Papers › Teaching Machine Comprehension with Compositional Explanations

Teaching Machine Comprehension with Compositional Explanations

2 May 2020Findings of the Association for Computational Linguistics 2020arXiv:2005.00806archive 2025-07-28

Qinyuan Ye, Xiao Huang, Elizabeth Boschee, Xiang Ren

Advances in machine reading comprehension (MRC) rely heavily on the collection of large scale human-annotated examples in the form of (question, paragraph, answer) triples. In contrast, humans are typically able to generalize with only a few examples, relying on deeper underlying world knowledge, linguistic sophistication, and/or simply superior deductive powers. In this paper, we focus on "teaching" machines reading comprehension, using a small number of semi-structured explanations that explicitly inform machines why answer spans are correct. We extract structured variables and rules from explanations and compose neural module teachers that annotate instances for training downstream MRC models. We use learnable neural modules and soft logic to handle linguistic variation and overcome sparse coverage; the modules are jointly optimized with the MRC model to improve final performance. On the SQuAD dataset, our proposed method achieves 70.14% F1 score with supervision from 26 explanations, comparable to plain supervised learning using 1,100 labeled instances, yielding a 12x speed up.

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 10 code samples: 9 from 2 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 10: 10 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 4 honoured, 1 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 9 samples from 2 repositories, 9 ran (6 with no instrument failure; 3 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

INK-USC/mrc-explanation officialmentioned in paperpytorchSyntology: 5 samples, 5 ran (2 instrument-failed) · 0 unverified report
INK-USC/nl-explanation officialpytorchSyntology: 4 samples, 4 ran (1 instrument-failed) · 0 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

10 samples harvested: 10 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 4 honoured, 1 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 0 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.

4ran · honoured contract
1ran · violated contract
3ran · our draft was wrong
1ran; the contract check could not run
1ran

Licence: 10 of the 10 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; the list below is grouped by repository, each group headed by its name and what it is to the paper. 1 sample is listed last, in a group without a repository. “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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

INK-USC/mrc-explanation official repository 5 samples, 5 ran (2 instrument-failed) · 0 unverified
Occurrence module/modules.py ran no licence file found · pointer only · db9dff06388f701c · report fixture: returned Occurrence · level recorded 2026-09-22
find in 13 papers module/modules.py ran · our draft was wrong no licence file found · pointer only · a33c4f77cdf2cc58 · report fixture: signature ref_q:dict/0/?, ref_p:dict/0/?, s:dict/0/?, args:dict/0/?, pretrained_modules:dict/0/?, soft:bool/0/bool, inputs:dict/0/? · returned list · level recorded 2026-09-22
get_st_ed module/modules.py ran · honoured contract no licence file found · pointer only · a3b5708ff6975fb3 · report fixture: signature phrase:list/1/str, info:dict/0/? · returned tuple · level recorded 2026-09-22
remove_repeated module/modules.py ran · our draft was wrong no licence file found · pointer only · 0fb83ac29ef90e19 · report fixture: signature lst:list/1/Item, keys:list/1/str · returned list · level recorded 2026-09-22
softened_string_eq module/modules.py ran · violated contract fingerprinted no licence file found · pointer only · 12a347dd24e25948 · report fixture: signature s1:str/0/str, s2:str/0/str · returned bool · level recorded 2026-09-22
INK-USC/nl-explanation official repository 4 samples, 4 ran (1 instrument-failed) · 0 unverified
_and module/modules.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · d9f13dc05f7e1bb0 · report fixture: signature lst:list/1/float, soft:bool/0/bool · returned Tensor · level recorded 2026-09-22
root module/modules.py ran · honoured contract no licence file found · pointer only · 828af04bf6b3de78 · report fixture: signature funcs:tuple/1/callable, inputs:dict/0/? · returned float · level recorded 2026-09-22
to_tensor in 92 papers
census: 8 implementations from 8 papers, 3 distinct outputs across 3 buckets, one shared input per bucket
module/modules.py ran · honoured contract fingerprinted no licence file found · pointer only · 5405b2997338abd0 · report fixture: signature lst:list/1/list · returned Tensor · level recorded 2026-09-22
tuple_fy module/modules.py ran · honoured contract fingerprinted no licence file found · pointer only · 2391c1cafa690f61 · report fixture: signature t:int/0/int · returned tuple · level recorded 2026-09-22
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
normalize_answer in 304 papers repository not located ran · our draft was wrong fingerprinted licence of this copy not recorded · 6a96435eba311b08 · report fixture: signature s:str/0/str · returned str · level recorded 2026-09-22

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. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

2 sibling assemblies for Compositional Explanations (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Compositional Explanations (graph method: Compositional Explanations). 6 bricks; individually on a fixture: 6 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. find entry · level 1 · ran · our draft was wrong · a33c4f77cdf2cc58
  2. Occurrence helper · level 1 · ran · db9dff06388f701c
  3. get_st_ed helper · level 1 · ran · honoured contract · a3b5708ff6975fb3
  4. remove_repeated helper · level 1 · ran · our draft was wrong · 0fb83ac29ef90e19
  5. softened_string_eq helper · level 1 · ran · violated contract · 12a347dd24e25948
  6. normalize_answer helper · level 1 · ran · our draft was wrong · 6a96435eba311b08

harvested Assembly for Compositional Explanations (graph method: Compositional Explanations). 4 bricks; individually on a fixture: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. root entry · level 1 · ran · honoured contract · 828af04bf6b3de78
  2. _and helper · level 1 · ran; the contract check could not run (RAISES) · d9f13dc05f7e1bb0
  3. tuple_fy helper · level 1 · ran · honoured contract · 2391c1cafa690f61
  4. to_tensor helper · level 1 · ran · honoured contract · 5405b2997338abd0

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="2005.00806") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Data AugmentationMachine Reading ComprehensionReading ComprehensionWorld Knowledge

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SPEED

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