AIConfPaper
← Search

Josef van Genabith

20 accepted papers

2026

Grounding or Guessing? Visual Signals for Detecting Hallucinations in Sign Language Translation

Yasser HAMIDULLAH, Koel Dutta Chowdhury, Yusser Al Ghussin, Shakib Yazdani, Cennet Oguz, Josef van Genabith +1
ICLR 2026poster

Hallucination, where models generate fluent text unsupported by visual evidence, remains a major flaw in vision–language models and is especially critical in sign language translation (SLT). In SLT, meaning depends on precise grounding in video, and gloss-free models are particularly vulnerable beca…

Cited by 0Source ↗Scholar ↗
2025

Continual Learning in Multilingual Sign Language Translation

Shakib Yazdani, Josef Van Genabith, Cristina España-Bonet
NAACL 2025long

The field of sign language translation (SLT) is still in its infancy, as evidenced by the low translation quality, even when using deep learn- ing approaches. Probably because of this, many common approaches in other machine learning fields have not been explored in sign language. Here, we focus on…

Cited by 0Source ↗PDF ↗Scholar ↗
2024

MMAR: Multilingual and Multimodal Anaphora Resolution in Instructional Videos

Cennet Oguz, Pascal Denis, Simon Ostermann, Emmanuel Vincent, Natalia Skachkova, Josef Van Genabith
EMNLP 2024finding

Multilingual anaphora resolution identifies referring expressions and implicit arguments in texts and links to antecedents that cover several languages. In the most challenging setting, cross-lingual anaphora resolution, training data, and test data are in different languages. As knowledge needs to…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2024

Rewiring the Transformer with Depth-Wise LSTMs

Hongfei Xu, Yang Song, Qiuhui Liu, Josef van Genabith, Deyi Xiong
COLING 2024main

Stacking non-linear layers allows deep neural networks to model complicated functions, and including residual connections in Transformer layers is beneficial for convergence and performance. However, residual connections may make the model “forget” distant layers and fail to fuse information from pr…

Cited by 2Source ↗PDF ↗Scholar ↗
2024

Sign Language Translation with Sentence Embedding Supervision

Yasser Hamidullah, Josef van Genabith, Cristina España-Bonet
ACL 2024short

State-of-the-art sign language translation (SLT) systems facilitate the learning process through gloss annotations, either in an end2end manner or by involving an intermediate step. Unfortunately, gloss labelled sign language data is usually not available at scale and, when available, gloss annotati…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2024

When Your Cousin Has the Right Connections: Unsupervised Bilingual Lexicon Induction for Related Data-Imbalanced Languages

Niyati Bafna, Cristina España-Bonet, Josef van Genabith, Benoît Sagot, Rachel Bawden
COLING 2024main

Most existing approaches for unsupervised bilingual lexicon induction (BLI) depend on good quality static or contextual embeddings requiring large monolingual corpora for both languages. However, unsupervised BLI is most likely to be useful for low-resource languages (LRLs), where large datasets are…

Cited by 3Source ↗PDF ↗code ↗Scholar ↗
2023

Find-2-Find: Multitask Learning for Anaphora Resolution and Object Localization

Cennet Oguz, Pascal Denis, Emmanuel Vincent, Simon Ostermann, Josef van Genabith
EMNLP 2023long main

In multimodal understanding tasks, visual and linguistic ambiguities can arise. Visual ambiguity can occur when visual objects require a model to ground a referring expression in a video without strong supervision, while linguistic ambiguity can occur from changes in entities in action flows. As an…

Cited by 0Source ↗Scholar ↗
2023

Translating away Translationese without Parallel Data

Rricha Jalota, Koel Dutta Chowdhury, Cristina España-Bonet, Josef van Genabith
EMNLP 2023long main

Translated texts exhibit systematic linguistic differences compared to original texts in the same language, and these differences are referred to as translationese. Translationese has effects on various cross-lingual natural language processing tasks, potentially leading to biased results. In this p…

Cited by 0Source ↗Scholar ↗
2021

A Bidirectional Transformer Based Alignment Model for Unsupervised Word Alignment

Jingyi Zhang, Josef van Genabith
ACL 2021long

Word alignment and machine translation are two closely related tasks. Neural translation models, such as RNN-based and Transformer models, employ a target-to-source attention mechanism which can provide rough word alignments, but with a rather low accuracy. High-quality word alignment can help neura…

Cited by 11Source ↗PDF ↗code ↗Scholar ↗
2021

Comparing Feature-Engineering and Feature-Learning Approaches for Multilingual Translationese Classification

Daria Pylypenko, Kwabena Amponsah-Kaakyire, Koel Dutta Chowdhury, Josef van Genabith, Cristina España-Bonet
EMNLP 2021main

Traditional hand-crafted linguistically-informed features have often been used for distinguishing between translated and original non-translated texts. By contrast, to date, neural architectures without manual feature engineering have been less explored for this task. In this work, we (i) compare th…

Cited by 21Source ↗PDF ↗Scholar ↗
2021

Investigating the Helpfulness of Word-Level Quality Estimation for Post-Editing Machine Translation Output

Raksha Shenoy, Nico Herbig, Antonio Krüger, Josef van Genabith
EMNLP 2021main

Compared to fully manual translation, post-editing (PE) machine translation (MT) output can save time and reduce errors. Automatic word-level quality estimation (QE) aims to predict the correctness of words in MT output and holds great promise to aid PE by flagging problematic output. Quality of QE…

Cited by 7Source ↗PDF ↗code ↗Scholar ↗
2021

Learning Hard Retrieval Decoder Attention for Transformers

Hongfei Xu, Qiuhui Liu, Josef van Genabith, Deyi Xiong
EMNLP 2021finding

The Transformer translation model is based on the multi-head attention mechanism, which can be parallelized easily. The multi-head attention network performs the scaled dot-product attention function in parallel, empowering the model by jointly attending to information from different representation…

Cited by 2Source ↗PDF ↗Scholar ↗
2021

Mid-Air Hand Gestures for Post-Editing of Machine Translation

Rashad Albo Jamara, Nico Herbig, Antonio Krüger, Josef van Genabith
ACL 2021long

To translate large volumes of text in a globally connected world, more and more translators are integrating machine translation (MT) and post-editing (PE) into their translation workflows to generate publishable quality translations. While this process has been shown to save time and reduce errors,…

Cited by 3Source ↗PDF ↗code ↗Scholar ↗
2021

Modeling Task-Aware MIMO Cardinality for Efficient Multilingual Neural Machine Translation

Hongfei Xu, Qiuhui Liu, Josef van Genabith, Deyi Xiong
ACL 2021short

Neural machine translation has achieved great success in bilingual settings, as well as in multilingual settings. With the increase of the number of languages, multilingual systems tend to underperform their bilingual counterparts. Model capacity has been found crucial for massively multilingual NMT…

Cited by 8Source ↗PDF ↗Scholar ↗
2021

Multi-Head Highly Parallelized LSTM Decoder for Neural Machine Translation

Hongfei Xu, Qiuhui Liu, Josef van Genabith, Deyi Xiong, Meng Zhang
ACL 2021long

One of the reasons Transformer translation models are popular is that self-attention networks for context modelling can be easily parallelized at sequence level. However, the computational complexity of a self-attention network is O(n2), increasing quadratically with sequence length. By contrast, th…

Cited by 15Source ↗PDF ↗Scholar ↗
2021

Probing Word Translations in the Transformer and Trading Decoder for Encoder Layers

Hongfei Xu, Josef van Genabith, Qiuhui Liu, Deyi Xiong
NAACL 2021long

Due to its effectiveness and performance, the Transformer translation model has attracted wide attention, most recently in terms of probing-based approaches. Previous work focuses on using or probing source linguistic features in the encoder. To date, the way word translation evolves in Transformer…

Cited by 13Source ↗PDF ↗Scholar ↗
2020

Efficient Context-Aware Neural Machine Translation with Layer-Wise Weighting and Input-Aware Gating

Hongfei Xu, Deyi Xiong, Josef van Genabith, Qiuhui Liu
IJCAI 2020poster

Existing Neural Machine Translation (NMT) systems are generally trained on a large amount of sentence-level parallel data, and during prediction sentences are independently translated, ignoring cross-sentence contextual information. This leads to inconsistency between translated sentences. In order…

Cited by 0Source ↗PDF ↗Scholar ↗
2020

The Transference Architecture for Automatic Post-Editing

Santanu Pal, Hongfei Xu, Nico Herbig, Sudip Kumar Naskar, Antonio Krüger, Josef van Genabith
COLING 2020main

In automatic post-editing (APE) it makes sense to condition post-editing (pe) decisions on both the source (src) and the machine translated text (mt) as input. This has led to multi-encoder based neural APE approaches. A research challenge now is the search for architectures that best support the ca…

Cited by 7Source ↗PDF ↗code ↗Scholar ↗
2020

Understanding Translationese in Multi-view Embedding Spaces

Koel Dutta Chowdhury, Cristina España-Bonet, Josef van Genabith
COLING 2020main

Recent studies use a combination of lexical and syntactic features to show that footprints of the source language remain visible in translations, to the extent that it is possible to predict the original source language from the translation. In this paper, we focus on embedding-based semantic spaces…

Cited by 14Source ↗PDF ↗Scholar ↗