Related papers: Dynamic Meta-Metrics: Source-Sentence Conditioned …

Unsupervised neural machine translation(NMT) is associated with noise and errors in synthetic data when executing vanilla back-translations. Here, we explicitly exploits language model(LM) to drive construction of an unsupervised NMT…

Evaluating the performance of Grammatical Error Correction (GEC) models has become increasingly challenging, as large language model (LLM)-based GEC systems often produce corrections that diverge from provided gold references. This…

Mixed-Modal Image Retrieval (MMIR) as a flexible search paradigm has attracted wide attention. However, previous approaches always achieve limited performance, due to two critical factors are seriously overlooked. 1) The contribution of…

Traditional Neural machine translation (NMT) involves a fixed training procedure where each sentence is sampled once during each epoch. In reality, some sentences are well-learned during the initial few epochs; however, using this approach,…

Multimodal machine translation (MMT) aims to improve neural machine translation (NMT) with additional visual information, but most existing MMT methods require paired input of source sentence and image, which makes them suffer from shortage…

We introduce a new, extensive multidimensional quality metrics (MQM) annotated dataset covering 11 language pairs in the biomedical domain. We use this dataset to investigate whether machine translation (MT) metrics which are fine-tuned on…

Large language models (LLMs) have excelled in various NLP tasks, including machine translation (MT), yet most studies focus on sentence-level translation. This work investigates the inherent capability of instruction-tuned LLMs for…

Multi-domain machine translation (MDMT) aims to build a unified model capable of translating content across diverse domains. Despite the impressive machine translation capabilities demonstrated by large language models (LLMs), domain…

We consider two problems of NMT domain adaptation using meta-learning. First, we want to reach domain robustness, i.e., we want to reach high quality on both domains seen in the training data and unseen domains. Second, we want our systems…

The goal of optimization-based meta-learning is to find a single initialization shared across a distribution of tasks to speed up the process of learning new tasks. Conditional meta-learning seeks task-specific initialization to better…

Given multiple source word embeddings learnt using diverse algorithms and lexical resources, meta word embedding learning methods attempt to learn more accurate and wide-coverage word embeddings. Prior work on meta-embedding has repeatedly…

It has been demonstrated that the art of prompt tuning is highly effective in efficiently extracting knowledge from pretrained foundation models, encompassing pretrained language models (PLMs), vision pretrained models, and vision-language…

Commit messages are essential in software development as they serve to document and explain code changes. Yet, their quality often falls short in practice, with studies showing significant proportions of empty or inadequate messages. While…

With the rising human-like precision of Large Language Models (LLMs) in numerous tasks, their utilization in a variety of real-world applications is becoming more prevalent. Several studies have shown that LLMs excel on many standard NLP…

The ability of generative large language models (LLMs) to perform in-context learning has given rise to a large body of research into how best to prompt models for various natural language processing tasks. Machine Translation (MT) has been…

While data augmentation is an important trick to boost the accuracy of deep learning methods in computer vision tasks, its study in natural language tasks is still very limited. In this paper, we present a novel data augmentation method for…

Evaluating machine translation (MT) for low-resource languages poses a persistent challenge, primarily due to the limited availability of high quality reference translations. This issue is further exacerbated in languages with multiple…

The rapid evolution of large language models (LLMs) has transformed conversational agents, enabling complex human-machine interactions. However, evaluation frameworks often focus on single tasks, failing to capture the dynamic nature of…

We investigate the generation of new concepts from combinations of properties as an artificial language develops. To do so, we have developed a new framework for conjunctive concept combination. This framework gives a semantic grounding to…

Large language models (LLMs) have demonstrated strong performance in sentence-level machine translation, but scaling to document-level translation remains challenging, particularly in modeling long-range dependencies and discourse phenomena…