Related papers: OCR Improves Machine Translation for Low-Resource …
In many humanitarian scenarios, translation into severely low resource languages often does not require a universal translation engine, but a dedicated text-specific translation engine. For example, healthcare records, hygienic procedures,…
Massively multilingual language models such as multilingual BERT offer state-of-the-art cross-lingual transfer performance on a range of NLP tasks. However, due to limited capacity and large differences in pretraining data sizes, there is a…
Machine translation (MT) is an important sub-field of natural language processing that aims to translate natural languages using computers. In recent years, end-to-end neural machine translation (NMT) has achieved great success and has…
Building machine translation (MT) systems for low-resource languages is notably difficult due to the scarcity of high-quality data. Although Large Language Models (LLMs) have improved MT system performance, adapting them to…
Transfer learning from high-resource languages is known to be an efficient way to improve end-to-end automatic speech recognition (ASR) for low-resource languages. Pre-trained or jointly trained encoder-decoder models, however, do not share…
The advent of Multilingual Language Models (MLLMs) and Large Language Models has spawned innovation in many areas of natural language processing. Despite the exciting potential of this technology, its impact on developing high-quality…
The use of subword embedding has proved to be a major innovation in Neural Machine Translation (NMT). It helps NMT to learn better context vectors for Low Resource Languages (LRLs) so as to predict the target words by better modelling the…
We present a novel approach to detecting over and under translations (OT/UT) as part of adequacy error checks in translation evaluation. We do not restrict ourselves to machine translation (MT) outputs and specifically target applications…
Neural machine translation (NMT) for low-resource local languages in Indonesia faces significant challenges, including the need for a representative benchmark and limited data availability. This work addresses these challenges by…
Indian language machine translation performance is hampered due to the lack of large scale multi-lingual sentence aligned corpora and robust benchmarks. Through this paper, we provide and analyse an automated framework to obtain such a…
Monolingual data have been demonstrated to be helpful in improving translation quality of both statistical machine translation (SMT) systems and neural machine translation (NMT) systems, especially in resource-poor or domain adaptation…
Machine translation (MT) plays an important role in benefiting linguists, sociologists, computer scientists, etc. by processing natural language to translate it into some other natural language. And this demand has grown exponentially over…
Training automatic speech recognition (ASR) systems requires large amounts of well-curated paired data. However, human annotators usually perform "non-verbatim" transcription, which can result in poorly trained models. In this paper, we…
Neural Machine Translation (NMT) has obtained state-of-the art performance for several language pairs, while only using parallel data for training. Target-side monolingual data plays an important role in boosting fluency for phrase-based…
Optical Character Recognition (OCR), the task of extracting textual information from scanned documents is a vital and broadly used technology for digitizing and indexing physical documents. Existing technologies perform well for clean…
Neural networks have become the technique of choice for OCR, but many aspects of how and why they deliver superior performance are still unknown. One key difference between current neural network techniques using LSTMs and the previous…
Existing analysis work in machine reading comprehension (MRC) is largely concerned with evaluating the capabilities of systems. However, the capabilities of datasets are not assessed for benchmarking language understanding precisely. We…
This paper explores the potential of context-aware monolingual human evaluation for assessing machine translation (MT) when no source is given for reference. To this end, we compare monolingual with bilingual evaluations (with source text),…
We propose a simple solution to use a single Neural Machine Translation (NMT) model to translate between multiple languages. Our solution requires no change in the model architecture from our base system but instead introduces an artificial…
Good OCR results for historical printings rely on the availability of recognition models trained on diplomatic transcriptions as ground truth, which is both a scarce resource and time-consuming to generate. Instead of having to train a…