yinwenpeng/Attentive_Convolution

Stars
106
Rank 319,214 (Top 7 %)
Language
Python
Created over 6 years ago
Updated over 6 years ago

yinwenpeng/Attentive_Convolution

yinwenpeng

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

This released code corresponds to TACL paper "attentive convolution". Attentive Convolution aims to generate a vector for two sentences.

Attentive_Convolution

This released code corresponds to paper "attentive convolution". Attentive Convolution aims to generate a vector for two sentences.

For general usage in terms of modeling relation of two sentences, pls refer to "train_AttentiveConvNet_easy_version.py" file and use the function "Attentive_Conv_for_Pair_easy_version".

BenchmarkingZeroShot

Answer_Selection

For those who want to model the inter-sentence relations, pls use the more powerful code of "Attentive Convolution" in another repository

SciTail

This released code is for our ACL2018 paper "End-Task Oriented Textual Entailment via Deep Explorations of Inter-Sentence Interactions". It gets STOA performance in a textual entailment benchmark -- 82.1% accuracy on SciTail dataset. We release the code and the pretrained model

KBQA_IBM_New

KBPath

Online-FLORS

KBQA_IBM

CNN_PI

FEVER

MachineComprehension

DatalessEntailment

LORELEI2018

FLORS

Thang

MetaEmb

SQUAD_CNN

BERT-play

ESA

term-def-seek

This program aims to find the definition of a term, first from WordNet, then Wikipedia if fail

TCLNLI

TextualEntailment