Numeracy for Language Models: Evaluating and Improving their Ability to Predict Numbers (P18-1)
Copied to clipboard
| Challenge: | Numeracy is the ability to understand and work with numbers. |
| Approach: | They propose a neural architecture that uses a continuous probability density function to model numerals from an open vocabulary using hierarchical models. |
| Outcome: | The proposed model reduces errors by 18% and 54% on clinical and scientific datasets compared to the second best model for each dataset . |
Similar Papers
Numeracy enhances the Literacy of Language Models (2021.emnlp-main)
Copied to clipboard
| Challenge: | Specialized number representations have shown improvements on numerical reasoning tasks like arithmetic word problems and masked number prediction. |
| Approach: | They propose to use six different number encoders to improve masked word prediction by avoiding conflating nominal and ordinal number occurrences. |
| Outcome: | The proposed representations improve masked word prediction accuracy and generalize to contexts without annotated numbers. |
Evaluating Numeracy of Language Models as a Natural Language Inference Task (2025.findings-naacl)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have enhanced their capabilities to solve mathematical problems, but other aspects of numeracy remain underexplored. |
| Approach: | They propose to frame numeracy as a Natural Language Inference task to assess the models’ ability to understand both numbers and language contexts. |
| Outcome: | The proposed model outperforms smaller models in arithmetic tasks, indicating that mathematical reasoning cannot be generalized to other numeracy skills such as number comparison and normalization. |
Representing Numbers in NLP: a Survey and a Vision (2021.naacl-main)
Copied to clipboard
| Challenge: | Numeracy is an essential skill for language understanding since numbers are often interspersed in text. |
| Approach: | They propose a comprehensive taxonomy of tasks and methods to represent numbers in text . they synthesize best practices for representing numbers in texts and articulate a vision for holistic numeracy . |
| Outcome: | The proposed model synthesizes best practices for representing numbers in text . it argues that the model is more effective than other approaches . |
Learning Numeracy: A Simple Yet Effective Number Embedding Approach Using Knowledge Graph (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models for numeracy-intensive applications fail to learn numerability . existing models fail to handle numbers, resulting in performance problems . |
| Approach: | They propose a number embedding approach that embeds numbers into dimensional space . they construct a knowledge graph consisting of number entities and magnitude relations . |
| Outcome: | The proposed method is easy to implement and shows that it performs well on numeracy-related tasks. |
Do NLP Models Know Numbers? Probing Numeracy in Embeddings (D19-1)
Copied to clipboard
| Challenge: | Existing models cannot capture numeracy, but they can be useful for complex reasoning tasks. |
| Approach: | They investigate numerical reasoning capabilities of a question-answering model . they probe token embedding methods on synthetic list maximum, number decoding, and addition tasks. |
| Outcome: | The proposed model excels on questions that require numerical reasoning, i.e., it already captures numeracy. |
Do Language Models Understand Measurements? (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies on numerical reasoning over text (NRoT) tests PLMs to understand numbers in contexts where numbers are an integral part of the context. |
| Approach: | They propose a simple embedding strategy to better distinguish between numbers and units, which leads to a significant improvement in probing tasks. |
| Outcome: | The proposed model distinguishes between numbers and units, which leads to significant improvement in probing tasks. |
Exploring Numeracy in Word Embeddings (P19-1)
Copied to clipboard
| Challenge: | Existing word embeddings are inadequate at capturing numerical properties of numbers. |
| Approach: | They propose to use word embeddings to capture numerical properties of numbers . they hope to develop methods which better capture numeric properties . |
| Outcome: | The proposed models lack the ability to capture numeric properties of numbers, the authors show . their findings provide a starting point for the development of better models . |
Laying Anchors: Semantically Priming Numerals in Language Modeling (2024.findings-naacl)
Copied to clipboard
| Challenge: | Numeracy is the comprehension of numbers, and numerals are important for comprehension. |
| Approach: | They propose methods to semantically prime numerals by generating anchors governed by the distribution of numeral in any corpus. |
| Outcome: | The proposed methods perform better on numeracy tasks for both in-domain and out-domain numerals. |
Improving Numeracy by Input Reframing and Quantitative Pre-Finetuning Task (2023.findings-eacl)
Copied to clipboard
| Challenge: | Innumeracy is a problem in pretrained language models, but it is not discussed in this paper . Numerals are an indispensable part of narratives and provide much fine-grained information. |
| Approach: | They propose a method to solve innumeracy in pretrained language models by exploring the notation of numbers. |
| Outcome: | The proposed method improves performance in three benchmark datasets containing quantitative-related tasks. |
Numeracy-600K: Learning Numeracy for Detecting Exaggerated Information in Market Comments (P19-1)
Copied to clipboard
| Challenge: | Numeracy is the ability to predict the magnitude of a numeral at some specific position in a text description. |
| Approach: | They propose to use a dataset to test whether neural network models can learn numeracy . numerability is the ability to predict the magnitude of a numeral at some specific position in a text description. |
| Outcome: | The proposed task can predict the magnitude of a numeral at a specific position in a text description. |