Hady W. Lauw

A Partition Cover Approach to Tokenization

Tokenization is the process of encoding strings into tokens of a fixed vocabulary size, and is widely utilized in Natural Language Processing applications. The leading tokenization algorithm today...

Towards Aligning Slides and Video Snippets: Mitigating Sequence and Content Mismatches

Towards Automated Slide Augmentation to Discover Credible and Relevant Links

Community Similarity based on User Profile Joins

Selecting Comparative Sets of Reviews Across Multiple Items

Learning Multi-Faceted Prototypical User Interests

Meta-Complementing the Semantics of Short Texts in Neural Topic Models

A Partition Cover Approach to Tokenization

Morphologically-Aware Vocabulary Reduction of Word Embeddings

Multi-Lingual Multi-Partite Product Title Matching

Cornac-AB: An Open-Source Recommendation Framework with Native A/B Testing Integration

AmpSum: Adaptive Multiple-Product Summarization towards Improving Recommendation Captions

Term Importance for Transformer-Based QA Retrieval: A Case Study of StackExchange

Text-Attributed Graph Representation Learning: Methods, Applications, and Challenges

Multimodal Review Generation for Recommender Systems

Aligning Dual Disentangled User Representations from Ratings and Textual Content

Hyperbolic Graph Topic Modeling Network with Continuously Updated Topic Tree

Learning Multiple Maps from Conditional Ordinal Triplets