Related papers: Towards Debiasing Translation Artifacts
Embeddings play a pivotal role in the efficacy of Large Language Models. They are the bedrock on which these models grasp contextual relationships and foster a more nuanced understanding of language and consequently perform remarkably on a…
Common intermediate language representation in neural machine translation can be used to extend bilingual to multilingual systems by incremental training. In this paper, we propose a new architecture based on introducing an interlingual…
It has been shown that NLI models are usually biased with respect to the word-overlap between premise and hypothesis; they take this feature as a primary cue for predicting the entailment label. In this paper, we focus on an overlooked…
Pairwise ranking methods are the basis of many widely used discriminative training approaches for structure prediction problems in natural language processing(NLP). Decomposing the problem of ranking hypotheses into pairwise comparisons…
The recent shift from dedicated NMT systems to general-purpose LLMs has reshaped machine translation, with LLMs reported to produce more fluent, less literal output than their predecessors. We test whether this shift extends to the…
Current advances in Natural Language Processing (NLP) have made it increasingly feasible to build applications leveraging textual data. Generally, the core of these applications rely on having a good semantic representation of text into…
The remarkable understanding and generation capabilities of large language models (LLMs) have greatly improved translation performance. However, incorrect understanding of the sentence to be translated can degrade translation quality. To…
Studying bias detection and mitigation methods in natural language processing and the particular case of machine translation is highly relevant, as societal stereotypes might be reflected or reinforced by these systems. In this paper, we…
Multilingual representations embed words from many languages into a single semantic space such that words with similar meanings are close to each other regardless of the language. These embeddings have been widely used in various settings,…
The quality of training data is one of the crucial problems when a learning-centered approach is employed. This paper proposes a new method to investigate the quality of a large corpus designed for the recognizing textual entailment (RTE)…
In this paper, we advance the current state-of-the-art method for debiasing monolingual word embeddings so as to generalize well in a multilingual setting. We consider different methods to quantify bias and different debiasing approaches…
Cross-lingual text classification leverages text classifiers trained in a high-resource language to perform text classification in other languages with no or minimal fine-tuning (zero/few-shots cross-lingual transfer). Nowadays,…
How do we perform efficient inference while retaining high translation quality? Existing neural machine translation models, such as Transformer, achieve high performance, but they decode words one by one, which is inefficient. Recent…
Natural Language Processing (NLP) systems learn harmful societal biases that cause them to amplify inequality as they are deployed in more and more situations. To guide efforts at debiasing these systems, the NLP community relies on a…
We investigate the behavior of maps learned by machine translation methods. The maps translate words by projecting between word embedding spaces of different languages. We locally approximate these maps using linear maps, and find that they…
Neural Machine Translation (NMT) systems are typically evaluated using automated metrics that assess the agreement between generated translations and ground truth candidates. To improve systems with respect to these metrics, NLP researchers…
Translated texts are distinctively different from original ones, to the extent that supervised text classification methods can distinguish between them with high accuracy. These differences were proven useful for statistical machine…
Much of human communication depends on implication, conveying meaning beyond literal words to express a wider range of thoughts, intentions, and feelings. For models to better understand and facilitate human communication, they must be…
Many natural language inference (NLI) datasets contain biases that allow models to perform well by only using a biased subset of the input, without considering the remainder features. For instance, models are able to make a classification…
Cross-lingual semantic textual similarity systems estimate the degree of the meaning similarity between two sentences, each in a different language. State-of-the-art algorithms usually employ machine translation and combine vast amount of…