Related papers: Growing Together: Modeling Human Language Learning…
Direct neural machine translation (direct NMT) is a type of NMT system that translates text between two non-English languages. Direct NMT systems often face limitations due to the scarcity of parallel data between non-English language…
Most vision-and-language pretraining research focuses on English tasks. However, the creation of multilingual multimodal evaluation datasets (e.g. Multi30K, xGQA, XVNLI, and MaRVL) poses a new challenge in finding high-quality training data…
Multimodal Large Language Model (MLLM) relies on the powerful LLM to perform multimodal tasks, showing amazing emergent abilities in recent studies, such as writing poems based on an image. However, it is difficult for these case studies to…
Multimodal Large Language Models (MLLMs) have achieved notable success in enhancing translation performance by integrating multimodal information. However, existing research primarily focuses on image-guided methods, whose applicability is…
This paper describes the Stevens Institute of Technology's submission for the WMT 2022 Shared Task: Code-mixed Machine Translation (MixMT). The task consisted of two subtasks, subtask $1$ Hindi/English to Hinglish and subtask $2$ Hinglish…
Retrieval-augmented Neural Machine Translation models have been successful in many translation scenarios. Different from previous works that make use of mutually similar but redundant translation memories~(TMs), we propose a new…
English, as a very high-resource language, enables the pretraining of high-quality large language models (LLMs). The same cannot be said for most other languages, as leading LLMs still underperform for non-English languages, likely due to a…
This work introduces a machine translation task where the output is aimed at audiences of different levels of target language proficiency. We collect a high quality dataset of news articles available in English and Spanish, written for…
Learning multilingual representations of text has proven a successful method for many cross-lingual transfer learning tasks. There are two main paradigms for learning such representations: (1) alignment, which maps different independently…
Neural machine translation is a recently proposed approach to machine translation. Unlike the traditional statistical machine translation, the neural machine translation aims at building a single neural network that can be jointly tuned to…
Despite the success of neural machine translation (NMT), simultaneous neural machine translation (SNMT), the task of translating in real time before a full sentence has been observed, remains challenging due to the syntactic structure…
Despite impressive progress in high-resource settings, Neural Machine Translation (NMT) still struggles in low-resource and out-of-domain scenarios, often failing to match the quality of phrase-based translation. We propose a novel…
Although all-in-one-model multilingual neural machine translation (multilingual NMT) has achieved remarkable progress, the convergence inconsistency in the joint training is ignored, i.e., different language pairs reaching convergence in…
Word alignment which aims to extract lexicon translation equivalents between source and target sentences, serves as a fundamental tool for natural language processing. Recent studies in this area have yielded substantial improvements by…
Large-scale generative models show an impressive ability to perform a wide range of Natural Language Processing (NLP) tasks using in-context learning, where a few examples are used to describe a task to the model. For Machine Translation…
Zero-shot translation aims to translate between language pairs not seen during training in Multilingual Machine Translation (MMT) and is largely considered an open problem. A common, albeit resource-consuming, solution is to add as many…
In this paper, we present a unified model that works for both multilingual and crosslingual prediction of reading times of words in various languages. The secret behind the success of this model is in the preprocessing step where all words…
Assessing the performance of interpreting services is a complex task, given the nuanced nature of spoken language translation, the strategies that interpreters apply, and the diverse expectations of users. The complexity of this task become…
This paper presents a high-quality multilingual dataset for the documentation domain to advance research on localization of structured text. Unlike widely-used datasets for translation of plain text, we collect XML-structured parallel text…
Large language models (LLMs) have significantly advanced various natural language processing (NLP) tasks. Recent research indicates that moderately-sized LLMs often outperform larger ones after task-specific fine-tuning. This study focuses…