41 citations · 59 across the 9 of their papers we have counts for
7 papers · 1 filter
PERT: A New Solution to Pinyin to Character Conversion Task
Jinghui Xiao, Qun Liu, Xin Jiang +3
Pinyin to Character conversion (P2C) task is the key task of Input Method Engine (IME) in commercial input software for Asian languages, such as Chinese, Japanese, Thai language an…
Pre-training Language Model Incorporating Domain-specific Heterogeneous Knowledge into A Unified Representation
Hongyin Zhu, Hao Peng, Zhiheng Lyu +3
Existing technologies expand BERT from different perspectives, e.g. designing different pre-training tasks, different semantic granularities, and different model architectures. Few…
An Approach to Improve Robustness of NLP Systems against ASR Errors
Tong Cui, Jinghui Xiao, Liangyou Li +2
Speech-enabled systems typically first convert audio to text through an automatic speech recognition (ASR) model and then feed the text to downstream natural language processing (N…
PPKE: Knowledge Representation Learning by Path-based Pre-training
Bin He, Di Zhou, Jing Xie +3
Entities may have complex interactions in a knowledge graph (KG), such as multi-step relationships, which can be viewed as graph contextual information of the entities. Traditional…
KgPLM: Knowledge-guided Language Model Pre-training via Generative and Discriminative Learning
Bin He, Xin Jiang, Jinghui Xiao +1
Recent studies on pre-trained language models have demonstrated their ability to capture factual knowledge and applications in knowledge-aware downstream tasks. In this work, we pr…
HyperText: Endowing FastText with Hyperbolic Geometry
Yudong Zhu, Di Zhou, Jinghui Xiao +3
Natural language data exhibit tree-like hierarchical structures such as the hypernym-hyponym relations in WordNet. FastText, as the state-of-the-art text classifier based on shallo…
Integrating Graph Contextualized Knowledge into Pre-trained Language Models
Bin He, Di Zhou, Jinghui Xiao +4
Complex node interactions are common in knowledge graphs, and these interactions also contain rich knowledge information. However, traditional methods usually treat a triple as a t…