Pun Detection and Location

“The Boating Store Had Its Best Sail Ever”: Pronunciation-attentive Contextualized Pun Recognition
Yichao Zhou, Jyun-yu Jiang, Jieyu Zhao, Kai-Wei Chang and Wei Wang
Computer Science Department, University of California, Los Angeles

Requirements

python3
pip3 install -r requirements.txt

Training for Pun Location

python cv_run_ner.py 
--data_dir data/semeval2017/data_with_pronunciation/pl-homo/ 
--bert_model bert-base-cased 
--task_name ner 
--output_dir out 
--max_seq_length 128 
--do_train 
--num_train_epochs 3 
--do_eval 
--pron_emb_size 16 
--do_pron

这里简述每个文件的作用：

run.sh 是用于批量跑本代码的脚本，用于比较系统性能等。
word2Sense.txt 是用于寻找出现在训练集中的双关词有多少个含义如: shot 8 就代表shot 这个单词，在训练集中有8个意思涉及到了双关意义
tools 文件夹下是工具文件

./tools/getSense.py 用于生成 /home/lawson/program/punLocation/data/pun_word_definition.txt 的文件
./tools/generateSenseEmb.py 是用于生成defi_emb_xxx.txt 文件

defi_emb_xxx.txt 是用于存储各个单词在 wordnet 中的不同含义
pun_word_definition.txt 是用于将每个双关词的各种含义使用bert处理得到的embedding
subtask3_v2 是用pun+gloss 对的方式解决pun interpretation 的问题

Pun Detection and Location

Related tags

Overview

Pun Detection and Location

Requirements

Training for Pun Location

Owner

lawson

Distributed Evolutionary Algorithms in Python

This program can detect your face and add an Christams hat on the top of your head

This repository contains an implementation of the Permutohedral Attention Module in Pytorch

The code for our paper "NSP-BERT: A Prompt-based Zero-Shot Learner Through an Original Pre-training Task —— Next Sentence Prediction"

RITA is a family of autoregressive protein models, developed by LightOn in collaboration with the OATML group at Oxford and the Debora Marks Lab at Harvard.

Time Dependent DFT in Tamm-Dancoff Approximation

Unofficial TensorFlow implementation of Protein Interface Prediction using Graph Convolutional Networks.

Official implementation of "Dynamic Anchor Learning for Arbitrary-Oriented Object Detection" (AAAI2021).

Image morphing without reference points by applying warp maps and optimizing over them.

PyTorch 1.0 inference in C++ on Windows10 platforms

NeuTex: Neural Texture Mapping for Volumetric Neural Rendering

Animate molecular orbital transitions using Psi4 and Blender

You Only 👀 One Sequence

Gesture recognition on Event Data

Pretraining Representations For Data-Efficient Reinforcement Learning

SkipGNN: Predicting Molecular Interactions with Skip-Graph Networks (Scientific Reports)

The Python ensemble sampling toolkit for affine-invariant MCMC

Emotional conditioned music generation using transformer-based model.

Style transfer between images was performed using the VGG19 model

A weakly-supervised scene graph generation codebase. The implementation of our CVPR2021 paper ``Linguistic Structures as Weak Supervision for Visual Scene Graph Generation''