AIConfPaper
← Search

David Dale

11 accepted papers

2025

BOUQuET : dataset, Benchmark and Open initiative for Universal Quality Evaluation in Translation

Pierre Andrews, Mikel Artetxe, Mariano Coria Meglioli, Marta R. Costa-juss{\`a}, Joe Chuang, David Dale +13
EMNLP 2025

BOUQuET is a multi-way, multicentric and multi-register/domain dataset and benchmark, and a broader collaborative initiative. This dataset is handcrafted in 8 non-English languages (i.e. Egyptian Arabic and Modern Standard Arabic, French, German, Hindi, Indonesian, Mandarin Chinese, Russian, and Spa

Cited by 0Source ↗PDF ↗Scholar ↗
2025

Improving Language and Modality Transfer in Translation by Character-level Modeling

Ioannis Tsiamas, David Dale, Marta R. Costa-jussà
ACL 2025long

Current translation systems, despite being highly multilingual, cover only 5% of the world’s languages. Expanding language coverage to the long-tail of low-resource languages requires data-efficient methods that rely on cross-lingual and cross-modal knowledge transfer. To this end, we propose a char…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

LCFO: Long Context and Long Form Output Dataset and Benchmarking

Marta R. Costa-jussà, Pierre Andrews, Mariano Coria Meglioli, Joy Chen, Joe Chuang, David Dale +7
ACL 2025finding

This paper presents the Long Context and Form Output (LCFO) benchmark, a novel evaluation framework for assessing gradual summarization and summary expansion capabilities across diverse domains. LCFO consists of long input documents (5k words average length), each of which comes with three summaries…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

Less Mature is More Adaptable for Sentence-level Language Modeling

Abhilasha Sancheti, David Dale, Artyom Kozhevnikov, Maha Elbayad
ACL 2025long

This work investigates sentence-level models (i.e., models that operate at the sentence-level) to study how sentence representations from various encoders influence downstream task performance, and which syntactic, semantic, and discourse-level properties are essential for strong performance. Our ex…

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

BLASER 2.0: a metric for evaluation and quality estimation of massively multilingual speech and text translation

David Dale, Marta R. Costa-jussà
EMNLP 2024finding

We present BLASER 2.0, an automatic metric of machine translation quality which supports both speech and text modalities. Compared to its predecessor BLASER (Chen et al., 2023), BLASER 2.0 is based on better underlying text and speech representations that cover 202 text languages and 57 speech ones…

Cited by 2Source ↗PDF ↗code ↗Scholar ↗
2024

MuTox: Universal MUltilingual Audio-based TOXicity Dataset and Zero-shot Detector

Marta Costa-jussà, Mariano Meglioli, Pierre Andrews, David Dale, Prangthip Hansanti, Elahe Kalbassi +3
ACL 2024findings

Research in toxicity detection in natural language processing for the speech modality (audio-based) is quite limited, particularly for languages other than English. To address these limitations and lay the groundwork for truly multilingual audio-based toxicity detection, we introduce MuTox, the firs…

Cited by 10Source ↗PDF ↗code ↗Scholar ↗
2024

SpeechAlign: A Framework for Speech Translation Alignment Evaluation

Belen Alastruey, Aleix Sant, Gerard I. Gállego, David Dale, Marta R. Costa-jussà
COLING 2024main

Speech-to-Speech and Speech-to-Text translation are currently dynamic areas of research. In our commitment to advance these fields, we present SpeechAlign, a framework designed to evaluate the underexplored field of source-target alignment in speech models. The SpeechAlign framework has two core com…

Cited by 1Source ↗PDF ↗code ↗Scholar ↗
2023

Detecting and Mitigating Hallucinations in Machine Translation: Model Internal Workings Alone Do Well, Sentence Similarity Even Better

David Dale, Elena Voita, Loic Barrault, Marta R. Costa-jussà
ACL 2023long

While the problem of hallucinations in neural machine translation has long been recognized, so far the progress on its alleviation is very little. Indeed, recently it turned out that without artificially encouraging models to hallucinate, previously existing methods fall short and even the standard…

Cited by 60Source ↗PDF ↗code ↗Scholar ↗
2023

HalOmi: A Manually Annotated Benchmark for Multilingual Hallucination and Omission Detection in Machine Translation

David Dale, Elena Voita, Janice Lam, Prangthip Hansanti, Christophe Ropers, Elahe Kalbassi +3
EMNLP 2023long main

Hallucinations in machine translation are translations that contain information completely unrelated to the input. Omissions are translations that do not include some of the input information. While both cases tend to be catastrophic errors undermining user trust, annotated data with these types of…

Cited by 0Source ↗code ↗Scholar ↗
2022

ParaDetox: Detoxification with Parallel Data

Varvara Logacheva, Daryna Dementieva, Sergey Ustyantsev, Daniil Moskovskiy, David Dale, Irina Krotova +2
ACL 2022long

We present a novel pipeline for the collection of parallel data for the detoxification task. We collect non-toxic paraphrases for over 10,000 English toxic sentences. We also show that this pipeline can be used to distill a large existing corpus of paraphrases to get toxic-neutral sentence pairs. We…

Cited by 84Source ↗PDF ↗code ↗Scholar ↗
2021

Text Detoxification using Large Pre-trained Neural Models

David Dale, Anton Voronov, Daryna Dementieva, Varvara Logacheva, Olga Kozlova, Nikita Semenov +1
EMNLP 2021main

We present two novel unsupervised methods for eliminating toxicity in text. Our first method combines two recent ideas: (1) guidance of the generation process with small style-conditional language models and (2) use of paraphrasing models to perform style transfer. We use a well-performing paraphras…

Cited by 71Source ↗PDF ↗code ↗Scholar ↗