paper-with-me

Papers

Do NLP Models Know Numbers? Probing Numeracy in Embeddings

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

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 vectors. Is this enough to capture numeracy? We begin by investigating the numerical reasoning capabilities of a state-of-the-art question answering model on the DROP dataset. We find this model excels on questions that require numerical reasoning, i.e., it already captures numeracy. To understand how this capability emerges, we probe token embedding methods (e.g., BERT, GloVe) on synthetic list maximum, number decoding, and addition tasks. A surprising degree of numeracy is naturally present in standard embeddings. For example, GloVe and word2vec accurately encode magnitude for numbers up to 1,000. Furthermore, character-level embeddings are even more precise---ELMo captures numeracy the best for all pre-trained methods---but BERT, which uses sub-word units, is less exact.

📄 PDF Abstract BibTeX arXiv:1909.07940

Code (1)

andrewschreiber/hs-math-nlp pytorch

Tasks

Question Answering

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Weight Decay 설명 없음
Residual Connection 설명 없음
Adam 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 $x$…
Attention 설명 없음
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…

Similar Papers 제목 키워드 기반

Exploring Numeracy in Word Embeddings

2019-07-01 · ACL 2019 7 · Aakanksha Naik, Ravich, Abhilasha er, Carolyn Rose 외

Word embeddings are now pervasive across NLP subfields as the de-facto method of forming text representataions. In this work, we show that existing embedding models are inadequate at constructing representations that cap…

Word Embeddings

Numeracy enhances the Literacy of Language Models

2021-11-01 · EMNLP 2021 11 · Avijit Thawani, Jay Pujara, Filip Ilievski

Specialized number representations in NLP have shown improvements on numerical reasoning tasks like arithmetic word problems and masked number prediction. But humans also use numeracy to make better sense of world concep…

PredictionSentence

Methods for Numeracy-Preserving Word Embeddings

2020-11-01 · EMNLP 2020 11 · Dhanasekar Sundararaman, Shijing Si, Vivek Subramanian, Guoyin Wang 외

Word embedding models are typically able to capture the semantics of words via the distributional hypothesis, but fail to capture the numerical properties of numbers that appear in the text. This leads to problems with n…

Question AnsweringWord Embeddings

Representing Numbers in NLP: a Survey and a Vision

2021-03-24 · NAACL 2021 4 · Avijit Thawani, Jay Pujara, Pedro A. Szekely, Filip Ilievski

NLP systems rarely give special consideration to numbers found in text. This starkly contrasts with the consensus in neuroscience that, in the brain, numbers are represented differently from words. We arrange recent NLP …

Survey

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…