Papers by Yukun Feng
One-class Text Classification with Multi-modal Deep Support Vector Data Description (2021.eacl-main)
Copied to clipboard
| Challenge: | Using multi-modal deep SVDD, we can build a much better description for target one-class data. |
| Approach: | They propose to extend uni-modal SVDD to multiple modal mSVDD and introduce a mechanism for incorporating negative supervision in the absence of real negative data. |
| Outcome: | The proposed model outperforms uni-modal SVDD and can get further improvements when negative supervision is incorporated. |
Automatic Document Selection for Efficient Encoder Pretraining (2022.emnlp-main)
Copied to clipboard
| Challenge: | Pretraining language models is expensive and data-intensive, but can it be improved? Several studies have found that directly pretraining on task data is more effective . |
| Approach: | They propose to automatically identify smaller yet domain-representative subsets by pretraining a model on a target domain. |
| Outcome: | The proposed method outperforms random selection on perplexity and downstream tasks with 20x less data and 3x fewer training iterations and 2x less estimated cloud compute cost. |
Learn To Remember: Transformer with Recurrent Memory for Document-Level Machine Translation (2022.findings-naacl)
Copied to clipboard
| Challenge: | Recent studies have shown that the effective use of contextual information between sentences can achieve better performance in document-level machine translation. |
| Approach: | They propose a recurrent memory unit to the Transformer to support the information exchange between the sentence and previous context. |
| Outcome: | The proposed model outperforms the previous work on TED and News by 0.91 s-BLEU and 1.49 d-BLUE on average. |
Practical, Efficient, and Customizable Active Learning for Named Entity Recognition in the Digital Humanities (N19-1)
Copied to clipboard
Alexander Erdmann, David Joseph Wrisley, Benjamin Allen, Christopher Brown, Sophie Cohen-Bodénès, Micha Elsner, Yukun Feng, Brian Joseph, Béatrice Joyeux-Prunel, Marie-Catherine de Marneffe
| Challenge: | Scholars in interdisciplinary fields like the Digital Humanities are increasingly interested in semantic annotation of specialized corpora. |
| Approach: | They propose an active learning solution for named entity recognition that maximizes a custom model’s improvement per additional unit of manual annotation. |
| Outcome: | The proposed model reduces required annotation by 20-60% and outperforms a competitive active learning baseline. |
Fusing Label Embedding into BERT: An Efficient Improvement for Text Classification (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to improve text classification performance of pre-trained models have been used to improve their performance. |
| Approach: | They propose a method for improving BERT's performance by using a label embedding technique while keeping almost the same computational cost. |
| Outcome: | The proposed method improves BERT's performance on six text classification benchmark datasets while keeping almost the same computational cost. |
Enhancing Large Vision-Language Models with Ultra-Detailed Image Caption Generation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing pipelines for generating high-quality, ultra-detailed image captions are limited by the scarcity of image caption data. |
| Approach: | They propose a pipeline for generating high-quality, ultra-detailed image captions that integrates both pre-processing and post-processor stages. |
| Outcome: | The proposed pipeline improves LVLMs' perception and cognitive abilities across multiple vision-language benchmarks. |
FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge Graphs (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for retrieval-augmented generation struggle with a trade-off between flexibility and retrieval quality. |
| Approach: | They propose a flexible modular KG-RAG framework that uses query text instead of KGs . they propose to use query text to infer the structural information of reasoning paths . |
| Outcome: | The proposed method achieves state-of-the-art performance with high efficiency and low resource consumption. |
The NLP Task Effectiveness of Long-Range Transformers (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing benchmarks on long-range attention models have not been sufficient to develop efficient Transformers and their practical application on complex NLP tasks. |
| Approach: | They propose to benchmark 7 Transformer variants on 5 difficult NLP tasks and 7 datasets to examine their capacity for long-range attention. |
| Outcome: | The proposed models have advantages on content selection and query-guided decoding, but they come with previously unrecognized drawbacks such as insufficient attention to distant tokens and accumulated approximation error. |
VIEWS: Entity-Aware News Video Captioning (2024.emnlp-main)
Copied to clipboard
Hammad Ayyubi, Tianqi Liu, Arsha Nagrani, Xudong Lin, Mingda Zhang, Anurag Arnab, Feng Han, Yukun Zhu, Xuande Feng, Kevin Zhang, Jialu Liu, Shih-Fu Chang
| Challenge: | Existing video captioning benchmarks and models produce generic captions for videos that lack specific identification of individuals, locations, or organizations. |
| Approach: | They propose a task of directly summarizing news videos into captions that are entity-aware . they validate the effectiveness of their approach across three video captioning models . |
| Outcome: | The proposed approach is effective across three video captioning models. |
Toward the Limitation of Code-Switching in Cross-Lingual Transfer (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies have shown the success of multilingual pretrained models for cross-lingual knowledge transfer. |
| Approach: | They propose to make code-switched sentences replace tokens from multiple languages so they are grammatically consistent . they also consider the similarity between context and the switched tokens to ensure that the newly substituted sentences are grammatically consistent - a limitation that could affect inference . |
| Outcome: | The proposed method outperforms the mBERT and original code-switching method on cross-lingual POS and Named-Entity-Recognition tasks on 30+ languages. |
Efficient Entity Embedding Construction from Type Knowledge for BERT (2022.findings-aacl)
Copied to clipboard
| Challenge: | Existing work has shown advantages of incorporating knowledge graphs (KGs) into BERT for various NLP tasks. |
| Approach: | They propose to integrate knowledge graphs into BERT to train entity embeddings to include rich information of factual knowledge. |
| Outcome: | The proposed models perform very well when combined with context. |
SkewRoute: Training-Free LLM Routing for Knowledge Graph Retrieval-Augmented Generation via Score Skewness of Retrieved Context (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models incur high inference costs during deployment, causing hallucination . no dedicated routing methods exist for RAG, and existing training-based routers face challenges scaling to this domain . |
| Approach: | They propose a plug-and-play routing framework that optimizes performance and cost . the framework delivers over 3x higher routing effectiveness while reducing runtime to less than 0.001x . |
| Outcome: | The proposed framework delivers over 3x higher routing effectiveness while reducing runtime to less than 0.001x compared to existing methods. |
A Simple and Effective Usage of Word Clusters for CBOW Model (2020.aacl-main)
Copied to clipboard
| Challenge: | Existing word clustering algorithms can be used to obtain word embeddings without additional language resources. |
| Approach: | They propose to replace infrequent input and output words with clusters to produce word embeddings. |
| Outcome: | The proposed method produces embeddings of frequent words and small amount of cluster embeddables, which can be fine-tuned on downstream tasks. |