paper-with-me

홈 › Papers

Jointly Improving Language Understanding and Generation with Quality-Weighted Weak Supervision of Automatic Labeling

2021-02-06 · EACL 2021 2 · Ernie Chang, Vera Demberg, Alex Marin

Neural natural language generation (NLG) and understanding (NLU) models are data-hungry and require massive amounts of annotated data to be competitive. Recent frameworks address this bottleneck with generative models that synthesize weak labels at scale, where a small amount of training labels are expert-curated and the rest of the data is automatically annotated. We follow that approach, by automatically constructing a large-scale weakly-labeled data with a fine-tuned GPT-2, and employ a semi-supervised framework to jointly train the NLG and NLU models. The proposed framework adapts the parameter updates to the models according to the estimated label-quality. On both the E2E and Weather benchmarks, we show that this weakly supervised training paradigm is an effective approach under low resource scenarios and outperforming benchmark systems on both datasets when 100% of training data is used.

📄 PDF Abstract BibTeX arXiv:2102.03551

Code (0)

등록된 구현이 없습니다.

Tasks

Text Generation

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Residual Connection 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Discriminative Fine-Tuning Discriminative Fine-Tuning is a fine-tuning strategy that is used for ULMFiT type models. Instead of using the same learning rate…
Multi-Head Attention 설명 없음
Adam 설명 없음

Similar Papers 제목 키워드 기반

IAD-Unify: A Region-Grounded Unified Model for Industrial Anomaly Segmentation, Understanding, and Generation

2026-04-14 · Haoyu Zheng, Tianwei Lin, Wei Wang, Zhuonan Wang 외 arxiv

Real-world industrial inspection requires not only localizing defects, but also explaining them in natural language and generating controlled defect edits. However, existing approaches fail to jointly support all three c…

HoliTok:A Coutinuous Holistic Tokenization with Robust Dual Capabilities of Speech Generation and Understanding

2026-05-28 · Bohan Li, Shi Lian, Hankun Wang, Yiwei Guo 외 arxiv

Unified speech foundation models require a holistic tokenization space that is both learnable by language models and decodable into high-quality waveforms. Existing speech tokenizers, however, often fail to satisfy these…

Speech Synthesis

Can LLMs understand LilyPond? A benchmark for symbolic music generation and understanding

2026-06-07 · Matteo Spanio, Mohammad Torabi, Andrea Poltronieri, Antonio Rodà arxiv

Symbolic music evaluation for large language models remains fragmented across representations, datasets, and metrics. We introduce LilyBench, a LilyPond-based benchmark that jointly evaluates symbolic music generation an…

Music Generation

A Generative Framework for Bidirectional Image-Report Understanding in Chest Radiography

2025-02-09 · Nicholas Evans, Stephen Baker, Miles Reed

The rapid advancements in large language models (LLMs) have unlocked their potential for multimodal tasks, where text and visual data are processed jointly. However, applying LLMs to medical imaging, particularly for che…

DiagnosticMultimodal Reasoning

PyraTok: Language-Aligned Pyramidal Tokenizer for Video Understanding and Generation

2026-01-22 · Onkar Susladkar, Tushar Prakash, Adheesh Juvekar, Kiet A. Nguyen 외 arxiv

Discrete video VAEs underpin modern text-to-video generation and video understanding systems, yet existing tokenizers typically learn visual codebooks at a single scale with limited vocabularies and shallow language supe…

Temporal Action LocalizationText-to-Video GenerationVideo ReconstructionVideo Segmentation