Papers by Feifei Zhai

9 papers
Multi-Stage Pre-training Enhanced by ChatGPT for Multi-Scenario Multi-Domain Dialogue Summarization (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for dialogue summarization only apply to specific scenarios and domains.
Approach: They propose a pre-trained model specifically designed for multi-scenario multi-domain dialogue summarization.
Outcome: The proposed model significantly outperforms state-of-the-art models on three dialogue summarization datasets from different scenarios and domains.
A Compact and Language-Sensitive Multilingual Translation Method (P19-1)

Copied to clipboard

Challenge: Existing paradigms for multilingual neural machine translation do not make full use of language commonality and parameter sharing.
Approach: They propose a multilingual neural machine translation paradigm with one encoder-decoder model that makes full use of language commonality and parameter sharing.
Outcome: The proposed method outperforms strong standard multilingual translation systems on WMT and IWSLT datasets.
TROVE: A Challenge for Fine-Grained Text Provenance via Source Sentence Tracing and Relationship Classification (2025.acl-long)

Copied to clipboard

Challenge: Large language models have demonstrated great potential in natural language generation, but their widespread adoption has raised concerns regarding content reliability and accountability.
Approach: They propose a challenge to trace each sentence of a target text back to specific source sentences within potentially lengthy or multi-document inputs.
Outcome: The proposed challenge traces each sentence of a target text back to specific source sentences . the dataset includes 11 scenarios covering QA and summarization in english and Chinese .
Domain-aware and Co-adaptive Feature Transformation for Domain Adaption Few-shot Relation Extraction (2024.lrec-main)

Copied to clipboard

Challenge: Existing approaches to relation extraction focus on the source domain, which makes it difficult to accurately transfer useful knowledge to the target domain.
Approach: They propose a domain-aware and co-adaptive feature transformation approach to address these issues by leveraging the target domain distribution features to guide the domain-based feature transformations.
Outcome: The proposed method outperforms existing models and achieves state-of-the-art performance on a benchmark dataset.
CROP: Contextual Region-Oriented Visual Token Pruning (2025.emnlp-main)

Copied to clipboard

Challenge: Existing VLMs process entire images, leading to excessive visual tokens . redundant image information also introduces a large number of visual token, requiring much higher memory and computation in VLM.
Approach: They propose a framework to prune visual tokens using localization and pruning . they propose CROP to locate local image regions relevant to the query .
Outcome: The proposed framework outperforms existing visual token pruning methods on a wide range of tasks.
Investigating Hallucinations in Simultaneous Machine Translation: Knowledge Distillation Solution and Components Analysis (2025.naacl-long)

Copied to clipboard

Challenge: Existing methods to mitigate hallucinations in siMT generate fluency but unfaithful translation.
Approach: They propose a method that utilizes the OMT model to mitigate hallucinations in SiMT.
Outcome: The proposed method reduces hallucinations and improves the SiMT performance.
Pay More Attention to Images: Numerous Images-Oriented Multimodal Summarization (2025.naacl-long)

Copied to clipboard

Challenge: Existing multimodal summarization approaches struggle with scenarios involving multiple images as input.
Approach: They propose a task to generate multimodal summaries by integrating multiple images as input . they propose 'multimodal information evaluation' method that measures differences between generated summary and input based on multimodal input - and compares various methods .
Outcome: The proposed method correlates more closely with human judgments than five widely used metrics .
Improving the Transformer Translation Model with Document-Level Context (D18-1)

Copied to clipboard

Challenge: Existing models for document-level context translation ignore documentlevel context.
Approach: They propose a document-level context encoder to represent document- level context and integrate it into the Transformer model.
Outcome: Experiments on NIST Chinese-English and IWSLT French-English datasets show that the proposed translation model outperforms the Transformer model significantly.
Three Strategies to Improve One-to-Many Multilingual Translation (D18-1)

Copied to clipboard

Challenge: Existing studies show that one-to-many multilingual translation cannot perform on par with the individually trained models.
Approach: They propose to exploit unique initial states for target languages and language-dependent positional embeddings to create hidden cells of the encoder to achieve comparable or even better performance than individually trained models.
Outcome: The proposed methods achieve comparable or even better performance than the individually trained models.

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