paper-with-me

홈 › Papers

NumGPT: Improving Numeracy Ability of Generative Pre-trained Models

2021-09-07 · Zhihua Jin, Xin Jiang, Xingbo Wang, Qun Liu, Yong Wang, Xiaozhe Ren, Huamin Qu

Existing generative pre-trained language models (e.g., GPT) focus on modeling the language structure and semantics of general texts. However, those models do not consider the numerical properties of numbers and cannot perform robustly on numerical reasoning tasks (e.g., math word problems and measurement estimation). In this paper, we propose NumGPT, a generative pre-trained model that explicitly models the numerical properties of numbers in texts. Specifically, it leverages a prototype-based numeral embedding to encode the mantissa of the number and an individual embedding to encode the exponent of the number. A numeral-aware loss function is designed to integrate numerals into the pre-training objective of NumGPT. We conduct extensive experiments on four different datasets to evaluate the numeracy ability of NumGPT. The experiment results show that NumGPT outperforms baseline models (e.g., GPT and GPT with DICE) on a range of numerical reasoning tasks such as measurement estimation, number comparison, math word problems, and magnitude classification. Ablation studies are also conducted to evaluate the impact of pre-training and model hyperparameters on the performance.

📄 PDF Abstract BibTeX arXiv:2109.03137

Code (0)

등록된 구현이 없습니다.

Tasks

Math

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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…
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 $x$…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
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…
Linear Warmup With Cosine Annealing Linear Warmup With Cosine Annealing is a learning rate schedule where we increase the learning rate linearly for $n$ updates and then anneal according to a cosine schedule…

Similar Papers 제목 키워드 기반

Do NLP Models Know Numbers? Probing Numeracy in Embeddings

2019-09-17 · IJCNLP 2019 11 · Eric Wallace, Yizhong Wang, Sujian Li, Sameer Singh 외

The ability to understand and work with numbers (numeracy) is critical for many complex reasoning tasks. Currently, most NLP models treat numbers in text in the same way as other tokens---they embed them as distributed v…

Question Answering

Investigating Numeracy Learning Ability of a Text-to-Text Transfer Model

2021-09-10 · Findings (EMNLP) 2021 11 · Kuntal Kumar Pal, Chitta Baral

The transformer-based pre-trained language models have been tremendously successful in most of the conventional NLP tasks. But they often struggle in those tasks where numerical understanding is required. Some possible r…

Transfer Learning

Arithmetic-Based Pretraining -- Improving Numeracy of Pretrained Language Models

2022-05-13 · Dominic Petrak, Nafise Sadat Moosavi, Iryna Gurevych

State-of-the-art pretrained language models tend to perform below their capabilities when applied out-of-the-box on tasks that require understanding and working with numbers. Recent work suggests two main reasons for thi…

Contrastive LearningReading ComprehensionTable-to-Text GenerationText Generation

Masked Measurement Prediction: Learning to Jointly Predict Quantities and Units from Textual Context

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Physical measurements constitute a large portion of numbers in academic papers, engineering reports, and web tables. Current benchmarks fall short of properly evaluating numeracy of pretrained language models on measurem…

Numeracy-600K: Learning Numeracy for Detecting Exaggerated Information in Market Comments

2019-07-01 · ACL 2019 7 · Chung-Chi Chen, Hen-Hsen Huang, Hiroya Takamura, Hsin-Hsi Chen

In this paper, we attempt to answer the question of whether neural network models can learn numeracy, which is the ability to predict the magnitude of a numeral at some specific position in a text description. A large be…

Position