Related papers: Unify word-level and span-level tasks: NJUNLP's Pa…

While many languages possess processes of joining two or more words to create compound words, previous studies have been typically limited only to languages with excessively productive compound formation (e.g., German, Dutch) and there is…

Quality Estimation (QE) models have the potential to change how we evaluate and maybe even train machine translation models. However, these models still lack the robustness to achieve general adoption. We show that State-of-the-art QE…

Sentence-level classification and sequential labeling are two fundamental tasks in language understanding. While these two tasks are usually modeled separately, in reality, they are often correlated, for example in intent classification and…

Quality Estimation (QE) aims to assess the quality of machine translation (MT) outputs without relying on reference translations, making it essential for real-world, large-scale MT evaluation. Large Language Models (LLMs) have shown…

The Unlearning Sensitive Content from Large Language Models task aims to remove targeted datapoints from trained models while minimally affecting their general knowledge. In our work, we leverage parameter-efficient, gradient-based…

Neural machine translation (NMT) has arguably achieved human level parity when trained and evaluated at the sentence-level. Document-level neural machine translation has received less attention and lags behind its sentence-level…

In this paper, we propose a methodology for task 10 of SemEval23, focusing on detecting and classifying online sexism in social media posts. The task is tackling a serious issue, as detecting harmful content on social media platforms is…

Ensembling various LLMs to unlock their complementary potential and leverage their individual strengths is highly valuable. Previous studies typically focus on two main paradigms: sample-level and token-level ensembles. Sample-level…

In this report, we present our submission to the WMT 2022 Metrics Shared Task. We build our system based on the core idea of UNITE (Unified Translation Evaluation), which unifies source-only, reference-only, and source-reference-combined…

Subword segmenters like BPE operate as a preprocessing step in neural machine translation and other (conditional) language models. They are applied to datasets before training, so translation or text generation quality relies on the quality…

For different language pairs, word-level neural machine translation (NMT) models with a fixed-size vocabulary suffer from the same problem of representing out-of-vocabulary (OOV) words. The common practice usually replaces all these rare or…

Compounded words are a challenge for NLP applications such as machine translation (MT). We introduce methods to learn splitting rules from monolingual and parallel corpora. We evaluate them against a gold standard and measure their impact…

Machine Translation Quality Estimation (MTQE) is the task of estimating the quality of machine-translated text in real time without the need for reference translations, which is of great importance for the development of MT. After two…

Multilingual Large Language Models (LLMs) struggle with cross-lingual tasks due to data imbalances between high-resource and low-resource languages, as well as monolingual bias in pre-training. Existing methods, such as bilingual…

Evaluating LLMs and text-to-image models is a computationally intensive task often overlooked. Efficient evaluation is crucial for understanding the diverse capabilities of these models and enabling comparisons across a growing number of…

Large Language Models (LLMs) have demonstrated impressive performance on a wide range of natural language processing (NLP) tasks, primarily through in-context learning (ICL). In ICL, the LLM is provided with examples that represent a given…

We describe an unsupervised method to create pseudo-parallel corpora for machine translation (MT) from unaligned text. We use multilingual BERT to create source and target sentence embeddings for nearest-neighbor search and adapt the model…

This paper describes our system for SemEval-2021 Task 5 on Toxic Spans Detection. We developed ensemble models using BERT-based neural architectures and post-processing to combine tokens into spans. We evaluated several pre-trained language…

Recent state-of-the-art language models utilize a two-phase training procedure comprised of (i) unsupervised pre-training on unlabeled text, and (ii) fine-tuning for a specific supervised task. More recently, many studies have been focused…

It is known that a deep neural network model pre-trained with large-scale data greatly improves the accuracy of various tasks, especially when there are resource constraints. However, the information needed to solve a given task can vary,…