45 citations · 101 across the 8 of their papers we have counts for
8 papers
Hashtag-Guided Low-Resource Tweet Classification
Shizhe Diao, Sedrick Scott Keh, Liangming Pan +3
Social media classification tasks (e.g., tweet sentiment analysis, tweet stance detection) are challenging because social media posts are typically short, informal, and ambiguous.…
Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Data
KaShun Shum, Shizhe Diao, Tong Zhang
Chain-of-thought (CoT) advances the reasoning abilities of large language models (LLMs) and achieves superior performance in complex reasoning tasks. However, most CoT studies rely…
Active Prompting with Chain-of-Thought for Large Language Models
Shizhe Diao, Pengcheng Wang, Yong Lin +3
The increasing scale of large language models (LLMs) brings emergent abilities to various complex tasks requiring reasoning, such as arithmetic and commonsense reasoning. It is kno…
Multilingual Word Sense Disambiguation with Unified Sense Representation
Ying Su, Hongming Zhang, Yangqiu Song +1
As a key natural language processing (NLP) task, word sense disambiguation (WSD) evaluates how well NLP models can understand the lexical semantics of words under specific contexts…
ZEN 2.0: Continue Training and Adaption for N-gram Enhanced Text Encoders
Yan Song, Tong Zhang, Yonggang Wang +1
Pre-trained text encoders have drawn sustaining attention in natural language processing (NLP) and shown their capability in obtaining promising results in different tasks. Recent…
Improving Constituency Parsing with Span Attention
Yuanhe Tian, Yan Song, Fei Xia +1
Constituency parsing is a fundamental and important task for natural language understanding, where a good representation of contextual information can help this task. N-grams, whic…
Keyphrase Generation with Cross-Document Attention
Shizhe Diao, Yan Song, Tong Zhang
Keyphrase generation aims to produce a set of phrases summarizing the essentials of a given document. Conventional methods normally apply an encoder-decoder architecture to generat…
ZEN: Pre-training Chinese Text Encoder Enhanced by N-gram Representations
Shizhe Diao, Jiaxin Bai, Yan Song +2
The pre-training of text encoders normally processes text as a sequence of tokens corresponding to small text units, such as word pieces in English and characters in Chinese. It om…