Yunyao Li interacted with
Adobe — Director of Machine Learning (CA)
Papers · 96
- Humans' ALMANAC: A Human Collaboration Dataset of Action-Level Mental Model Annotations for Agent Collaboration
- Human-LLM Collaborative Feature Engineering for Tabular Data
-
ACL 2026 Industry Track: Overview
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)2026S2
- Unveiling unwillingness to communicate among EFL learners in flipped learning: an ecological perspective
- The Intersects of AI and Film: How Machine Learning Determines Narrative Structures and Creates Cultural Representation
- ACL 2025 Industry Track: Overview
- CoPrompter: User-Centric Evaluation of LLM Instruction Alignment for Improved Prompt Engineering
- StorySparkQA: Expert-Annotated QA Pairs with Real-World Knowledge for Children’s Story-Based Learning
- Construction of Paired Knowledge Graph - Text Datasets Informed by Cyclic Evaluation
- SFPN: segmentation-based feature pyramid network for multi-focus image fusion
- Deep Knowledge Tracking Based on Double Attention Mechanism and Cognitive Difficulty
- Deep Homography Estimation With Feature Correlation Transformer
- Infrared and visible image fusion via mutual information maximization
- Beyond Labels: Empowering Human Annotators with Natural Language Explanations through a Novel Active-Learning Architecture
- Growing and Serving Large Open-domain Knowledge Graphs
- Multi-scale homography estimation based on dual feature aggregation transformer
- PriMeSRL-Eval: A Practical Quality Metric for Semantic Role Labeling Systems Evaluation
- Label Sleuth: From Unlabeled Text to a Classifier in a Few Hours
- Informed Patch Enhanced HyperGCN for skeleton-based action recognition
- Universal Proposition Bank 2.0
- Machine learning cutting forces in milling processes of functionally graded materials
- Accepted Tutorials at The Web Conference 2022
- Identifying Origin-Destination Trips from GPS Data – Application in Travel Time Reliability of Dedicated Trucks
- Deep Learning on Graphs for Natural Language Processing
- TableLab: An Interactive Table Extraction System with Adaptive Deep Learning
- Making AI Machines Work for Humans in FoW
- Question Answering over Knowledge Bases by Leveraging Semantic Parsing and Neuro-Symbolic Reasoning
- Improved Semantic Role Labeling using Parameterized Neighborhood Memory Adaptation
- Learning Explainable Linguistic Expressions with Neural Inductive Logic Programming for Sentence Classification
- A Novel Workflow for Accurately and Efficiently Crowdsourcing Predicate Senses and Argument Labels
- CLAR: A Cross-Lingual Argument Regularizer for Semantic Role Labeling
- Estimation of Short-Term Online Taxi Travel Time Based on Neural Network
- Answering Complex Questions by Combining Information from Curated and Extracted Knowledge Bases
- Ontology mediated information extraction in financial domain with Mastro System-T
- Learning Electronic Health Records through Hyperbolic Embedding of Medical Ontologies
- HEIDL: Learning Linguistic Expressions with Deep Learning and Human-in-the-Loop
- Low-resource Deep Entity Resolution with Transfer and Active Learning
- Bridging the Semantic Gap with SQL Query Logs in Natural Language Interfaces to Databases
- DIMSIM: An Accurate Chinese Phonetic Similarity Algorithm Based on Learned High Dimensional Encoding
- Natural Language Data Management and Interfaces
- Exploiting Structure in Representation of Named Entities using Active Learning
- SystemT: Declarative Text Understanding for Enterprise
- LUSTRE: An Interactive System for Entity Structured Representation and Variant Generation
- CROWD-IN-THE-LOOP: A Hybrid Approach for Annotating Semantic Roles
- Creation and Interaction with Large-scale Domain-Specific Knowledge Bases
- Active Learning for Black-Box Semantic Role Labeling with Neural Factors
- Towards Re-defining Relation Understanding in Financial Domain
- Natural Language Data Management and Interfaces: Recent Development and Open Challenges
- Synthesizing Extraction Rules from User Examples with SEER
- SEER: Auto-Generating Information Extraction Rules from User-Specified Examples
- K-SRL: Instance-based Learning for Semantic Role Labeling
- Multilingual Aliasing for Auto-Generating Proposition Banks
- Multilingual Information Extraction with PolyglotIE
- Towards Semi-Automatic Generation of Proposition Banks for Low-Resource Languages
- POLYGLOT: Multilingual Semantic Role Labeling with Unified Labels
- Transparent Machine Learning for Information Extraction: State-of-the-Art and the Future
- VINERy: A Visual IDE for Information Extraction
- Generating High Quality Proposition Banks for Multilingual Semantic Role Labeling
-
XML based Keyword Search
2014-12-18S2
- A Survey of Natural Language Query Builder Interface for Structured Databases using Dependency Parsing
- Enterprise Search in the Big Data Era: Recent Developments and Open Challenges
- VLDB 2014 Ph.D. Workshop - An Overview
- Understand users’ comprehension and preferences for composing information visualizations
- Rule-Based Information Extraction is Dead! Long Live Rule-Based Information Extraction Systems!
- OpinionBlocks: A Crowd-Powered, Self-improving Interactive Visual Analytic System for Understanding Opinion Text
- Automatic Term Ambiguity Detection
- I can do text analytics!: designing development tools for novice developers
- Gumshoe quality toolkit: administering programmable search
-
Image Enhancement by Lift-Wavelet Based Homomorphic Filtering
2012-10-16S2
-
Automatic suggestion of query-rewrite rules for enterprise search
Annual International ACM SIGIR Conference on Research and Development in Information Retrieval2012-08-12S2
- WizIE: A Best Practices Guided Development Environment for Information Extraction
-
Session details: Text mining
Proceedings of the 20th ACM international conference on Information and knowledge management2011-10-24S2
- Facilitating pattern discovery for relation extraction with semantic-signature-based clustering
- SystemT: A Declarative Information Extraction System
- A Graph Approach to Spelling Correction in Domain-Centric Search
- The SystemT IDE: an integrated development environment for information extraction rules
- Selectivity estimation for extraction operators over text data
- Domain Adaptation of Rule-Based Annotators for Named-Entity Recognition Tasks
- SystemT: An Algebraic Approach to Declarative Information Extraction
- Enterprise information extraction: recent developments and open challenges
- Understanding queries in a search database system
- Enabling enterprise mashups over unstructured text feeds with InfoSphere MashupHub and SystemT
- A new evidence model and its application for discriminating enemy operation intention
- SystemT: a system for declarative information extraction
- Regular Expression Learning for Information Extraction
- Implementation of UNDP 403 distance teacher training system using Struts+Hibernate Frame
- Enabling Schema-Free XQuery with meaningful query focus
- NaLIX: A generic natural language search environment for XML data
- Enabling Domain-Awareness for a Generic Natural Language Interface
- DaNaLIX: a domain-adaptive natural language interface for querying XML
- Making database systems usable
-
Getting work done on the web: supporting transactional queries
Annual International ACM SIGIR Conference on Research and Development in Information Retrieval2006-08-06S2
- Term Disambiguation in Natural Language Query for XML
- Constructing a Generic Natural Language Interface for an XML Database
- NaLIX: an interactive natural language interface for querying XML
- Schema-Free XQuery