leuchine

Qi Liu's starred repositories

blimp

The Benchmark of Linguistic Minimal Pairs

Language:Python13400

bert-syntax

Assessing syntactic abilities of BERT

Language:PythonApache-2.015000

Symbolic-Metamodeling

Codebase for "Demystifying Black-box Models with Symbolic Metamodels", NeurIPS 2019.

Language:Jupyter Notebook4800

causal-text-embeddings

Software and data for "Using Text Embeddings for Causal Inference"

Language:PythonMIT12200

DeepLearningExamples

State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.

Language:Jupyter Notebook1279200

structural-probes

Codebase for testing whether hidden states of neural networks encode discrete structures.

Language:PythonNOASSERTION37400

jiant

jiant is an nlp toolkit

Language:PythonMIT162000

anli

Adversarial Natural Language Inference Benchmark

Language:PythonNOASSERTION38600

ctrl

Conditional Transformer Language Model for Controllable Generation

Language:PythonBSD-3-Clause185600

cosql

A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases

1400

SpanBERT

Code for using and evaluating SpanBERT.

Language:PythonNOASSERTION87700

universal-triggers

Universal Adversarial Triggers for Attacking and Analyzing NLP (EMNLP 2019)

Language:PythonMIT28700

text-to-text-transfer-transformer

Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"

Language:PythonApache-2.0596300

awesome-point-cloud-analysis

A list of papers and datasets about point cloud analysis (processing)

398100

sparse-structured-attention

Sparse and structured neural attention mechanisms

Language:PythonBSD-3-Clause22100

interpret_bert

Interpreting Bidirectional Encoder Representations from Transformers (BERT)

Language:PythonGPL-3.010800

contextual-repr-analysis

A toolkit for evaluating the linguistic knowledge and transferability of contextual representations. Code for "Linguistic Knowledge and Transferability of Contextual Representations" (NAACL 2019).

Language:Python21100

Tree-Transformer

Implementation of the paper Tree Transformer

Language:Python20700

udify

A single model that parses Universal Dependencies across 75 languages. Given a sentence, jointly predicts part-of-speech tags, morphology tags, lemmas, and dependency trees.

Language:PythonMIT21700

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Language:PythonMIT2955200

CCKS2019中文命名实体识别任务。从医疗文本中识别疾病和诊断、解剖部位、影像检查、实验室检验、手术和药物6种命名实体。现已实现基于jieba和AC自动机的baseline构建、基于BiLSTM和CRF的序列标住模型构建。bert的部分代码主要源于https://github.com/charles9n/bert-sklearn.git 感谢作者。模型最终测试集得分0.81，还有较大改进空间。可以当做一个baseline。

Language:Python34000