Papers by Paul McNamee
The Multilingual Microblog Translation Corpus: Improving and Evaluating Translation of User-Generated Text (2022.lrec-1)
Copied to clipboard
| Challenge: | a corpus of over 200,000 microblog translations supports translation of thirteen languages into English . large collections of parallel text, or bitext, are increasingly available in many languages . |
| Approach: | They propose a corpus of over 200,000 microblog posts that supports translation of thirteen languages into English. |
| Outcome: | The proposed corpus contains over 200,000 translations of microblog posts in 13 languages . fine-tuning showed significant improvements in translation quality . |
Platforms for Non-speakers Annotating Names in Any Language (P18-4)
Copied to clipboard
| Challenge: | Traditionally, native speakers of a language have been asked to annotate a corpus in that language. |
| Approach: | They propose two annotation platforms that allow an English speaker to annotate names for any language without knowing the language. |
| Outcome: | The proposed annotations achieved state-of-the-art performance on two surprise languages and ten languages at TAC-KBP EDL2017. |
Dragonfly: Advances in Non-Speaker Annotation for Low Resource Languages (2020.lrec-1)
Copied to clipboard
| Challenge: | Using semantic and contextual information, non-speakers of a language familiar with the Latin script can produce high quality named entity annotations to support construction of . name tagger. |
| Approach: | They propose a procedure for annotating low resource languages using Dragonfly that others can use. |
| Outcome: | The proposed procedure improves the performance of NER models on native speaker and non-speaker annotations in low resource languages. |
Curriculum Learning for Domain Adaptation in Neural Machine Translation (N19-1)
Copied to clipboard
| Challenge: | Neural machine translation (NMT) performance drops when domains do not match and in-domain training data is scarce. |
| Approach: | They propose a curriculum learning approach to adapt generic neural machine translation models to a specific domain. |
| Outcome: | The proposed approach outperforms unadapted and adapted baselines in two domains and two language pairs. |
Benchmarking Neural and Statistical Machine Translation on Low-Resource African Languages (2020.lrec-1)
Copied to clipboard
| Challenge: | a recent study has focused on languages where large amounts of resources are available. |
| Approach: | They benchmark state of the art statistical and neural machine translation systems on Somali and Swahili languages . they find that statistical machine translation and neural translation can perform similarly in low-resource scenarios . |
| Outcome: | The results show that statistical machine translation and neural machine translation perform similarly in low-resource scenarios. |
Tagging Location Phrases in Text (2020.lrec-1)
Copied to clipboard
| Challenge: | a number of studies have focused on detecting named entities in written language. |
| Approach: | They describe a Location Phrase Detection task to detect non-named locations . they use sequential tagging and an annotation approach to create annotated datasets . |
| Outcome: | The proposed task can detect non-named locations in English and Russian news . the authors develop a sequential tagging approach and annotate datasets for English and Russia . |
A Hyperparameter Optimization Toolkit for Neural Machine Translation Research (2023.acl-demo)
Copied to clipboard
| Challenge: | Insufficient tuning of hyperparameters may lead to poor results and exaggerated results . lack of open-source support tools means that the level of rigor in hyperparametric optimization may vary widely. |
| Approach: | They propose a hyperparameter optimization toolkit for neural machine translation that is implemented as a wrapper on top of the open-source Sockeye NMT software. |
| Outcome: | The proposed toolkit is implemented as a wrapper on top of the open-source Sockeye NMT software. |
An Extensive Exploration of Back-Translation in 60 Languages (2023.findings-acl)
Copied to clipboard
| Challenge: | Back-translation has been shown to improve model quality through the creation of synthetic training bitext. |
| Approach: | They use back-translation to train models from 60 languages into English . early studies showed promise of the technique and follow on studies have produced refinements . |
| Outcome: | a new study shows that back-translation improves translation quality in low-resource languages . the results are consistent with previous studies, though there are limitations . |
Whisper-UT: A Unified Translation Framework for Speech and Text (2025.emnlp-main)
Copied to clipboard
Cihan Xiao, Matthew Wiesner, Debashish Chakraborty, Reno Kriz, Keith Cunningham, Kenton Murray, Kevin Duh, Luis Tavarez-Arce, Paul McNamee, Sanjeev Khudanpur
| Challenge: | Encoder-decoder models have achieved remarkable success in speech and text tasks, but efficiently adapting them to diverse uni/multimodal scenarios remains a challenge. |
| Approach: | They propose a framework that leverages lightweight adapters to enable seamless adaptation across tasks. |
| Outcome: | The proposed framework improves speech translation performance through a 2-stage decoding strategy without requiring 3-way parallel data. |