5 citations · 15 across the 11 of their papers we have counts for
11 papers
Self-Knowledge Guided Retrieval Augmentation for Large Language Models
Yile Wang, Peng Li, Maosong Sun +1
Large language models (LLMs) have shown superior performance without task-specific fine-tuning. Despite the success, the knowledge stored in the parameters of LLMs could still be i…
Prompt-Guided Retrieval Augmentation for Non-Knowledge-Intensive Tasks
Zhicheng Guo, Sijie Cheng, Yile Wang +2
Retrieval-augmented methods have received increasing attention to support downstream tasks by leveraging useful information from external resources. Recent studies mainly focus on…
CVT-SLR: Contrastive Visual-Textual Transformation for Sign Language Recognition with Variational Alignment
Jiangbin Zheng, Yile Wang, Cheng Tan +5
Sign language recognition (SLR) is a weakly supervised task that annotates sign videos as textual glosses. Recent studies show that insufficient training caused by the lack of larg…
Can Offline Reinforcement Learning Help Natural Language Understanding?
Ziqi Zhang, Yile Wang, Yue Zhang +1
Pre-training has been a useful method for learning implicit transferable knowledge and it shows the benefit of offering complementary features across different modalities. Recent w…
Pre-Training a Graph Recurrent Network for Language Representation
Yile Wang, Linyi Yang, Zhiyang Teng +2
Transformer-based pre-trained models have gained much advance in recent years, becoming one of the most important backbones in natural language processing. Recent work shows that t…
Using Context-to-Vector with Graph Retrofitting to Improve Word Embeddings
Jiangbin Zheng, Yile Wang, Ge Wang +5
Although contextualized embeddings generated from large-scale pre-trained models perform well in many tasks, traditional static embeddings (e.g., Skip-gram, Word2Vec) still play an…
YATO: Yet Another deep learning based Text analysis Open toolkit
Zeqiang Wang, Yile Wang, Jiageng Wu +2
We introduce YATO, an open-source, easy-to-use toolkit for text analysis with deep learning. Different from existing heavily engineered toolkits and platforms, YATO is lightweight…
Lost in Context? On the Sense-wise Variance of Contextualized Word Embeddings
Yile Wang, Yue Zhang
Contextualized word embeddings in language models have given much advance to NLP. Intuitively, sentential information is integrated into the representation of words, which can help…
Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learning
Yuncheng Hua, Yuan-Fang Li, Gholamreza Haffari +2
A compelling approach to complex question answering is to convert the question to a sequence of actions, which can then be executed on the knowledge base to yield the answer, aka t…
Does Chinese BERT Encode Word Structure?
Yile Wang, Leyang Cui, Yue Zhang
Contextualized representations give significantly improved results for a wide range of NLP tasks. Much work has been dedicated to analyzing the features captured by representative…
How Can BERT Help Lexical Semantics Tasks?
Yile Wang, Leyang Cui, Yue Zhang
Contextualized embeddings such as BERT can serve as strong input representations to NLP tasks, outperforming their static embeddings counterparts such as skip-gram, CBOW and GloVe.…