Explore @ZurichNLP Open Source projects

@ZurichNLP

ZurichNLP

Stars
368
Global Org. Rank 28,764 (Top 10 %)
Registered almost 7 years ago
Most used languages

Python
56.8 %

Jupyter Notebook
18.9 %

Shell
10.8 %

Mathematica 2.7 %

Perl
2.7 %

HTML
2.7 %

Vue 2.7 %

PLSQL 2.7 %
Location 🇨🇭 Switzerland
Country Total Rank 1,310
Country Ranking

PLSQL 9

Mathematica 15

Perl
35

Jupyter Notebook
142

Shell
165

Vue 199

Python
267

HTML
716

mbr

Minimum Bayes Risk Decoding for Hugging Face Transformers

ContraDecode

The implementation of "Mitigating Hallucinations and Off-target Machine Translation with Source-Contrastive and Language-Contrastive Decoding"

xstance

A Multilingual Multi-Target Dataset for Stance Detection

nmtscore

A library of translation-based text similarity measures

swissbert

The multilingual language model for Switzerland

Jupyter Notebook

ContraPro

Contrastive evaluation of pronoun translation in neural machine translation

multilingual-instruction-tuning

Code and data for the paper "Turning English-centric LLMs Into Polyglots: How Much Multilinguality Is Needed?"

Jupyter Notebook

coverage-contrastive-conditioning

Data and code accompanying the paper "As Little as Possible, as Much as Necessary: Detecting Over- and Undertranslations with Contrastive Conditioning" (ACL 2022)

ContraWSD

Word sense disambiguation test sets for NMT

understanding-mbr

domain-robustness

segtest

A Test Suite for Morphological Phenomena in Neural Machine Translation

mtrain

Training automation for neural and statistical machine translation engines

mbr-sensitivity

Data and code for the paper "Identifying Weaknesses in Machine Translation Metrics Through Minimum Bayes Risk Decoding: A Case Study for COMET"

sdg_swisstext_2024_sharedtask

Repository for data and evaluation of 2024 Shared Task on SDG classification held by the Swiss Text Conference.

BLESS

Code for the EMNLP 2023 paper "BLESS: Benchmarking Large Language Models on Sentence Simplification"

Jupyter Notebook

emnlp2018-imitation-learning-for-neural-morphology

Code for Paper "Imitation Learning for Neural Morphological String Transduction" by Peter Makarov and Simon Clematide. 2018. EMNLP

monotonicity_loss

romanesco

Simple recurrent neural network (RNN) language model

translation-direction-detection

Unsupervised translation direction detection using NMT systems

mt-parity-assessment-data

experimental data for paper "A Set of Recommendations for Assessing Human–Machine Parity in Language Translation"

acl2020-historical-text-normalization

Code for the ACL 2020 paper "Semi-supervised Contextual Historical Text Normalization" by Peter Makarov and Simon Clematide

contrastive-conditioning

Code and data accompanying the paper "Contrastive Conditioning for Assessing Disambiguation in MT: A Case Study of Distilled Bias"

coling2018-neural-transition-based-morphology

Code repository for COLING 2018 paper by Makarov and Clematide

distil-lingeval

Data and code accompanying the paper "On the Limits of Minimal Pairs in Contrastive Evaluation"

20Minuten

Jupyter Notebook

MultiPivotNMT

The implementation of "Investigating Multi-Pivot Ensembling with Massively Multilingual Machine Translation Models"

multilingual-lemma-disambiguation-gold-standard

A Multilingual Lemma Disambiguation Gold Standard for German, Finnish, French and Italian (as described in the MA thesis )

specific_hospo_respo

Code for hospitality review response generation

Jupyter Notebook

voting-booklet-bias

Code for the paper "Voting Booklet Bias: Stance Detection in Swiss Federal Communication"

Jupyter Notebook

recognizing-semantic-differences

Code for the paper "Towards Unsupervised Recognition of Token-level Semantic Differences in Related Documents"

swiss-german-text-encoders

Code for the paper "Modular Adaptation of Multilingual Encoders to Written Swiss German Dialect"

CoNTra_corpora

Collection of corpora built in the project Rich Context in Neural Machine Translation (2017-2020)

RANLP2021-German-ATS

daikon

Simple encoder-decoder neural machine translation written in tensorflow

SockUeye

RumantschCorpora

SockAPeye

understanding-ctx-aug

Code for the 2023 ACL Findings paper, Uncovering Hidden Consequences of Pre-training Objectives in Sequence-to-Sequence Models (Kew & Sennrich, 2023)

Jupyter Notebook

romanisation-transfer

Code for the Paper "On Romanization for Model Transfer Between Scripts in Neural Machine Translation"