FAQ-based Question Answering System

1st Place Solution for CrowdFlower Product Search Results Relevance Competition on Kaggle.

A curated list of papers dedicated to neural text (semantic) matching.

3rd Place Solution for HomeDepot Product Search Results Relevance Competition on Kaggle.

A basic implementation(not official code) of AVP-SLAM(IROS 2020) in simulation. https://arxiv.org/abs/2007.01813

Tensorflow implementations of various Deep Semantic Matching Models (DSMM).

[CVPR 2025 Highlight] MATCHA: Towards Matching Anything.

[ACM-CIKM] 2nd place solution at CIKM AnalytiCup 2018, a task for determining short text similarities.

Convolutional Neural Networks for Soft-Matching N-Grams in Ad-hoc Search

Code for SegMASt3R: Geometry Grounded Segment Matching (NeurIPS 2025)

A simple Keras implementation of Paper "Text Matching as Image Recognition"

A simple Keras implementation of ARC-II model proposed by paper "Convolutional Neural Network Architectures for Matching Natural Language Sentences"

A better job search based on semantic matching

Playing around drones with Android's Speech-to-text & Text-to-Speech; Setting up a Wake-up-word other than OK Google, and trying to match converted text to a given Ontology

A search engine for the curious

semantic matching toolkit

Serene Data Integration Platform

Hybrid resume–JD matching system using TF-IDF and Hugging Face MiniLM sentence embeddings with explainable hybrid scoring and deterministic feedback.

semantic matching，语义匹配

Matches JSON-keys and values best effort using translations, synonyms and Levenshtein distance. Also provides value and unit conversion of the associated JSON-values. Part of a Seminar Thesis at the Institute of Enterprise Systems at the University of Mannheim.

Semantic matching algorithm for linking texts with their relevant Medical Subject Headings (MeSH).

A semantic matcher is trained using BERT to identify all situations in which witnesses expresses their inability to remember.

Modular NLP tools for domain-specific semantic matching and structured data

Resume Keyword Optimizer is a Streamlit app that helps job seekers improve their resumes by comparing them to job descriptions. It identifies missing, present, and extra skills using a keyword matching system, offering personalized feedback and suggestions for improvement.

🏆 Explore real-world machine learning challenges with this Kaggle competitions portfolio, showcasing practical projects and skills in Python.

Resume Parsing Bias Detection Pipeline