Math Word Problem Generation with Mathematical Consistency and Problem Context Constraints

Wang, Zichao; Lan, Andrew S.; Baraniuk, Richard G.

doi:10.18653/v1/2021.emnlp-main.484

Cited by 19 publications

(7 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Beyond the generation of the correct answer, transformer models are also able to create distractor answers, as needed for the generation of multiple choice questionnaires [42,43]. Bringing language models to mathematics education, sev-eral works discuss the automatic generation of math word problems [44,45,46], which combines the challenge of understanding equations and putting them into the appropriate context.…”

Section: Review Of Research Applying Large Languagementioning

confidence: 99%

ChatGPT for Good? On Opportunities and Challenges of Large Language Models for Education

Kasneci¹,

Seßler²,

Küchemann³

et al. 2023

Preprint

133

View full text Add to dashboard Cite

Large language models represent a significant advancement in the field of AI. The underlying technology is key to further innovations and, despite critical views and even bans within communities and regions, large language models are here to stay. This position paper presents the potential benefits and challenges of educational applications of large language models, from student and teacher perspectives. We briefly discuss the current state of large language models and their applications. We then highlight how these models can be used to create educational content, improve student engagement and interaction, and personalize learning experiences. With regard to challenges, we argue that large language models in education require teachers and learners to develop sets of competencies and literacies necessary to both understand the technology as well as their limitations and unexpected brittleness of such systems. In addition, a clear strategy within educational systems and a clear pedagogical approach with a strong focus on critical thinking and strategies for fact checking are required to integrate and take full advantage of large language models in learning settings and teaching curricula. Other challenges such as the potential bias in the output, the need for continuous human oversight, and the potential for misuse are not unique to the application of AI in education. But we believe that, if handled sensibly, these challenges can offer insights and opportunities in education scenarios to acquaint students early on with potential societal biases, criticalities, and risks of AI applications. We conclude with recommendations for how to address these challenges and ensure that such models are used in a responsible and ethical manner in education.

show abstract

Section: Review Of Research Applying Large Languagementioning

confidence: 99%

ChatGPT for Good? On Opportunities and Challenges of Large Language Models for Education

Kasneci¹,

Seßler²,

Küchemann³

et al. 2023

Preprint

133

View full text Add to dashboard Cite

show abstract

“…Language models can also be used in generating synthetic EHR data. PromptEHR uses prompt learning for conditional generation of synthetic data (Wang and Sun 2022). Different from previous methods, we model the logical associations between various types of medical events with multivisit health state inference.…”

Section: Synthetic Ehr Generationmentioning

confidence: 99%

“…We compare MSIC to mainstream synthetic EHR generation methods as baselines. For medical event synthesis, the baselines include: (1) LSTM+MLP is a straightforward sequential prediction model to yield event probabilities across multiple visits; (2) MedGAN (Choi et al 2017) is a pioneer in using GAN for synthetic EHR generation; (3) MedBGAN & MedWGAN (Baowaly et al 2019) take advantage of Boundary-seeking GAN (Hjelm et al 2018) and Wasserstein GAN (Adler and Lunz 2018) to improve the generation performance; (4) EVA (Biswal et al 2021) is a VAE-based model featuring a BiLSTM encoder and CNN decoder; (5) MTGAN (Lu et al 2023) is a time-series generation model via conditional GAN; and (6) PromptEHR (Wang and Sun 2022) employs prompt learning for conditional EHR generation.…”

Section: Experiments Experimental Setupmentioning

confidence: 99%

Collaborative Synthesis of Patient Records through Multi-Visit Health State Inference

Sun,

Lin,

Yan

2024

AAAI

View full text Add to dashboard Cite

Electronic health records (EHRs) have become the foundation of machine learning applications in healthcare, while the utility of real patient records is often limited by privacy and security concerns. Synthetic EHR generation provides an additional perspective to compensate for this limitation. Most existing methods synthesize new records based on real EHR data, without consideration of different types of events in EHR data, which cannot control the event combinations in line with medical common sense. In this paper, we propose MSIC, a Multi-visit health Status Inference model for Collaborative EHR synthesis to address these limitations. First, we formulate the synthetic EHR generation process as a probabilistic graphical model and tightly connect different types of events by modeling the latent health states. Then, we derive a health state inference method tailored for the multi-visit scenario to effectively utilize previous records to synthesize current and future records. Furthermore, we propose to generate medical reports to add textual descriptions for each medical event, providing broader applications for synthesized EHR data. For generating different paragraphs in each visit, we incorporate a multi-generator deliberation framework to collaborate the message passing of multiple generators and employ a two-phase decoding strategy to generate high-quality reports. Our extensive experiments on the widely used benchmarks, MIMIC-III and MIMIC-IV, demonstrate that MSIC advances state-of-the-art results on the quality of synthetic data while maintaining low privacy risks.

show abstract

“…MWP Generation: Early MWP generation methods are mostly template-based, including Answer Set Programming (ASP) (Polozov et al, 2015), schema and frame semantics (Singley and Bennett, 2002;Deane, 2003). With the development of deep learning framework, ; Wang et al (2021) generate problem text given equation templates and keywords, where the keywords are extracted from the golden MWP via heuristic rules. Their model is learned with Seq2seq in an end-to-end manner and integrates features of templates and keywords in the decoding phase.…”

Section: Related Workmentioning

confidence: 99%

DISK: Domain-constrained Instance Sketch for Math Word Problem Generation

Cao¹,

Zeng²,

Xu³

et al. 2022

Preprint

View full text Add to dashboard Cite

A math word problem (MWP) is a coherent narrative which reflects the underlying logic of math equations. Successful MWP generation can automate the writing of mathematics questions. Previous methods mainly generate MWP text based on inflexible pre-defined templates. In this paper, we propose a neural model for generating MWP text from math equations. Firstly, we incorporate a matching model conditioned on the domain knowledge to retrieve a MWP instance which is most consistent with the ground-truth, where the domain is a latent variable extracted with a domain summarizer. Secondly, by constructing a Quantity Cell Graph (QCG) from the retrieved MWP instance and reasoning over it, we improve the model's comprehension of real-world scenarios and derive a domainconstrained instance sketch to guide the generation. Besides, the QCG also interacts with the equation encoder to enhance the alignment between math tokens (e.g., quantities and variables) and MWP text. Experiments and empirical analysis on educational MWP set show that our model achieves impressive performance in both automatic evaluation metrics and human evaluation metrics. Equations: x = 6 * y ; (x + y) * 3= 147 Problem: Jane travels 6 times faster than mike. Traveling in opposite directions they are 147 miles apart after 3 hrs. Find their rates of travel. Equations: (1 -1/3 -9/20) * x = 245 Problem: At a local high school, 3/8 of the students are freshman. 1/4 are juniors. And 245 are seniors. Find the total number of students.

show abstract

Math Word Problem Generation with Mathematical Consistency and Problem Context Constraints

Cited by 19 publications

References 52 publications

ChatGPT for Good? On Opportunities and Challenges of Large Language Models for Education

ChatGPT for Good? On Opportunities and Challenges of Large Language Models for Education

Collaborative Synthesis of Patient Records through Multi-Visit Health State Inference

DISK: Domain-constrained Instance Sketch for Math Word Problem Generation

Contact Info

Product

Resources

About