Qian's Projects
Simple language-driven navigation tasks for studying compositional learning
A BERT model for scientific text.
Author implementation of the paper "Don’t paraphrase, detect! Rapid and Effective Data Collection for Semantic Parsing"
BiLSTM-CRF joint model for tasks like sequence labeling using char/word level embeddings in Tensorflow
software engineering tools
personal online resume
the resum of siviltaram
Unsurprising JavaScript
Data and Code Release for "On the Potential of Lexico-logical Alignments for Semantic Parsing to SQL Queries"
Stanford NLP for .NET
A auto test framework for project sudoku
Data and Code for ICLR2020 Paper "TabFact: A Large-scale Dataset for Table-based Fact Verification"
TAPEX: Table Pre-training via Learning a Neural SQL Executor
The official implementation of EMNLP 2020, "A Simple and Effective Model for Answering Multi-span Questions".
🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.
Build To Win
Code to reproduce experiments in the paper "Task-Oriented Dialogue as Dataflow Synthesis" (TACL 2020).
TAT-QA (Tabular And Textual dataset for Question Answering) contains 16,552 questions associated with 2,757 hybrid contexts from real-world financial reports.
:deciduous_tree:从中文文本中自动提取关键词和摘要
The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
ToTTo is an open-domain English table-to-text dataset with over 120,000 training examples that proposes a controlled generation task: given a Wikipedia table and a set of highlighted table cells, produce a one-sentence description. We hope it can serve as a useful research benchmark for high-precision conditional text generation.
🦄 State-of-the-Art Conversational AI with Transfer Learning
A PyTorch implementation of Transformer in "Attention is All You Need"