Contrastive data and learning for natural language processing
Current NLP models heavily rely on effective representation learning algorithms. Contrastive
learning is one such technique to learn an embedding space such that similar data sample …
learning is one such technique to learn an embedding space such that similar data sample …
Mitigating Hallucinations and Off-target Machine Translation with Source-Contrastive and Language-Contrastive Decoding
Hallucinations and off-target translation remain unsolved problems in machine translation,
especially for low-resource languages and massively multilingual models. In this paper, we …
especially for low-resource languages and massively multilingual models. In this paper, we …
Multi-level contrastive learning for script-based character understanding
In this work, we tackle the scenario of understanding characters in scripts, which aims to
learn the characters' personalities and identities from their utterances. We begin by …
learn the characters' personalities and identities from their utterances. We begin by …
ACES: Translation accuracy challenge sets for evaluating machine translation metrics
As machine translation (MT) metrics improve their correlation with human judgement every
year, it is crucial to understand the limitations of such metrics at the segment level …
year, it is crucial to understand the limitations of such metrics at the segment level …
Text style transfer with contrastive transfer pattern mining
Text style transfer (TST) is an important task in natural language generation, which aims to
alter the stylistic attributes (eg, sentiment) of a sentence and keep its semantic meaning …
alter the stylistic attributes (eg, sentiment) of a sentence and keep its semantic meaning …
Revisiting commonsense reasoning in machine translation: Training, evaluation and challenge
The ability of commonsense reasoning (CR) decides whether a neural machine translation
(NMT) model can move beyond pattern recognition. Despite the rapid advancement of NMT …
(NMT) model can move beyond pattern recognition. Despite the rapid advancement of NMT …
As little as possible, as much as necessary: Detecting over-and undertranslations with contrastive conditioning
J Vamvas, R Sennrich - arXiv preprint arXiv:2203.01927, 2022 - arxiv.org
Omission and addition of content is a typical issue in neural machine translation. We
propose a method for detecting such phenomena with off-the-shelf translation models. Using …
propose a method for detecting such phenomena with off-the-shelf translation models. Using …
Quantifying the plausibility of context reliance in neural machine translation
Establishing whether language models can use contextual information in a human-plausible
way is important to ensure their safe adoption in real-world settings. However, the questions …
way is important to ensure their safe adoption in real-world settings. However, the questions …
Machine translation meta evaluation through translation accuracy challenge sets
Recent machine translation (MT) metrics calibrate their effectiveness by correlating with
human judgement. However, these results are often obtained by averaging predictions …
human judgement. However, these results are often obtained by averaging predictions …
With a little help from the authors: Reproducing human evaluation of an MT error detector
This work presents our efforts to reproduce the results of the human evaluation experiment
presented in the paper of Vamvas and Sennrich (2022), which evaluated an automatic …
presented in the paper of Vamvas and Sennrich (2022), which evaluated an automatic …