566 citations · 625 across the 23 of their papers we have counts for
24 papers
Where Should the Gaussians Go? Reusable Label-Aware Allocation for Budget-Constrained Gaussian Splatting of Cinematic CT
Bowen Xiang, Dingjie Su, Jon S. Heiselman +1
Anatomical labels help 3D Gaussian splatting preserve vessels in cinematic renderings of CT, but the representation is still found by optimising each patient's scene, where densifi…
Transfer Learning Enhanced Single-choice Decision for Multi-choice Question Answering
Chenhao Cui, Yufan Jiang, Shuangzhi Wu +1
Multi-choice Machine Reading Comprehension (MMRC) aims to select the correct answer from a set of options based on a given passage and question. The existing methods employ the pre…
SkillNet-X: A Multilingual Multitask Model with Sparsely Activated Skills
Zhangyin Feng, Yong Dai, Fan Zhang +6
Traditional multitask learning methods basically can only exploit common knowledge in task- or language-wise, which lose either cross-language or cross-task knowledge. This paper p…
Retrieval-Augmented Classification with Decoupled Representation
Xinnian Liang, Shuangzhi Wu, Hui Huang +3
Retrieval augmented methods have shown promising results in various classification tasks. However, existing methods focus on retrieving extra context to enrich the input, which is…
SCM: Enhancing Large Language Model with Self-Controlled Memory Framework
Bing Wang, Xinnian Liang, Jian Yang +6
Large Language Models (LLMs) are constrained by their inability to process lengthy inputs, resulting in the loss of critical historical information. To address this limitation, in…
Character, Word, or Both? Revisiting the Segmentation Granularity for Chinese Pre-trained Language Models
Xinnian Liang, Zefan Zhou, Hui Huang +5
Pretrained language models (PLMs) have shown marvelous improvements across various NLP tasks. Most Chinese PLMs simply treat an input text as a sequence of characters, and complete…
Enhancing Dialogue Summarization with Topic-Aware Global- and Local- Level Centrality
Xinnian Liang, Shuangzhi Wu, Chenhao Cui +3
Dialogue summarization aims to condense a given dialogue into a simple and focused summary text. Typically, both the roles' viewpoints and conversational topics change in the dialo…
FewFedWeight: Few-shot Federated Learning Framework across Multiple NLP Tasks
Weilong Dong, Xinwei Wu, Junzhuo Li +3
Massively multi-task learning with large language models has recently made substantial progress on few-shot generalization. However, this is usually performed in a centralized lear…
Swing Distillation: A Privacy-Preserving Knowledge Distillation Framework
Junzhuo Li, Xinwei Wu, Weilong Dong +3
Knowledge distillation (KD) has been widely used for model compression and knowledge transfer. Typically, a big teacher model trained on sufficient data transfers knowledge to a sm…
Contrastive Learning with Prompt-derived Virtual Semantic Prototypes for Unsupervised Sentence Embedding
Jiali Zeng, Yongjing Yin, Yufan Jiang +2
Contrastive learning has become a new paradigm for unsupervised sentence embeddings. Previous studies focus on instance-wise contrastive learning, attempting to construct positive…
UM4: Unified Multilingual Multiple Teacher-Student Model for Zero-Resource Neural Machine Translation
Jian Yang, Yuwei Yin, Shuming Ma +5
Most translation tasks among languages belong to the zero-resource translation problem where parallel corpora are unavailable. Multilingual neural machine translation (MNMT) enable…
An Efficient Coarse-to-Fine Facet-Aware Unsupervised Summarization Framework based on Semantic Blocks
Xinnian Liang, Jing Li, Shuangzhi Wu +4
Unsupervised summarization methods have achieved remarkable results by incorporating representations from pre-trained language models. However, existing methods fail to consider ef…
Modeling Paragraph-Level Vision-Language Semantic Alignment for Multi-Modal Summarization
Chenhao Cui, Xinnian Liang, Shuangzhi Wu +1
Most current multi-modal summarization methods follow a cascaded manner, where an off-the-shelf object detector is first used to extract visual features, then these features are fu…
Modeling Multi-Granularity Hierarchical Features for Relation Extraction
Xinnian Liang, Shuangzhi Wu, Mu Li +1
Relation extraction is a key task in Natural Language Processing (NLP), which aims to extract relations between entity pairs from given texts. Recently, relation extraction (RE) ha…
Task-guided Disentangled Tuning for Pretrained Language Models
Jiali Zeng, Yufan Jiang, Shuangzhi Wu +2
Pretrained language models (PLMs) trained on large-scale unlabeled corpus are typically fine-tuned on task-specific downstream datasets, which have produced state-of-the-art result…
Learning Confidence for Transformer-based Neural Machine Translation
Yu Lu, Jiali Zeng, Jiajun Zhang +2
Confidence estimation aims to quantify the confidence of the model prediction, providing an expectation of success. A well-calibrated confidence estimate enables accurate failure p…
SkillNet-NLU: A Sparsely Activated Model for General-Purpose Natural Language Understanding
Fan Zhang, Duyu Tang, Yong Dai +3
Prevailing deep models are single-purpose and overspecialize at individual tasks. However, when being extended to new tasks, they typically forget previously learned skills and lea…
Pretraining without Wordpieces: Learning Over a Vocabulary of Millions of Words
Zhangyin Feng, Duyu Tang, Cong Zhou +6
The standard BERT adopts subword-based tokenization, which may break a word into two or more wordpieces (e.g., converting "lossless" to "loss" and "less"). This will bring inconven…
Unsupervised Keyphrase Extraction by Jointly Modeling Local and Global Context
Xinnian Liang, Shuangzhi Wu, Mu Li +1
Embedding based methods are widely used for unsupervised keyphrase extraction (UKE) tasks. Generally, these methods simply calculate similarities between phrase embeddings and docu…
Improving Machine Reading Comprehension with Single-choice Decision and Transfer Learning
Yufan Jiang, Shuangzhi Wu, Jing Gong +5
Multi-choice Machine Reading Comprehension (MMRC) aims to select the correct answer from a set of options based on a given passage and question. Due to task specific of MMRC, it is…
Accelerating Transformer Decoding via a Hybrid of Self-attention and Recurrent Neural Network
Chengyi Wang, Shuangzhi Wu, Shujie Liu
Due to the highly parallelizable architecture, Transformer is faster to train than RNN-based models and popularly used in machine translation tasks. However, at inference time, eac…
Source Dependency-Aware Transformer with Supervised Self-Attention
Chengyi Wang, Shuangzhi Wu, Shujie Liu
Recently, Transformer has achieved the state-of-the-art performance on many machine translation tasks. However, without syntax knowledge explicitly considered in the encoder, incor…
Learning Unsupervised Word Mapping by Maximizing Mean Discrepancy
Pengcheng Yang, Fuli Luo, Shuangzhi Wu +3
Cross-lingual word embeddings aim to capture common linguistic regularities of different languages, which benefit various downstream tasks ranging from machine translation to trans…
Achieving Human Parity on Automatic Chinese to English News Translation
Hany Hassan, Anthony Aue, Chang Chen +21
Machine translation has made rapid advances in recent years. Millions of people are using it today in online translation systems and mobile applications in order to communicate acr…