paper-with-me

홈 › Papers

LUNA: Language Understanding with Number Augmentations on Transformers via Number Plugins and Pre-training

2022-12-06 · Hongwei Han, Jialiang Xu, Mengyu Zhou, Yijia Shao, Shi Han, Dongmei Zhang

Transformers are widely used in NLP tasks. However, current approaches to leveraging transformers to understand language expose one weak spot: Number understanding. In some scenarios, numbers frequently occur, especially in semi-structured data like tables. But current approaches to rich-number tasks with transformer-based language models abandon or lose some of the numeracy information - e.g., breaking numbers into sub-word tokens - which leads to many number-related errors. In this paper, we propose the LUNA framework which improves the numerical reasoning and calculation capabilities of transformer-based language models. With the number plugin of NumTok and NumBed, LUNA represents each number as a whole to model input. With number pre-training, including regression loss and model distillation, LUNA bridges the gap between number and vocabulary embeddings. To the best of our knowledge, this is the first work that explicitly injects numeracy capability into language models using Number Plugins. Besides evaluating toy models on toy tasks, we evaluate LUNA on three large-scale transformer models (RoBERTa, BERT, TabBERT) over three different downstream tasks (TATQA, TabFact, CrediTrans), and observe the performances of language models are constantly improved by LUNA. The augmented models also improve the official baseline of TAT-QA (EM: 50.15 -> 59.58) and achieve SOTA performance on CrediTrans (F1 = 86.17).

📄 PDF Abstract BibTeX arXiv:2212.02691

Code (1)

zmy/luna 공식 구현 jax

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Multi-Head Attention 설명 없음
Attention 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Weight Decay 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Similar Papers 제목 키워드 기반

LUNA: A Framework for Language Understanding and Naturalness Assessment

2024-01-09 · Marat Saidov, Aleksandra Bakalova, Ekaterina Taktasheva, Vladislav Mikhailov 외

The evaluation of Natural Language Generation (NLG) models has gained increased attention, urging the development of metrics that evaluate various aspects of generated text. LUNA addresses this challenge by introducing a…

nlg evaluationText Generation

Enhancing Transformers without Self-supervised Learning: A Loss Landscape Perspective in Sequential Recommendation

2023-08-20 · Vivian Lai, Huiyuan Chen, Chin-Chia Michael Yeh, Minghua Xu 외

Transformer and its variants are a powerful class of architectures for sequential recommendation, owing to their ability of capturing a user's dynamic interests from their past interactions. Despite their success, Transf…

Self-Supervised LearningSequential Recommendation

Secure and Robust Communications for Cislunar Space Networks

2023-10-15 · Selen Gecgel Cetin, Gunes Karabulut Kurt, Angeles Vazquez-Castro

There is no doubt that the Moon has become the center of interest for commercial and international actors. Over the past decade, the number of planned long-term missions has increased dramatically. This makes the establi…

LUNA: Linear Universal Neural Attention with Generalization Guarantees

2025-12-08 · Ashkan Shahbazi, Ping He, Ali Abbasi, Yikun Bai 외 arxiv

Scaling attention faces a critical bottleneck: the $\mathcal{O}(n^2)$ quadratic computational cost of softmax attention, which limits its application in long-sequence domains. While linear attention mechanisms reduce thi…

Computational Efficiency

CERT: Contrastive Self-supervised Learning for Language Understanding

2020-05-16 · Hongchao Fang, Sicheng Wang, Meng Zhou, Jiayuan Ding 외

Pretrained language models such as BERT, GPT have shown great effectiveness in language understanding. The auxiliary predictive tasks in existing pretraining approaches are mostly defined on tokens, thus may not be able …

Natural Language UnderstandingSelf-Supervised LearningSentenceTranslation