Browse State-of-the-Art › Headline Generation
Headline Generation
36 papers with code · 1 benchmark · 2 datasets archive 2025-07-28
Benchmarks archive 2025-07-28
1 leaderboard table shown for this task, 1 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| YTSeg (2 rows) | BART (no context) | From Text Segmentation to Smart Chaptering: A Novel Benchmark for... | — | — | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
2 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 86 · with a code link: 36 · where Syntology ran a sample: 4 (4 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (4 of 86 tagged: 4 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 86 of 86, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
25 Mar 2024 4 repositories listedNSINA is the largest news corpus for Sinhala, available up to date.
-
7 Mar 2022 3 repositories listedWe introduce IT5, the first family of encoder-decoder transformer models pretrained specifically on Italian.
-
25 Aug 2019 3 repositories listedWe propose a simple yet effective approach for improving Korean word representations using additional linguistic annotation (i. e.
-
24 May 2018 3 repositories listed Syntology official (archive's flag): 12 ran · 16 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 2 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 17 harvested samples) · 2 pointer-only (licence)In this survey, we consider seq2seq problems from the RL point of view and provide a formulation combining the power of RL methods in decision-making with sequence-to-sequence models that enable remembering long-term…
-
22 Dec 2020 2 repositories listedProviding pretrained language models with simple task descriptions in natural language enables them to solve some tasks in a fully unsupervised fashion.
-
9 Jul 2020 2 repositories listedPretrained language models based on Transformer architecture are the reason for recent breakthroughs in many areas of NLP, including sentiment analysis, question answering, named entity recognition.
-
2 Jun 2019 2 repositories listedRecent work in the field of automatic summarization and headline generation focuses on maximizing ROUGE scores for various news datasets.
-
21 Jan 2025 1 repository listedIn this paper, we propose a framework Fact-Preserved Personalized News Headline Generation (short for FPG), to prompt a tradeoff between personalization and consistency.
-
21 Jan 2025 1 repository listedPrevailing methods focus on user-oriented content preferences, but most of them overlook the fact that diverse stylistic preferences are integral to users' panoramic interests, leading to suboptimal personalization.
-
BeliN: A Novel Corpus for Bengali Religious News Headline Generation using Contextual Feature Fusion2 Jan 2025 1 repository listedAutomatic text summarization, particularly headline generation, remains a critical yet underexplored area for Bengali religious news.
-
28 Dec 2024 1 repository listed Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 5 harvested samples) · 1 pointer-only (licence)This paper introduces AfriHG -- a news headline generation dataset created by combining from XLSum and MasakhaNEWS datasets focusing on 16 languages widely spoken by Africa.
-
6 Jun 2024 1 repository listedMillions of news articles published online daily can overwhelm readers.
-
TeClass: A Human-Annotated Relevance-based Headline Classification and Generation Dataset for Telugu17 Apr 2024 1 repository listedWe further demonstrate the impact of this work by fine-tuning various headline generation models using TeClass dataset.
-
29 Nov 2023 1 repository listedThe task of headline generation within the realm of Natural Language Processing (NLP) holds immense significance, as it strives to distill the true essence of textual content into concise and attention-grabbing…
-
26 Oct 2023 1 repository listedStylistic headline generation is the task to generate a headline that not only summarizes the content of an article, but also reflects a desired style that attracts users.
-
16 Oct 2023 1 repository listedTo explore how humans can best leverage LLMs for writing and how interacting with these models affects feelings of ownership and trust in the writing process, we compared common human-AI interaction types (e. g.…
-
4 Sep 2023 1 repository listedHeadline generation, a key task in abstractive summarization, strives to condense a full-length article into a succinct, single line of text.
-
10 May 2023 1 repository listedWe present Vārta, a large-scale multilingual dataset for headline generation in Indic languages.
-
7 Nov 2022 1 repository listedIn this paper, we propose a novel Seq2Seq model called CLH3G (Contrastive Learning enhanced Historical Headlines based Headline Generation) which can use the historical headlines of the articles that the author wrote in…
-
1 Jun 2022 1 repository listedTherefore, we propose the first title-text dataset on web documents that incorporates a wide variety of domains to facilitate downstream training.
-
28 May 2022 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 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) · 1 unverified (of 3 harvested samples) · 3 pointer-only (licence)Sentence summarization aims at compressing a long sentence into a short one that keeps the main gist, and has extensive real-world applications such as headline generation.
-
12 May 2022 1 repository listedScientific extreme summarization (TLDR) aims to form ultra-short summaries of scientific papers.
-
15 Sep 2021 1 repository listedWe also consider a new headline generation strategy that takes advantage of the controllable generation order of Transformer.
-
1 Aug 2021 1 repository listedTo build up a benchmark for this problem, we publicize a large-scale dataset named PENS (PErsonalized News headlineS).
-
3 Jun 2021 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 4 harvested samples) · 4 pointer-only (licence)In this framework, we further pre-train mBART sequence-to-sequence denoising auto-encoder model with an auxiliary task using monolingual data of three languages.
-
3 May 2021 1 repository listedThe presented datasets for event detection and headline selection are the first public Russian datasets for their tasks.
-
2 May 2020 1 repository listedBuilding a binary classifier that predicts an entailment relation between an article and its headline, we filter out untruthful instances from the supervision data.
-
8 Apr 2020 1 repository listedFurthermore, we propose a simple and effective method to mine the keyphrases of interest in the news article and build a first large-scale keyphrase-aware news headline corpus, which contains over 180K aligned triples…
-
4 Apr 2020 1 repository listedCurrent summarization systems only produce plain, factual headlines, but do not meet the practical needs of creating memorable titles to increase exposure.
-
6 Feb 2020 1 repository listedTo generate inspired headlines, we propose a novel framework called POpularity-Reinforced Learning for inspired Headline Generation (PORL-HG).
-
10 Sep 2019 1 repository listed
-
9 Sep 2019 1 repository listed
-
8 Jun 2019 1 repository listed
-
1 Jun 2019 1 repository listed
-
25 Apr 2019 1 repository listed
-
30 Aug 2018 1 repository listed
-
ComMer: a Framework for Compressing and Merging User Data for Personalization5 Jan 2025 0 repositories listed
-
Abstractive Summarization of Low resourced Nepali language using Multilingual Transformers29 Sep 2024 0 repositories listed
-
Creating Arabic LLM Prompts at Scale12 Aug 2024 0 repositories listed
-
Multilingual Fine-Grained News Headline Hallucination Detection22 Jul 2024 0 repositories listed
-
Why Would You Suggest That? Human Trust in Language Model Responses4 Jun 2024 0 repositories listed
-
Online Personalizing White-box LLMs Generation with Neural Bandits24 Apr 2024 0 repositories listed
-
Modeling Unified Semantic Discourse Structure for High-quality Headline Generation23 Mar 2024 0 repositories listed
-
27 Feb 2024 0 repositories listed
-
How to Generate Popular Post Headlines on Social Media?18 Sep 2023 0 repositories listed
-
HonestBait: Forward References for Attractive but Faithful Headline Generation26 Jun 2023 0 repositories listed
-
"Why is this misleading?": Detecting News Headline Hallucinations with Explanations12 Feb 2023 0 repositories listed
-
Automatic Generation of Factual News Headlines in Finnish5 Dec 2022 0 repositories listed
-
Grafting Pre-trained Models for Multimodal Headline Generation14 Nov 2022 0 repositories listed
-
Leveraging Key Information Modeling to Improve Less-Data Constrained News Headline Generation via Duality Fine-Tuning10 Oct 2022 0 repositories listed
-
Visual Subtitle Feature Enhanced Video Outline Generation24 Aug 2022 0 repositories listed
-
Effectiveness of Data Augmentation and Pretraining for Improving Neural Headline Generation in Low-Resource Settings1 Jun 2022 0 repositories listed
-
Updated Headline Generation: Creating Updated Summaries for Evolving News Stories1 May 2022 0 repositories listed
-
IndicNLG Benchmark: Multilingual Datasets for Diverse NLG Tasks in Indic Languages10 Mar 2022 0 repositories listed
-
HonestBait: Headline Generation via Faithful Forward Reference16 Nov 2021 0 repositories listed
-
Learning Non-Autoregressive Models from Search for Unsupervised Sentence Summarization16 Nov 2021 0 repositories listed
-
Few-Shot Text Generation with Natural Language Instructions1 Nov 2021 0 repositories listed
-
When a Computer Cracks a Joke: Automated Generation of Humorous Headlines17 Sep 2021 0 repositories listed
-
Improving Neural Language Processing with Named Entities1 Sep 2021 0 repositories listed
-
DeepTitle -- Leveraging BERT to generate Search Engine Optimized Headlines22 Jul 2021 0 repositories listed
-
Ad Headline Generation using Self-Critical Masked Language Model1 Jun 2021 0 repositories listed
-
MathBERT: A Pre-Trained Model for Mathematical Formula Understanding2 May 2021 0 repositories listed
-
Can Humor Prediction Datasets be used for Humor Generation? Humorous Headline Generation via Style Transfer1 Jul 2020 0 repositories listed
-
Evaluation Metrics for Headline Generation Using Deep Pre-Trained Embeddings1 May 2020 0 repositories listed
-
Importance-Aware Learning for Neural Headline Editing25 Nov 2019 0 repositories listed
-
Multiple News Headlines Generation using Page Metadata1 Oct 2019 0 repositories listed
-
HEvAS: Headline Evaluation and Analysis System1 Sep 2019 0 repositories listed
-
Multi-lingual Wikipedia Summarization and Title Generation On Low Resource Corpus1 Sep 2019 0 repositories listed
-
RANLP 2019 Multilingual Headline Generation Task Overview1 Sep 2019 0 repositories listed
-
Character n-gram Embeddings to Improve RNN Language Models13 Jun 2019 0 repositories listed
-
A Case Study on Neural Headline Generation for Editing Support1 Jun 2019 0 repositories listed
-
Headline Generation: Learning from Decomposable Document Titles17 Apr 2019 0 repositories listed
-
28 Mar 2019 0 repositories listed
-
A novel repetition normalized adversarial reward for headline generation19 Feb 2019 0 repositories listed
-
Self-Attentive Model for Headline Generation23 Jan 2019 0 repositories listed
-
Reducing Odd Generation from Neural Headline Generation1 Dec 2018 0 repositories listed
-
Frustratingly Easy Model Ensemble for Abstractive Summarization1 Oct 2018 0 repositories listed
-
Extractive Headline Generation Based on Learning to Rank for Community Question Answering1 Aug 2018 0 repositories listed
-
Source-side Prediction for Neural Headline Generation22 Dec 2017 0 repositories listed
-
Low-Resource Neural Headline Generation31 Jul 2017 0 repositories listed
-
Abstractive Headline Generation for Spoken Content by Attentive Recurrent Neural Networks with ASR Error Modeling26 Dec 2016 0 repositories listed
-
Neural Headline Generation on Abstract Meaning Representation1 Nov 2016 0 repositories listed
-
Topic Sensitive Neural Headline Generation20 Aug 2016 0 repositories listed
-
Neural Headline Generation with Sentence-wise Optimization7 Apr 2016 0 repositories listed
-
Event-Driven Headline Generation1 Jul 2015 0 repositories listed
-
HEADS: Headline Generation as Sequence Prediction Using an Abstract Feature-Rich Space1 May 2015 0 repositories listed
Syntology lines on 4 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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