Discover ZurichNLP/romanisation-transfer Open Source project

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

ContraDecode

A Multilingual Multi-Target Dataset for Stance Detection

xstance

A library of translation-based text similarity measures

nmtscore

The multilingual language model for Switzerland

swissbert

Contrastive evaluation of pronoun translation in neural machine translation

ContraPro

Perl

multilingual-instruction-tuning

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

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

coverage-contrastive-conditioning

Word sense disambiguation test sets for NMT

ContraWSD

understanding-mbr

domain-robustness

A Test Suite for Morphological Phenomena in Neural Machine Translation

segtest

Training automation for neural and statistical machine translation engines

mtrain

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

mbr-sensitivity

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

sdg_swisstext_2024_sharedtask

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

BLESS

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

emnlp2018-imitation-learning-for-neural-morphology

Simple recurrent neural network (RNN) language model

monotonicity_loss

PLSQL

romanesco

Unsupervised translation direction detection using NMT systems

translation-direction-detection

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

mt-parity-assessment-data

HTML

acl2020-historical-text-normalization

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

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

contrastive-conditioning

Code repository for COLING 2018 paper by Makarov and Clematide

coling2018-neural-transition-based-morphology

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

distil-lingeval

20Minuten

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

MultiPivotNMT

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

multilingual-lemma-disambiguation-gold-standard

specific_hospo_respo

Code for hospitality review response generation

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

voting-booklet-bias

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

recognizing-semantic-differences

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

swiss-german-text-encoders

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

CoNTra_corpora

RANLP2021-German-ATS

Simple encoder-decoder neural machine translation written in tensorflow

daikon

SockUeye

Vue

RumantschCorpora

SockAPeye

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

understanding-ctx-aug