xiaowensun-lab Goto Github PK

abigsurvey

A collection of 700+ survey papers on Natural Language Processing (NLP) and Machine Learning (ML)

bert-multi-label-text-classification

This repo contains a PyTorch implementation of a pretrained BERT model for multi-label text classification.

diagrams

dstc

Dialog State Tracking Challenge 2 & 3 Data

dstc11_simmc2.1-vit

Submission code for DSTC11 Track1, SIMMC2.1

emo2vec_wassa_paper

empatheticdialogues

Dialogue model that produces empathetic responses when trained on the EmpatheticDialogues dataset.

fashion-retrieval

This repository contains an implementation of the models introduced in the paper Dialog-based Interactive Image Retrieval. The network is implemented using PyTorch and the rest of the framework is in Python.

hybrid-code-networks

Hybrid Code Networks in PyTorch

lhc-chatbot

Live Helper Chat extension to provided quick responses automatically for an operators. Powered by DeepPavlov and MeiliSearch

missing_aware_prompts-l

Multimodal Prompting with Missing Modalities for Visual Recognition, CVPR'23

multimodal-speech-emotion-recognition

Lightweight and Interpretable ML Model for Speech Emotion Recognition and Ambiguity Resolution (trained on IEMOCAP dataset)

noisyfer

The official pytorch code for paper "Facial Emotion Recognition with Noisy Multi-task Annotations" (2021 WACV)

pytorch-multigpu

Multi GPU Training Code for Deep Learning with PyTorch

simmc

With the aim of building next generation virtual assistants that can handle multimodal inputs and perform multimodal actions, we introduce two new datasets (both in the virtual shopping domain), the annotation schema, the core technical tasks, and the baseline models. The code for the baselines and the datasets will be opensourced.

simmc-1

DSTC9 Track4

simmc21

Code for SIMMC 2.0: A Task-oriented Dialog Dataset for Immersive Multimodal Conversations

uniter-dialog

Cleaned-up code for DSTC 10: SIMMC 2.0 track: subtask 2: multimodal coreference resolution

vilt-dialog

Code for the ICML 2021 (long talk) paper: "ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision"