paper-with-me

Papers

Rethinking Self-Supervision Objectives for Generalizable Coherence Modeling

2021-10-14 · ACL 2022 5 · Prathyusha Jwalapuram, Shafiq Joty, Xiang Lin

Given the claims of improved text generation quality across various pre-trained neural models, we consider the coherence evaluation of machine generated text to be one of the principal applications of coherence models that needs to be investigated. Prior work in neural coherence modeling has primarily focused on devising new architectures for solving the permuted document task. We instead use a basic model architecture and show significant improvements over state of the art within the same training regime. We then design a harder self-supervision objective by increasing the ratio of negative samples within a contrastive learning setup, and enhance the model further through automatic hard negative mining coupled with a large global negative queue encoded by a momentum encoder. We show empirically that increasing the density of negative samples improves the basic model, and using a global negative queue further improves and stabilizes the model while training with hard negative samples. We evaluate the coherence model on task-independent test sets that resemble real-world applications and show significant improvements in coherence evaluations of downstream tasks.

📄 PDF Abstract BibTeX arXiv:2110.07198

Code (0)

등록된 구현이 없습니다.

Tasks

Coherence EvaluationContrastive LearningText Generation

Methods 이 논문이 사용한 방법론

Test 설명 없음
Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Catching the Imposter: Self-Supervised Learning of Physical Coherence with Cross-Entity Feature Permutations

2026-08-14 · Aleksei Rozanov, Arvind Renganathan, Vipin Kumar arxiv

Scientific data often describe entities whose features are jointly governed by the laws of physics, yet existing self-supervised learning (SSL) objectives largely ignore this physical coherence. We introduce imposter, a …

Self-Supervised Learning

LaxMotion: Rethinking Supervision Granularity for 3D Human Motion Generation

2025-11-14 · Sheng Liu, Yuanzhi Liang, Sidan Du arxiv

Recent 3D human motion generation models demonstrate remarkable reconstruction accuracy yet struggle to generalize beyond training distributions. This limitation arises partly from the use of precise 3D supervision, whic…

MonoSelfRecon: Purely Self-Supervised Explicit Generalizable 3D Reconstruction of Indoor Scenes from Monocular RGB Views

2024-04-10 · Runfa Li, Upal Mahbub, Vasudev Bhaskaran, Truong Nguyen

Current monocular 3D scene reconstruction (3DR) works are either fully-supervised, or not generalizable, or implicit in 3D representation. We propose a novel framework - MonoSelfRecon that for the first time achieves exp…

3D Reconstruction3D Scene ReconstructionDepth EstimationNeRF

Rethinking Deep Clustering Paradigms: Self-Supervision Is All You Need

2025-03-05 · Amal Shaheena, Nairouz Mrabahb, Riadh Ksantinia, Abdulla Alqaddoumia

The recent advances in deep clustering have been made possible by significant progress in self-supervised and pseudo-supervised learning. However, the trade-off between self-supervision and pseudo-supervision can give ri…

AllClusteringDeep Clustering

Skip-Clip: Self-Supervised Spatiotemporal Representation Learning by Future Clip Order Ranking

2019-10-28 · Alaaeldin El-Nouby, Shuangfei Zhai, Graham W. Taylor, Joshua M. Susskind

Deep neural networks require collecting and annotating large amounts of data to train successfully. In order to alleviate the annotation bottleneck, we propose a novel self-supervised representation learning approach for…

Action RecognitionFuture predictionRepresentation LearningSelf-Supervised Action Recognition