SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1909.03186 · EMNLP · 2020

On Extractive and Abstractive Neural Document Summarization with Transformer Language Models

Christopher Pal, Jonathan Pilault, Polytechnique Montreal, Raymond Li, Sandeep Subramanian, Element Ai, Sandeep Subramanian1, Raymond Li1, Jonathan Pilault1, Christopher Pal1

arXiv · PDF · Open in the Atlas

Code that ran

1 of 6 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 1 has no contract verdict; 0 failures of our instrument; 5 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; 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/1909.03186.json · badge: /api/ran/1909.03186.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
Bread-and-Code/Text-Summarization community (classifier label)
classifier basis not recorded on the link
1 ran · 5 no recorded run
FunctionStatusWhere it lives
convert_single_example Ran
ran on a synthesized input
Bread-and-Code/Text-Summarization/Sam/transfer_learning/preprocess.py
code served (permissive licence) · get_code("8b4900c56e32f11a")
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 InputFeatures. The image it ran in was not recorded. If your copy returns the same type 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

class SimpleTokenizer:
    """Minimal tokenizer for testing."""
    def tokenize(self, text):
        """Split text into tokens."""
        return text.lower().split()
    
    def convert_tokens_to_ids(self, tokens):
        """Convert tokens to ids."""
        # Simple mapping: [CLS]=101, [SEP]=102, other tokens map to ord value
        token_map = {
            '[CLS]': 101,
            '[SEP]': 102,
        }
        ids = []
        for token in tokens:
            if token in token_map:
                ids.append(token_map[token])
            else:
                ids.append(hash(token) % 1000 + 103)
        return ids

class InputExample:
    """A single training/test example."""
    def __init__(self, src_txt, tgt_txt):
        self.src_txt = src_txt
        self.tgt_txt = tgt_txt

# Create instances
tokenizer = SimpleTokenizer()
example = InputExample(
    src_txt="hello world example",
    tgt_txt="bonjour monde"
)

ARGS = {
    'ex_index': 0,
    'example': example,
    'max_seq_length_src': 10,
    'max_seq_length_tgt': 8,
    'tokenizer': tokenizer,
}
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 InputFeatures — a InputFeatures output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a InputFeatures output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
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
encoding_layer Not yet run
unverified (harvested, no recorded run)
Bread-and-Code/Text-Summarization/Sam/Rnn_encoding_layer.py
code served (permissive licence) · get_code("3872fc8eb31e89eb")
How it ran

no invocation recorded.

file_based_convert_examples_to_features Not yet run
unverified (harvested, no recorded run)
Bread-and-Code/Text-Summarization/Sam/transfer_learning/preprocess.py
code served (permissive licence) · get_code("cd9f0332b1d8fafc")
How it ran

no invocation recorded.

file_based_input_fn_builder Not yet run
unverified (harvested, no recorded run)
Bread-and-Code/Text-Summarization/Sam/transfer_learning/preprocess.py
code served (permissive licence) · get_code("3d56dfd55a3825c2")
How it ran

no invocation recorded.

inference_decoding_layer Not yet run
unverified (harvested, no recorded run)
Bread-and-Code/Text-Summarization/Sam/RNN_inference_decoding_layer.py
code served (permissive licence) · get_code("5dcbd82955f38694")
How it ran

no invocation recorded.

training_decoding_layer Not yet run
unverified (harvested, no recorded run)
Bread-and-Code/Text-Summarization/Sam/RNN_training_decoding_layer.py
code served (permissive licence) · get_code("fccaf351e41b9588")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 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 6 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

We present a method to produce abstractive summaries of long documents that exceed several thousand words via neural abstractive summarization. We perform a simple extractive step before generating a summary, which is then used to condition the transformer language model on relevant information before being tasked with generating a summary. We also show that this approach produces more abstractive summaries compared to prior work that employs a copy mechanism while still achieving higher ROUGE scores. We provide extensive comparisons with strong baseline methods, prior state of the art work as well as multiple variants of our approach including those using only transformers, only extractive techniques and combinations of the two. We examine these models using four different summarization tasks and datasets: arXiv papers, PubMed papers, the Newsroom and BigPatent datasets. We find that transformer based methods produce summaries with fewer n-gram copies, leading to n-gram copying statistics that are more similar to human generated abstracts. We include a human evaluation, finding that transformers are ranked highly for coherence and fluency, but purely extractive methods score higher for informativeness and relevance. We hope that these architectures and experiments may serve as strong points of comparison for future work. 1

For agents

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

get_harvested_code_for_paper("1909.03186")
get_code_for_paper("1909.03186")
have("1909.03186")

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

curl https://syntology.ai/api/ran/1909.03186.json

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

[![Syntology run record](https://syntology.ai/api/ran/1909.03186.svg)](https://syntology.ai/paper/1909.03186)

Connect an agent — have() is free.