Guangyi Lv
YOU?
Author Swipe
View article: Evaluating and Improving Robustness in Large Language Models: A Survey and Future Directions
Evaluating and Improving Robustness in Large Language Models: A Survey and Future Directions Open
Large Language Models (LLMs) have gained enormous attention in recent years due to their capability of understanding and generating natural languages. With the rapid development and wild-range applications (e.g., Agents, Embodied Intellige…
View article: Description-Enhanced Label Embedding Contrastive Learning for Text Classification
Description-Enhanced Label Embedding Contrastive Learning for Text Classification Open
Text Classification is one of the fundamental tasks in natural language processing, which requires an agent to determine the most appropriate category for input sentences. Recently, deep neural networks have achieved impressive performance…
View article: LadRa-Net: Locally Aware Dynamic Reread Attention Net for Sentence Semantic Matching
LadRa-Net: Locally Aware Dynamic Reread Attention Net for Sentence Semantic Matching Open
Sentence semantic matching requires an agent to determine the semantic relation between two sentences, which is widely used in various natural language tasks, such as Natural Language Inference (NLI), Paraphrase Identification (PI), and so…
View article: DeepME: Deep Mixture Experts for Large-scale Image Classification
DeepME: Deep Mixture Experts for Large-scale Image Classification Open
Although deep learning has demonstrated its outstanding performance on image classification, most well-known deep networks make efforts to optimize both their structures and their node weights for recognizing fewer (e.g., no more than 1000…
View article: DGA-Net Dynamic Gaussian Attention Network for Sentence Semantic Matching
DGA-Net Dynamic Gaussian Attention Network for Sentence Semantic Matching Open
Sentence semantic matching requires an agent to determine the semantic relation between two sentences, where much recent progress has been made by the advancement of representation learning techniques and inspiration of human behaviors. Am…
View article: Making the Relation Matters: Relation of Relation Learning Network for Sentence Semantic Matching
Making the Relation Matters: Relation of Relation Learning Network for Sentence Semantic Matching Open
Sentence semantic matching is one of the fundamental tasks in natural language processing, which requires an agent to determine the semantic relation among input sentences. Recently, deep neural networks have achieved impressive performanc…
View article: Detecting Domain Polarity-Changes of Words in a Sentiment Lexicon
Detecting Domain Polarity-Changes of Words in a Sentiment Lexicon Open
Sentiment lexicons are instrumental for sentiment analysis.One can use a set of sentiment words provided in a sentiment lexicon and a lexicon-based classifier to perform sentiment analysis.One major issue with this approach is that many se…
View article: R$^2$-Net: Relation of Relation Learning Network for Sentence Semantic Matching
R$^2$-Net: Relation of Relation Learning Network for Sentence Semantic Matching Open
Sentence semantic matching is one of the fundamental tasks in natural language processing, which requires an agent to determine the semantic relation among input sentences. Recently, deep neural networks have achieved impressive performanc…
View article: Detecting Domain Polarity-Changes of Words in a Sentiment Lexicon
Detecting Domain Polarity-Changes of Words in a Sentiment Lexicon Open
Sentiment lexicons are instrumental for sentiment analysis. One can use a set of sentiment words provided in a sentiment lexicon and a lexicon-based classifier to perform sentiment classification. One major issue with this approach is that…
View article: Deep Technology Tracing for High-Tech Companies
Deep Technology Tracing for High-Tech Companies Open
Technological change and innovation are vitally important, especially for\nhigh-tech companies. However, factors influencing their future research and\ndevelopment (R&D) trends are both complicated and various, leading it a quite\ndifficul…
View article: DRr-Net: Dynamic Re-Read Network for Sentence Semantic Matching
DRr-Net: Dynamic Re-Read Network for Sentence Semantic Matching Open
Sentence semantic matching requires an agent to determine the semantic relation between two sentences, which is widely used in various natural language tasks such as Natural Language Inference (NLI) and Paraphrase Identification (PI). Amon…
View article: Skeptical Deep Learning with Distribution Correction
Skeptical Deep Learning with Distribution Correction Open
Recently deep neural networks have been successfully used for various classification tasks, especially for problems with massive perfectly labeled training data. However, it is often costly to have large-scale credible labels in real-world…
View article: A Context-Enriched Neural Network Method for Recognizing Lexical Entailment
A Context-Enriched Neural Network Method for Recognizing Lexical Entailment Open
Recognizing lexical entailment (RLE) always plays an important role in inference of natural language, i.e., identifying whether one word entails another, for example, fox entails animal. In the literature, automatically recognizing lexical…
View article: Reading the Videos: Temporal Labeling for Crowdsourced Time-Sync Videos Based on Semantic Embedding
Reading the Videos: Temporal Labeling for Crowdsourced Time-Sync Videos Based on Semantic Embedding Open
Recent years have witnessed the boom of online sharing media contents, which raise significant challenges in effective management and retrieval. Though a large amount of efforts have been made, precise retrieval on video shots with certain…