Papers by Yuanmeng Zhang

7 papers
Contrastive Zero-Shot Learning for Cross-Domain Slot Filling with Adversarial Attack (2020.coling-main)

Copied to clipboard

Challenge: Existing approaches to zero-shot slot filling ignore constraints in the latent space and lack robustness.
Approach: They propose a Contrastive Zero-Shot Learning with Adversarial Attack method for slot filling . they propose to map slot value contextual representations to slot description representations .
Outcome: The proposed method outperforms state-of-the-art models under zero-shot and few-shot settings.
Can Multi-agent Help Disambiguation in Multi-domain Translation? (2026.findings-acl)

Copied to clipboard

Challenge: Existing multi-agent systems have shown strong potential for machine translation (MT) but their performance in multidomain translation remains unsatisfactory due to cross-domain word ambiguity .
Approach: They propose a multi-agent collaborative disambiguation framework for MDT that leverages the collaborative capabilities of LLMs for disambiguations.
Outcome: The proposed framework improves translation performance across multiple domains and improves disambiguation accuracy.
ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer (2021.acl-long)

Copied to clipboard

Challenge: Existing BERT-based pre-trained language models achieve high performance on many downstream tasks, but native derived sentence representations are collapsed and thus poor performance on semantic textual similarity (STS) tasks.
Approach: They propose a framework for self-supervised Sentence Representation Transfer that adopts contrastive learning to fine-tune BERT in an unsupervised way.
Outcome: The proposed framework improves on the BERT-derived representations by 8% on STS datasets and shows robustness in data scarcity scenarios.
Large-Scale Relation Learning for Question Answering over Knowledge Bases with Pre-trained Language Models (2021.emnlp-main)

Copied to clipboard

Challenge: Existing KBQA methods focus on the natural language but ignore textual information carried by the nodes and edges.
Approach: They propose to perform relation extraction, relation matching, and relation reasoning tasks to align the natural language expressions to the relations in the KB and reason over the missing connections.
Outcome: Experiments on WebQSP show that the proposed model outperforms baselines even when the KB is incomplete.
DMDTEval: An Evaluation and Analysis of LLMs on Disambiguation in Multi-domain Translation (2025.emnlp-main)

Copied to clipboard

Challenge: Currently, Large Language Models (LLMs) have achieved remarkable results in machine translation, but their performance in multidomain translation (MDT) is less satisfactory.
Approach: They propose to evaluate the disambiguation ability of Large Language Models in multi-domain translation . they construct a translation test set with multi- domain ambiguous word annotation .
Outcome: The proposed framework evaluates LLMs on disambiguation in multi-domain translation (DMDTEval) the results show that LLM's perform poorly in multidomain translation, highlighting ambiguity in translation.
CapOnImage: Context-driven Dense-Captioning on Image (2022.emnlp-main)

Copied to clipboard

Challenge: Existing image captioning systems generate narrative captions for images, which are spatially detached from the image in presentation.
Approach: They propose a task called captioning on image which generatesense captions at different locations of the image based on contextual information.
Outcome: The proposed model achieves the best results in both captioning accuracy and diversity aspects.
ICL: Iterative Continual Learning for Multi-domain Neural Machine Translation (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing studies have focused on learning domain knowledge from multiple domains, but task-specific parameters hinder mutual transfer of knowledge between new domains.
Approach: They propose an iterative Continual learning framework for multi-domain neural machine translation that leverages previously acquired domain knowledge.
Outcome: The proposed model outperforms baseline models on UM-Corpus and OPUS datasets.

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