Search Results for author:
Found 10 papers, 3 papers with code
MAMMOTH: Massively Multilingual Modular Open Translation @ Helsinki
NLP in the age of monolithic large language models is approaching its limits in terms of size and information that can be handled.
Multilingual NMT with a language-independent attention bridge
In this paper, we propose a multilingual encoder-decoder architecture capable of obtaining multilingual sentence representations by means of incorporating an intermediate {\em attention bridge} that is shared across all languages.
The MeMAD Submission to the WMT18 Multimodal Translation Task
Our experiments show that the effect of the visual features in our system is small.
The University of Helsinki submissions to the WMT19 news translation task
In this paper, we present the University of Helsinki submissions to the WMT 2019 shared task on news translation in three language pairs: English-German, English-Finnish and Finnish-English.
An Empirical Investigation of Word Alignment Supervision for Zero-Shot Multilingual Neural Machine Translation
In this paper, we investigate the benefits of an explicit alignment to language labels in Transformer-based MNMT models in the zero-shot context, by jointly training one cross attention head with word alignment supervision to stress the focus on the target language label.
The Helsinki submission to the AmericasNLP shared task
The University of Helsinki participated in the AmericasNLP shared task for all ten language pairs.
Latest Development in the FoTran Project – Scaling Up Language Coverage in Neural Machine Translation Using Distributed Training with Language-Specific Components
We describe the enhancement of a multilingual NMT toolkit developed as part of the FoTran project.
A Closer Look at Parameter Contributions When Training Neural Language and Translation Models
We analyze the learning dynamics of neural language and translation models using Loss Change Allocation (LCA), an indicator that enables a fine-grained analysis of parameter updates when optimizing for the loss function.
Why bother with geometry? On the relevance of linear decompositions of Transformer embeddings
A recent body of work has demonstrated that Transformer embeddings can be linearly decomposed into well-defined sums of factors, that can in turn be related to specific network inputs or components.
SemEval-2024 Shared Task 6: SHROOM, a Shared-task on Hallucinations and Related Observable Overgeneration Mistakes
This paper presents the results of the SHROOM, a shared task focused on detecting hallucinations: outputs from natural language generation (NLG) systems that are fluent, yet inaccurate.
