SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.11575 · ACL · 2021

Learn to Resolve Conversational Dependency: A Consistency Training Framework for Conversational Question Answering

Jaewoo Kang, Jungsoo Park, Hyunjae Kim, Gangwoo Kim

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 1 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/2106.11575.json · badge: /api/ran/2106.11575.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
dmis-lab/excord community
Papers with Code archive
2 ran · 1 no recorded run
FunctionStatusWhere it lives
masked_log_softmax Ran
ran; our contract draft was wrong, not the code
dmis-lab/excord/excord.py
code served (permissive licence) · get_code("6475a89b863b68b7")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create a vector tensor with shape (2, 4) - batch size 2, dimension 4
vector = torch.randn(2, 4)

# Create a mask tensor with shape (2,) that will be broadcastable to vector
# Mask values: 1.0 means "keep", 0.0 means "mask out"
mask = torch.tensor([1.0, 1.0])

# Set dim to -1 (last dimension) for log_softmax
dim = -1

ARGS = {
    "vector": vector,
    "mask": mask,
    "dim": dim
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
masked_softmax Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
dmis-lab/excord/excord.py
code served (permissive licence) · get_code("971291e2c5ef552b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn.functional as F

torch.manual_seed(0)

# Create a vector tensor with shape (2, 4) - batch size 2, 4 dimensions
vector = torch.randn(2, 4)

# Create a mask tensor with shape (2,) that will be unsqueezed to match vector dimensions
mask = torch.ones(2, dtype=torch.float32)

# Alternative: create a mask that's already properly shaped
mask = torch.ones(2, 1, dtype=torch.float32)

# Test case 1: mask with fewer dimensions than vector
dim = -1
memory_efficient = False
mask_fill_value = -1e+32

ARGS = {
    "vector": vector,
    "mask": mask,
    "dim": dim,
    "memory_efficient": memory_efficient,
    "mask_fill_value": mask_fill_value
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
consistency_reg Not yet run
unverified (harvested, no recorded run)
dmis-lab/excord/excord.py
code served (permissive licence) · get_code("ded3f8b7dfafa26a")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 3 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.

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

One of the main challenges in conversational question answering (CQA) is to resolve the conversational dependency, such as anaphora and ellipsis. However, existing approaches do not explicitly train QA models on how to resolve the dependency, and thus these models are limited in understanding human dialogues. In this paper, we propose a novel framework, EXCORD (Explicit guidance on how to resolve Conversational Dependency) to enhance the abilities of QA models in comprehending conversational context. EXCORD first generates self-contained questions that can be understood without the conversation history, then trains a QA model with the pairs of original and self-contained questions using a consistency-based regularizer. In our experiments, we demonstrate that EXCORD significantly improves the QA models' performance by up to 1.2 F1 on QuAC (Choi et al., 2018), and 5.2 F1 on CANARD (Elgohary et al., 2019), while addressing the limitations of the existing approaches. 1 † Corresponding author 1 Our models and code are available at: https://github.com/dmis-lab/excord 2 While the term "context" usually refers to the evidence document from which the answer is extracted, in CQA, it refers to conversational context.

For agents

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

get_harvested_code_for_paper("2106.11575")
get_code_for_paper("2106.11575")
have("2106.11575")

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

curl https://syntology.ai/api/ran/2106.11575.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.11575.svg)](https://syntology.ai/paper/2106.11575)

Connect an agent — have() is free.