONE) · get_code("328a352304d452f0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DancingSoul/NQ_BERT-DM when it was checked. 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.

Encoder Not yet run
unverified (harvested, no recorded run)
DancingSoul/NQ_BERT-DM/modules/graph_encoder.py
pointer only (licence: NONE) · get_code("61cf9ac60bc28ea1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DancingSoul/NQ_BERT-DM when it was checked. 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.

EncoderLayer Not yet run
unverified (harvested, no recorded run)
DancingSoul/NQ_BERT-DM/modules/graph_encoder.py
pointer only (licence: NONE) · get_code("04a6fb299fea5a82")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DancingSoul/NQ_BERT-DM when it was checked. 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.

GraphAttention Not yet run
unverified (harvested, no recorded run)
DancingSoul/NQ_BERT-DM/modules/graph_encoder.py
pointer only (licence: NONE) · get_code("61af68f9191fc0d0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DancingSoul/NQ_BERT-DM when it was checked. 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.

GraphAttentionLayer Not yet run
unverified (harvested, no recorded run)
DancingSoul/NQ_BERT-DM/modules/graph_encoder.py
pointer only (licence: NONE) · get_code("472f4c28f8396e93")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DancingSoul/NQ_BERT-DM when it was checked. 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.

GraphEncoder Not yet run
unverified (harvested, no recorded run)
DancingSoul/NQ_BERT-DM/modules/graph_encoder.py
pointer only (licence: NONE) · get_code("8d472f7368f335e3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DancingSoul/NQ_BERT-DM when it was checked. 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.

NodePosition Not yet run
unverified (harvested, no recorded run)
DancingSoul/NQ_BERT-DM/modules/graph_encoder.py
pointer only (licence: NONE) · get_code("3f23ae7e8ac9411b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DancingSoul/NQ_BERT-DM when it was checked. 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.

PreTrainedModel Not yet run
unverified (harvested, no recorded run)
DancingSoul/NQ_BERT-DM/modules/graph_encoder.py
pointer only (licence: NONE) · get_code("7662a878ed2c7d57")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DancingSoul/NQ_BERT-DM when it was checked. 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 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 15 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
LayerNorm
brick of this paper's assembly: helper
5 other papers
2 dated earlier, 3 later · 3 only as an assembly brick
1706.03762 (2017-06)
Attention Is All You Need
2004.06165 (2020-04)
Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks
2401.06633 (2024-01)
Ada-Retrieval: An Adaptive Multi-Round Retrieval Paradigm for Sequential Recommendations
and 2 more not named here

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 2026-11-22.

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 Questions is a new challenging machine reading comprehension benchmark with two-grained answers, which are a long answer (typically a paragraph) and a short answer (one or more entities inside the long answer). Despite the effectiveness of existing methods on this benchmark, they treat these two sub-tasks individually during training while ignoring their dependencies. To address this issue, we present a novel multi-grained machine reading comprehension framework that focuses on modeling documents at their hierarchical nature, which are different levels of granularity: documents, paragraphs, sentences, and tokens. We utilize graph attention networks to obtain different levels of representations so that they can be learned simultaneously. The long and short answers can be extracted from paragraphlevel representation and token-level representation, respectively. In this way, we can model the dependencies between the two-grained answers to provide evidence for each other. We jointly train the two sub-tasks, and our experiments show that our approach significantly outperforms previous systems at both long and short answer criteria.

For agents

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

get_harvested_code_for_paper("2005.05806")
get_code_for_paper("2005.05806")
have("2005.05806")

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

curl https://syntology.ai/api/ran/2005.05806.json

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

[![Syntology run record](https://syntology.ai/api/ran/2005.05806.svg)](https://syntology.ai/paper/2005.05806)

Connect an agent — have() is free.