vhientran

2023-awesome-instruction-learning

Papers and Datasets on Instruction Learning / Instruction Tuning. ✨✨✨

2024_acl_paying_attention_to_the_source

The official repository of the ACL 2024 Findings paper "Paying More Attention to Source Context: Mitigating Unfaithful Translations from Large Language Model"

ATLOP

Source code for paper "Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling", AAAI 2021

cnn-rnf

Convolutional Neural Networks with Recurrent Neural Filters

Code-ZSRE

The official source code of our paper: "Enhancing Semantic Correlation between Instances and Relations for Zero-Shot Relation Extraction", Journal of Natural Language Processing.

mtl-da-emnlp

Code to reproduce the experiments presented in the EMNLP 2021 paper "Rethinking data augmentation for low-resource neural machine translation: a multi-task learning approach"

neat-vision

Neat (Neural Attention) Vision, is a visualization tool for the attention mechanisms of deep-learning models for Natural Language Processing (NLP) tasks. (framework-agnostic)

OTE-MTL

Code and dataset for Findings of EMNLP 2020 paper titled "A Multi-task Learning Framework for Opinion Triplet Extraction"

trimf

vhientran.github.io

My personal website

vhientran/Code-ZSRE

The official source code of our paper: "Enhancing Semantic Correlation between Instances and Relations for Zero-Shot Relation Extraction", Journal of Natural Language Processing.

vhientran/2024_acl_paying_attention_to_the_source

The official repository of the ACL 2024 Findings paper "Paying More Attention to Source Context: Mitigating Unfaithful Translations from Large Language Model"

vhientran/vhientran.github.io

My personal website

vhientran/2022NAACL-TreeMix

Code for 2022 NAACL paper TreeMix

vhientran/2023-awesome-instruction-learning

Papers and Datasets on Instruction Learning / Instruction Tuning. ✨✨✨

vhientran/2023-TreeSwap

Complimentary code for our paper TreeSwap: Data Augmentation for Machine Translation via Dependency Subtree Swapping (RANLP 2023)

vhientran/2023-Adaptive-MT-LLM-Fine-tuning

Fine-tuning Mistral LLM for Adaptive Machine Translation

vhientran/2023-HOLLY-benchmark

This repository contains a dataset for semantically appropriate application of lexical constraints in NMT.

vhientran/2023-Perturbation-basedQE

Perturbation-based QE: An Explainable, Unsupervised Word-level Quality Estimation Method for Blackbox Machine Translation

vhientran/2023-PMC-LLaMA

The official codes for "PMC-LLaMA: Towards Building Open-source Language Models for Medicine"

vhientran/2023-TIM

code for Teaching LM to Translate with Comparison

vhientran/2023-WICL

Code for EMNLP 2023 Findings paper: "Not All Demonstration Examples are Equally Beneficial: Reweighting Demonstration Examples for In-Context Learning"

vhientran/2024naacl_icl_anti-lm_decoding

vhientran/AAAI23-Mono4SiMT

Implementation of the paper “Improving Simultaneous Machine Translation with Monolingual Data”.

vhientran/Awesome-LLM-MT

vhientran/CAD

Unofficial re-implementation of "Trusting Your Evidence: Hallucinate Less with Context-aware Decoding"

vhientran/CLaP

Code for our NAACL-2024 paper "Contextual Label Projection for Cross-Lingual Structured Prediction"

vhientran/DecoMT

DecoMT

vhientran/EMNLP2023_ParroT

The ParroT framework to enhance and regulate the Translation Abilities during Chat based on open-sourced LLMs (e.g., LLaMA-7b, Bloomz-7b1-mt) and human written translation and evaluation data.

vhientran/ICCASSP23-NMT-targeted-attack

Adversarial Attack against NMT

vhientran/knn-seq

Efficient, Extensible kNN-MT Framework

vhientran/LLMSurvey

The official GitHub page for the survey paper "A Survey of Large Language Models".

vhientran/LMFlow

An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

vhientran/LoRA

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

vhientran/Okapi

Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback

vhientran/peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

vhientran/PFT-ef-EAMT23

Terminology experiments on the Canadian Hansard — Expériences de terminologie sur le Hansard canadien (EAMT 2023)

vhientran/qlora

QLoRA: Efficient Finetuning of Quantized LLMs

vhientran/swie_overmiss_llm4mt

Code for "Improving Translation Faithfulness of Large Language Models via Augmenting Instructions"

vhientran/translation_llm