Papers › Towards Interpretable Natural Language Understanding with Explanations as Latent Variables

Towards Interpretable Natural Language Understanding with Explanations as Latent Variables

24 Oct 2020NeurIPS 2020 12arXiv:2011.05268archive 2025-07-28

Wangchunshu Zhou, Jinyi Hu, HANLIN ZHANG, Xiaodan Liang, Maosong Sun, Chenyan Xiong, Jian Tang

Recently generating natural language explanations has shown very promising results in not only offering interpretable explanations but also providing additional information and supervision for prediction. However, existing approaches usually require a large set of human annotated explanations for training while collecting a large set of explanations is not only time consuming but also expensive. In this paper, we develop a general framework for interpretable natural language understanding that requires only a small set of human annotated explanations for training. Our framework treats natural language explanations as latent variables that model the underlying reasoning process of a neural model. We develop a variational EM framework for optimization where an explanation generation module and an explanation-augmented prediction module are alternatively optimized and mutually enhance each other. Moreover, we further propose an explanation-based self-training method under this framework for semi-supervised learning. It alternates between assigning pseudo-labels to unlabeled data and generating new explanations to iteratively improve each other. Experiments on two natural language understanding tasks demonstrate that our framework can not only make effective predictions in both supervised and semi-supervised settings, but also generate good natural language explanation.

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: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 12 unverified; every one of the 2 samples that ran constructed an object rather than computing a result. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 14 samples from 1 repository, 2 ran (2 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

JamesHujy/ELV officialmentioned in papermentioned on GitHubpytorchSyntology: 14 samples, 2 ran (0 instrument-failed) · 12 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: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 12 unverified; every one of the 2 samples that ran constructed an object rather than computing a result. “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.

2ran
12unverified

Licence: 0 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 JamesHujy/ELV. “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.

JamesHujy/ELV official repository 14 samples, 2 ran (0 instrument-failed) · 12 unverified
BertConfig in 14 papers ELV_re/s2s_ft/modeling_decoding.py ran MIT (permissive) · cfcccfa363b0d97d · report fixture: returned BertConfig · level recorded 2026-09-22
LabelSmoothingLoss in 6 papers ELV_re/s2s_ft/modeling_decoding.py ran MIT (permissive) · e0010670dcd7b506 · report fixture: returned LabelSmoothingLoss · level recorded 2026-09-22
BertAttention in 28 papers ELV_re/s2s_ft/modeling_decoding.py unverified MIT (permissive) · 79fb582753417716 · report
BertEmbeddings in 21 papers ELV_re/s2s_ft/modeling_decoding.py unverified MIT (permissive) · 079b9f19680e22e9 · report
BertEncoder in 20 papers ELV_re/s2s_ft/modeling_decoding.py unverified MIT (permissive) · fcc6106b91ccf5a8 · report
BertForSeq2SeqFinetuningWithPseudoMask ELV_re/s2s_ft/modeling_decoding.py unverified MIT (permissive) · a073600618d7cd25 · report
BertLMPredictionHead in 10 papers ELV_re/s2s_ft/modeling_decoding.py unverified MIT (permissive) · 4c4cc2ac34ec0f6d · report
BertLayer in 23 papers ELV_re/s2s_ft/modeling_decoding.py unverified MIT (permissive) · 06470b60e5848309 · report
BertModel in 16 papers ELV_re/s2s_ft/modeling_decoding.py unverified MIT (permissive) · f31e6bafe1bf135f · report
BertPreTrainingHeads in 5 papers ELV_re/s2s_ft/modeling_decoding.py unverified MIT (permissive) · 9ab2eef8291e2fb8 · report
BertPredictionHeadTransform in 10 papers ELV_re/s2s_ft/modeling_decoding.py unverified MIT (permissive) · 8edf5cdb355831e7 · report
BertSelfAttention in 29 papers ELV_re/s2s_ft/modeling_decoding.py unverified MIT (permissive) · 0cddc969b8e047cc · report
PreTrainedBertModel ELV_re/s2s_ft/modeling_decoding.py unverified MIT (permissive) · 1e4c8070e2b6f7a0 · report
TransformerFFN in 5 papers ELV_re/s2s_ft/modeling_decoding.py unverified MIT (permissive) · a50158bd9f69ff91 · 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 variational EM framework (graph method: variational EM framework). 20 bricks; individually on a fixture: 6 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 14 unverified. The assembly has not been run end-to-end.

  1. BertForSeq2SeqFinetuningWithPseudoMask entry · level 0 · unverified · a073600618d7cd25
  2. BertModel model · level 0 · unverified · f31e6bafe1bf135f
  3. BertPreTrainingHeads helper · level 0 · unverified · 9ab2eef8291e2fb8
  4. LabelSmoothingLoss loss · level 1 · ran · e0010670dcd7b506
  5. PreTrainedBertModel helper · level 0 · unverified · 1e4c8070e2b6f7a0
  6. BertEmbeddings helper · level 0 · unverified · 079b9f19680e22e9
  7. BertEncoder helper · level 0 · unverified · fcc6106b91ccf5a8
  8. BertPooler helper · level 1 · ran · 8f1a0b9437ccc562
  9. BertLMPredictionHead helper · level 0 · unverified · 4c4cc2ac34ec0f6d
  10. BertConfig helper · level 1 · ran · cfcccfa363b0d97d
  11. BertLayer model · level 0 · unverified · 06470b60e5848309
  12. BertPredictionHeadTransform helper · level 0 · unverified · 8edf5cdb355831e7
  13. BertAttention model · level 0 · unverified · 79fb582753417716
  14. BertIntermediate helper · level 1 · ran · 9597f5146c4fa55c
  15. BertOutput helper · level 0 · unverified · 4a7f9dbc40aaed5d
  16. TransformerFFN helper · level 0 · unverified · a50158bd9f69ff91
  17. BertSelfAttention helper · level 0 · unverified · 0cddc969b8e047cc
  18. BertSelfOutput helper · level 0 · unverified · 3b0ae0e2b34fdf2e
  19. gelu helper · level 1 · ran · honoured contract · 40e9fee2e0b7e278
  20. swish helper · level 2 · ran · our draft was wrong · 0f786c407fb1ee4c

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="2011.05268") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Explanation GenerationNatural Language Understanding

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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