Papers by Dongxiang Zhang

5 papers
Translating a Math Word Problem to a Expression Tree (D18-1)

Copied to clipboard

Challenge: Sequence-to-sequence (SEQ2SEQ) models have been successfully applied to automatic math word problem solving.
Approach: They propose an equation normalization method to normalize duplicated equations and propose an ensemble model to combine their advantages.
Outcome: The proposed model outperforms the previous state-of-the-art models on the math word problem solving.
Meta-Learning Adversarial Domain Adaptation Network for Few-Shot Text Classification (2021.findings-acl)

Copied to clipboard

Challenge: Existing approaches for few-shot text classification rely on exploitation of lexical features and distributional signatures on training data, while neglecting to strengthen the model's ability to adapt to new tasks.
Approach: They propose a meta-learning framework integrated with an adversarial domain adaptation network to improve the model's adaptive ability and generate high-quality text embedding for new classes.
Outcome: The proposed framework outperforms the state-of-the-art models on four datasets and shows clear superiority over existing models.
Incorporating Instructional Prompts into a Unified Generative Framework for Joint Multiple Intent Detection and Slot Filling (2022.coling-1)

Copied to clipboard

Challenge: Existing approaches to multiple intent detection and slot filling focus on task-specific components to capture the relationships between intents and slots.
Approach: They propose a Unified Generative framework that captures the relationships between intents and slots in an utterance and formulates the task as a question-answering problem.
Outcome: The proposed framework surpasses baselines on full-data and multi-intent benchmarks on 5-shot and 10-shot scenarios.
TLM: Token-Level Masking for Transformers (2023.emnlp-main)

Copied to clipboard

Challenge: Structured dropout approaches have been investigated to regularize the multi-head attention mechanism in Transformers.
Approach: They propose a new regularization scheme based on token-level rather than structure-level to reduce overfitting by manipulating the connections between tokens in the multi-head attention via masking.
Outcome: The proposed regularization scheme outperforms attention dropout and DropHead on 18 datasets and can establish a new record on the data-to-text benchmark Rotowire (18.93 BLEU).
Modeling Intra-Relation in Math Word Problems with Different Functional Multi-Head Attentions (P19-1)

Copied to clipboard

Challenge: Several deep learning models have been proposed for solving math word problems (MWPs) but their approaches to capturing features are not specifically designed for MWP.
Approach: They propose to use a group attention mechanism to extract global features, quantity-related features, quantities-pair features and question-related feature in MWPs.
Outcome: The proposed approach performs significantly better than previous state-of-the-art methods and boosts performance from 66.9% to 69.5% on Math23K with training-test split, from 65.8% to 66.99% on Math 23K with 5-fold cross-validation and from 69.99% to 76.1% on MAWPS.

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