Yao Zhao

QoS-aware Web Service Composition Considering the Constraints between Services

2017

In the field of Web service composition, many scholars consider that there is no connection between concrete services but actually there are conflicts and dependencies between different types of services. For addressing the problem of …

A Well-Composed Text is Half Done! Composition Sampling for Diverse Conditional Generation

2022 · arXiv (Cornell University)

We propose Composition Sampling, a simple but effective method to generate diverse outputs for conditional generation of higher quality compared to previous stochastic decoding strategies. It builds on recently proposed plan-based neural generation models (Narayan …

Implicit Relation Linking for Question Answering over Knowledge Graph

2022 · Findings of the Association for Computational Linguistics: ACL 2022

Relation linking (RL) is a vital module in knowledge-based question answering (KBQA) systems. It aims to link the relations expressed in natural language (NL) to the corresponding ones in knowledge graph (KG). Existing methods mainly …

Sentiment and Semantic Hierarchical Transformer for Utterance-level Emotion Recognition

2022

In natural language processing, utterance-level emotion recognition (ULER) is a fundamental task which requires comprehensive analysis of words and contexts. Since one word can exhibit opposite emotion polarities in different contexts, even large scale deep …

Asymptotic Consistent Graph Structure Learning for Multivariate Time-Series Anomaly Detection

2024 · IEEE Transactions on Instrumentation and Measurement

Capturing complex inter-variable relationships is crucial for anomaly detection for multivariate time series (MTS) data. In recent years, graph neural networks (GNNs) have been introduced to explicitly model complex inter-variable relationships from global static or …

A frequency attention-embedded network for polyp segmentation

2025 · Scientific Reports

Gastrointestinal polyps are observed and treated under endoscopy, so there presents significant challenges to advance endoscopy imaging segmentation of polyps. Current methodologies often falter in distinguishing complex polyp structures within diverse (mucosal) tissue environments. In …

Attend and Enrich: Enhanced Visual Prompt for Zero-Shot Learning

2025 · Proceedings of the AAAI Conference on Artificial Intelligence

Zero-shot learning (ZSL) endeavors to transfer knowledge from the seen categories to recognize unseen categories, which mostly relies on the semantic-visual interactions between image and attribute tokens. Recently, the prompt learning has emerged in ZSL …

Paragraph-level Neural Question Generation with Maxout Pointer and Gated Self-attention Networks

2018

Question generation, the task of automatically creating questions that can be answered by a certain span of text within a given passage, is important for question-answering and conversational systems in digital assistants such as Alexa, …

PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization

2019 · arXiv (Cornell University)

Recent work pre-training Transformers with self-supervised objectives on large text corpora has shown great success when fine-tuned on downstream NLP tasks including text summarization. However, pre-training objectives tailored for abstractive text summarization have not been …

PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization

2020 · International Conference on Machine Learning

Recent work pre-training Transformers with self-supervised objectives on large text corpora has shown great success when fine-tuned on downstream NLP tasks including text summarization. However, pre-training objectives tailored for abstractive text summarization have not been …