Search Results for author:
Found 37 papers, 14 papers with code
Unsupervised Translation of German–Lower Sorbian: Exploring Training and Novel Transfer Methods on a Low-Resource Language
This paper describes the methods behind the systems submitted by the University of Groningen for the WMT 2021 Unsupervised Machine Translation task for German–Lower Sorbian (DE–DSB): a high-resource language to a low-resource one.
Linguistically Motivated Subwords for English-Tamil Translation: University of Groningen’s Submission to WMT-2020
This paper describes our submission for the English-Tamil news translation task of WMT-2020.
Optimal Word Segmentation for Neural Machine Translation into Dravidian Languages
Dravidian languages, such as Kannada and Tamil, are notoriously difficult to translate by state-of-the-art neural models.
Low-Resource Unsupervised NMT: Diagnosing the Problem and Providing a Linguistically Motivated Solution
Unsupervised Machine Translation has been advancing our ability to translate without parallel data, but state-of-the-art methods assume an abundance of monolingual data.
Simple Embedding-Based Word Sense Disambiguation
The results of our experiments show that by lexically extending the amount of words in the gloss and context, although it works well for other implementations of Lesk, harms our method.
Data Selection for Unsupervised Translation of German–Upper Sorbian
This paper describes the methods behind the systems submitted by the University of Groningen for the WMT 2020 Unsupervised Machine Translation task for German–Upper Sorbian.
Evaluating Pre-training Objectives for Low-Resource Translation into Morphologically Rich Languages
We conduct our evaluation on four typologically diverse target MRLs, and find that PT-Inflect surpasses NMT systems trained only on parallel data.
UDapter: Typology-based Language Adapters for Multilingual Dependency Parsing and Sequence Labeling
To address this, we propose a novel language adaptation approach by introducing contextual language adapters to a multilingual parser.
Are Character-level Translations Worth the Wait? Comparing ByT5 and mT5 for Machine Translation
Pretrained character-level and byte-level language models have been shown to be competitive with popular subword models across a range of Natural Language Processing (NLP) tasks.
Subword-Delimited Downsampling for Better Character-Level Translation
This new downsampling method not only outperforms existing downsampling methods, showing that downsampling characters can be done without sacrificing quality, but also leads to promising performance compared to subword models for translation.
Patching Leaks in the Charformer for Efficient Character-Level Generation
Character-based representations have important advantages over subword-based ones for morphologically rich languages.
Hyper-X: A Unified Hypernetwork for Multi-Task Multilingual Transfer
Massively multilingual models are promising for transfer learning across tasks and languages.
The Importance of Context in Very Low Resource Language Modeling
This paper investigates very low resource language model pretraining, when less than 100 thousand sentences are available.
Unsupervised Translation of German--Lower Sorbian: Exploring Training and Novel Transfer Methods on a Low-Resource Language
Lastly, we experiment with the order in which offline and online back-translation are used to train an unsupervised system, finding that using online back-translation first works better for DE$\rightarrow$DSB by 2. 76 BLEU.
A Shared Task of a New, Collaborative Type to Foster Reproducibility: A First Exercise in the Area of Language Science and Technology with REPROLANG2020
n this paper, we introduce a new type of shared task {---} which is collaborative rather than competitive {---} designed to support and fosterthe reproduction of research results.
UDapter: Language Adaptation for Truly Universal Dependency Parsing
The resulting parser, UDapter, outperforms strong monolingual and multilingual baselines on the majority of both high-resource and low-resource (zero-shot) languages, showing the success of the proposed adaptation approach.
BERTje: A Dutch BERT Model
The transformer-based pre-trained language model BERT has helped to improve state-of-the-art performance on many natural language processing (NLP) tasks.
Ranked #3 on
Sentiment Analysis
on DBRD
Cross-Lingual Word Embeddings for Morphologically Rich Languages
Cross-lingual word embedding models learn a shared vector space for two or more languages so that words with similar meaning are represented by similar vectors regardless of their language.
Multi-Team: A Multi-attention, Multi-decoder Approach to Morphological Analysis.
This paper describes our submission to SIGMORPHON 2019 Task 2: Morphological analysis and lemmatization in context.
Squib: Reproducibility in Computational Linguistics: Are We Willing to Share?
For a selection of ten papers, we attempted to reproduce the results using the provided data and code.
Modeling Input Uncertainty in Neural Network Dependency Parsing
Recently introduced neural network parsers allow for new approaches to circumvent data sparsity issues by modeling character level information and by exploiting raw data in a semi-supervised setting.
MoNoise: Modeling Noise Using a Modular Normalization System
We show that MoNoise beats the state-of-the-art on different normalization benchmarks for English and Dutch, which all define the task of normalization slightly different.
Ranked #1 on
Lexical Normalization
on LexNorm
The Power of Character N-grams in Native Language Identification
In this paper, we explore the performance of a linear SVM trained on language independent character features for the NLI Shared Task 2017.
Parser Adaptation for Social Media by Integrating Normalization
This work explores different approaches of using normalization for parser adaptation.
Bilingual Learning of Multi-sense Embeddings with Discrete Autoencoders
We present an approach to learning multi-sense word embeddings relying both on monolingual and bilingual information.
Word Representations, Tree Models and Syntactic Functions
Word representations induced from models with discrete latent variables (e. g.\ HMMs) have been shown to be beneficial in many NLP applications.
Treelet Probabilities for HPSG Parsing and Error Correction
In the second experiment it is tested for the ability to score the parse tree of the correct sentence higher than the constituency tree of the original version of the sentence containing grammatical error.
