Papers by Tingting Ma

8 papers
Disentangling Reasoning Capabilities from Language Models with Compositional Reasoning Transformers (2023.findings-acl)

Copied to clipboard

Challenge: ReasonFormer is a unified reasoning framework for complex decision-making . it is based on the dual-process theory of cognitive science, where two cognitive systems interact to form a whole reasoning process.
Approach: They propose a unified reasoning framework that mirrors the modular reasoning process of humans . they decouple the representation module and the reasoning modules to capture different levels of cognition .
Outcome: The proposed framework shows that humans can perform better in complex decision-making tasks.
iMOVE : Instance-Motion-Aware Video Understanding (2025.findings-acl)

Copied to clipboard

Challenge: Recent advances in Video Large Language Models have led to rapid development, significantly enhancing the capture of overall video semantics and achieving remarkable performance in general video understanding tasks.
Approach: They propose a large-scale instance-motion-aware video instruction-tuning dataset iMOVE that utilizes Event-awful Spatiotemporal Efficient Modeling to retain informative instance spatiotemporal motion details while maintaining computational efficiency.
Outcome: The proposed model excels in video temporal understanding and general video understanding.
TIARA: Multi-grained Retrieval for Robust Question Answering over Large Knowledge Base (2022.emnlp-main)

Copied to clipboard

Challenge: KBQA is a challenging area for pre-trained language models due to its extensive space and complexity.
Approach: They propose a model that uses multi-grained retrieval to focus on most relevant KB contexts . constrained decoding is used to control output space and reduce generation errors .
Outcome: The proposed model outperforms existing models on GrailQA and WebQuestionsSP.
On the Effectiveness of Sentence Encoding for Intent Detection Meta-Learning (2022.naacl-main)

Copied to clipboard

Challenge: Recent studies on few-shot intent detection have attempted to formulate the task as a meta-learning problem.
Approach: They propose to modify a few-shot intent detection task to produce a non-trivially strong performance without further domain-specific adaptation.
Outcome: The proposed model improves on the prototypical network variants with task-specific fine-tuning.
CoLaDa: A Collaborative Label Denoising Framework for Cross-lingual Named Entity Recognition (2023.acl-long)

Copied to clipboard

Challenge: Existing approaches to named entity recognition (NER) are limited by the cost of labeling and labeling, especially for low-resource languages.
Approach: They propose a model-collaboration-based denoising scheme that enables models trained on different data sources to collaboratively denoise pseudo labels used by each other.
Outcome: The proposed framework achieves superior results on benchmark datasets and can generalize to distant languages.
Bridging the Editing Gap in LLMs: FineEdit for Precise and Targeted Text Modifications (2025.findings-emnlp)

Copied to clipboard

Challenge: a recent study shows that large language models can perform precise text editing tasks.
Approach: InstrEditBench is a benchmark dataset that compares 30,000 structured editing tasks . experimental evaluations show FineEdit outperforms state-of-the-art models .
Outcome: The proposed model outperforms state-of-the-art models on single-turn edits and mistral-7B-OpenOrca on direct edits.
Decomposed Meta-Learning for Few-Shot Named Entity Recognition (2022.findings-acl)

Copied to clipboard

Challenge: Named entity recognition systems aim at recognizing unseen entity types based on a few labeled examples.
Approach: They propose a decomposed meta-learning approach to solve few-shot span detection and few- shot entity typing problems by introducing a model-agnostic meta-loop algorithm.
Outcome: The proposed approach achieves superior performance over prior methods on benchmarks.
Issues with Entailment-based Zero-shot Text Classification (2021.acl-short)

Copied to clipboard

Challenge: Pre-trained BERT models with no fine-tuning can yield competitive performance against BERT fine- tuned for NLI.
Approach: They propose to use any target label into a sentence of hypothesis and verify whether it could be entailed by the input.
Outcome: The proposed models perform better than models fine-tuned for BERT, but the results are in general negative.

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