49 citations · 72 across the 12 of their papers we have counts for
12 papers
ThinK: Thinner Key Cache by Query-Driven Pruning
Yuhui Xu, Zhanming Jie, Hanze Dong +6
Large Language Models (LLMs) have revolutionized the field of natural language processing, achieving unprecedented performance across a variety of applications. However, their incr…
Design of Chain-of-Thought in Math Problem Solving
Zhanming Jie, Trung Quoc Luong, Xinbo Zhang +2
Chain-of-Thought (CoT) plays a crucial role in reasoning for math problem solving. We conduct a comprehensive examination of methods for designing CoT, comparing conventional natur…
Leveraging Training Data in Few-Shot Prompting for Numerical Reasoning
Zhanming Jie, Wei Lu
Chain-of-thought (CoT) prompting with large language models has proven effective in numerous natural language processing tasks, but designing prompts that generalize well to divers…
Sequence-to-Sequence Pre-training with Unified Modality Masking for Visual Document Understanding
Shuwei Feng, Tianyang Zhan, Zhanming Jie +2
This paper presents GenDoc, a general sequence-to-sequence document understanding model pre-trained with unified masking across three modalities: text, image, and layout. The propo…
Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extraction
Zhanming Jie, Jierui Li, Wei Lu
Solving math word problems requires deductive reasoning over the quantities in the text. Various recent research efforts mostly relied on sequence-to-sequence or sequence-to-tree m…
To be Closer: Learning to Link up Aspects with Opinions
Yuxiang Zhou, Lejian Liao, Yang Gao +2
Dependency parse trees are helpful for discovering the opinion words in aspect-based sentiment analysis (ABSA). However, the trees obtained from off-the-shelf dependency parsers ar…
Better Feature Integration for Named Entity Recognition
Lu Xu, Zhanming Jie, Wei Lu +1
It has been shown that named entity recognition (NER) could benefit from incorporating the long-distance structured information captured by dependency trees. We believe this is bec…
ENT-DESC: Entity Description Generation by Exploring Knowledge Graph
Liying Cheng, Dekun Wu, Lidong Bing +4
Previous works on knowledge-to-text generation take as input a few RDF triples or key-value pairs conveying the knowledge of some entities to generate a natural language descriptio…
Dependency-Guided LSTM-CRF for Named Entity Recognition
Zhanming Jie, Wei Lu
Dependency tree structures capture long-distance and syntactic relationships between words in a sentence. The syntactic relations (e.g., nominal subject, object) can potentially in…
Efficient Dependency-Guided Named Entity Recognition
Zhanming Jie, Aldrian Obaja Muis, Wei Lu
Named entity recognition (NER), which focuses on the extraction of semantically meaningful named entities and their semantic classes from text, serves as an indispensable component…
Dependency-based Hybrid Trees for Semantic Parsing
Zhanming Jie, Wei Lu
We propose a novel dependency-based hybrid tree model for semantic parsing, which converts natural language utterance into machine interpretable meaning representations. Unlike pre…
Matrix Product Operators for Sequence to Sequence Learning
Chu Guo, Zhanming Jie, Wei Lu +1
The method of choice to study one-dimensional strongly interacting many body quantum systems is based on matrix product states and operators. Such method allows to explore the most…