Papers by Yanna Ma

4 papers
Multi-View Reasoning: Consistent Contrastive Learning for Math Word Problem (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for generating complex semantics and diverse equations are limited by a fixed view.
Approach: They propose a multi-view consistent contrastive learning approach that decouples human reasoning into two independent but consistent views.
Outcome: The proposed approach significantly outperforms existing baselines on complex problems on multiple languages.
An Expression Tree Decoding Strategy for Mathematical Equation Generation (2023.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to generate mathematical equations from natural language ignore parallel or dependent relations between math expressions.
Approach: They propose to integrate tree structure into the expression-level generation and advocate an expression tree decoding strategy.
Outcome: The proposed method outperforms baseline methods for generating mathematical equations from natural language.
Inferring from Logits: Exploring Best Practices for Decoding-Free Generative Candidate Selection (2025.acl-long)

Copied to clipboard

Challenge: Existing work has been using decoding-free candidate selection methods to obtain candidate probability from initial output logits over vocabulary.
Approach: They propose to evaluate a set of tasks using decoding-free candidate selection methods on a comprehensive set of questions.
Outcome: The proposed methods are evaluated on a set of tasks including five multiple-choice QA tasks with a small candidate pool and four clinical decision tasks with 10k+ options.
Multimodal Self-Instruct: Synthetic Abstract Image and Visual Reasoning Instruction Using Language Model (2024.emnlp-main)

Copied to clipboard

Challenge: Using large language models, large multimodal models struggle with basic tasks like reading time from a clock and planning a route using a road map.
Approach: They propose a multimodal self-instruct that synthesizes massive abstract images and visual reasoning instructions.
Outcome: The proposed model synthesizes 11,193 abstract images and reasoning instructions across eight visual scenarios.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations