Papers by Matt Post
Recovering document annotations for sentence-level bitext (2024.findings-acl)
Copied to clipboard
| Challenge: | In machine translation, historical models were incapable of handling longer contexts, so the lack of document-level datasets was less noticeable. |
| Approach: | They propose a document-level filtering technique that discards document- level metadata. |
| Outcome: | The proposed method improves translation without degradation of sentence-level translation. |
Navigating the Metrics Maze: Reconciling Score Magnitudes and Accuracies (2024.acl-long)
Copied to clipboard
| Challenge: | a decade ago a single metric, BLEU, governed progress in machine translation research. |
| Approach: | They investigate the "dynamic range" of a number of modern machine translation metrics to provide a collective understanding of differences in scores . they use a large dataset to discover deltas at which metrics achieve system-level differences that are meaningful to humans . |
| Outcome: | The proposed method is more stable than statistical p-values in regards to testset size. |
A Discriminative Neural Model for Cross-Lingual Word Alignment (D19-1)
Copied to clipboard
| Challenge: | a novel word alignment model for machine translation has been developed for a number of languages . explicit word-to-word alignments have largely been lost in neural MT systems . |
| Approach: | They propose a discriminative word alignment model which integrates into a Transformer-based machine translation model. |
| Outcome: | The proposed model performs better on Chinese and Arabic alignments than standard models. |
The Johns Hopkins University Bible Corpus: 1600+ Tongues for Typological Exploration (2020.lrec-1)
Copied to clipboard
Arya D. McCarthy, Rachel Wicks, Dylan Lewis, Aaron Mueller, Winston Wu, Oliver Adams, Garrett Nicolai, Matt Post, David Yarowsky
| Challenge: | Our corpus spans 1611 diverse written languages, with constituents of more than 90 language families. |
| Approach: | They propose to scrape and merge online resources and merge them with existing corpora to create a verse-parallel scheme for all translations. |
| Outcome: | The results show that the Bible provides high coverage of core vocabulary. |
Automatic Machine Translation Evaluation in Many Languages via Zero-Shot Paraphrasing (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing metrics for machine translation evaluation are causing the correlation between human judgments and automatic metrics to break down. |
| Approach: | They propose to train a multilingual NMT system to score machine translation output with a sequence-to-sequence paraphraser, conditioned on a human reference. |
| Outcome: | The proposed model outperforms or statistically ties with all prior metrics on the WMT 2019 segment-level shared metrics task in all languages (excluding Gujarati where the model had no training data). |
A Study in Improving BLEU Reference Coverage with Diverse Automatic Paraphrasing (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Using neural paraphrasing techniques, we investigate whether automatically generating additional *diverse* references can provide better coverage of the space of valid translations. |
| Approach: | They propose to use neural paraphrasing techniques to generate additional references that provide better coverage of the space of valid translations. |
| Outcome: | The proposed approach beats human paraphrases in the BLEU evaluation. |
PEAR: Pairwise Evaluation for Automatic Relative Scoring in Machine Translation (2026.acl-long)
Copied to clipboard
| Challenge: | PEAR is a supervised quality estimation metric that reframes reference-free machine translation evaluation as a graded pairwise comparison. |
| Approach: | They propose to use a supervised quality estimation metric family to reframe machine translation evaluation as a graded pairwise comparison. |
| Outcome: | The proposed metric outperforms strictly matched single-candidate QE baselines on the WMT24 meta-evaluation benchmark. |
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. |
Simulated multiple reference training improves low-resource machine translation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing valid translations for a given sentence are limited by a single reference translation, causing data sparsity in low-resource settings. |
| Approach: | They propose a method that approximates the full space of possible translations by sampling a paraphrase of the reference sentence from a MT model and training it to predict the paraphraser’s distribution over possible tokens. |
| Outcome: | The proposed method improves in low-resource settings and is complementary to back-translation. |
SLIDE: Reference-free Evaluation for Machine Translation using a Sliding Document Window (2024.naacl-short)
Copied to clipboard
| Challenge: | prevailing evaluation methods for machine translation metrics are at the sentence-level . but there are many linguistic phenomena that cannot be translated without context . |
| Approach: | They propose a metric that leverages a moving window that slides over a document to feed it into a quality estimation model. |
| Outcome: | The proposed metric obtains significantly higher pairwise system accuracy than its sentence-level baseline. |
Multilingual Pixel Representations for Translation and Effective Cross-lingual Transfer (2023.emnlp-main)
Copied to clipboard
| Challenge: | Recent work shows that pixel representations can be finetuned across scripts without vocabulary extensions, adapters, or transliteration. |
| Approach: | They propose to use pixel representations to train multilingual machine translation models . they explore parameter sharing within and across scripts to better understand where they lead to positive transfer . |
| Outcome: | The proposed model improves on two multilingual datasets with different language coverage compared to subword embeddings . the proposed model can be finetuned cross-lingually or to unseen scripts, and is more data-efficient than other alternatives such as vocabulary expansion . |
Improved Lexically Constrained Decoding for Translation and Monolingual Rewriting (N19-1)
Copied to clipboard
J. Edward Hu, Huda Khayrallah, Ryan Culkin, Patrick Xia, Tongfei Chen, Matt Post, Benjamin Van Durme
| Challenge: | Lexically-constrained sequence decoding allows for explicit positive or negative phrase-based constraints to be placed on target output strings in machine translation or monolingual text rewriting tasks. |
| Approach: | They propose a vectorized dynamic beam allocation algorithm which extends work in lexically-constrained decoding to work with batching. |
| Outcome: | The proposed method improves on natural language inference, question answering and machine translation tasks by fivefold . |
SALTED: A Framework for SAlient Long-tail Translation Error Detection (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Traditional machine translation metrics are insensitive to the long tail of behavioral problems. |
| Approach: | They propose a specification-based framework for behavioral testing of NMT models . they use high-precision detectors that flag errors between a source sentence and output . |
| Outcome: | The proposed framework provides a reliable view of problems that were previously invisible. |
Levenshtein Training for Word-level Quality Estimation (2021.emnlp-main)
Copied to clipboard
| Challenge: | a novel scheme to perform word-level quality estimation is proposed for word-based quality estimation . authors propose a two-stage transfer learning procedure on augmented and human data . a Levenshtein Transformer can learn to post-edit without explicit supervision. |
| Approach: | They propose a novel scheme to use a Levenshtein Transformer to perform word-level quality estimation. |
| Outcome: | The proposed method performs better under data-constrained and unconstrained conditions than existing methods. |
A unified approach to sentence segmentation of punctuated text in many languages (2021.acl-long)
Copied to clipboard
| Challenge: | Existing tools for segmenting punctuated text in many languages are limited in their language coverage and evaluation is ad hoc. |
| Approach: | They propose a new context-based modeling approach that can be trained on noisily-annotated data. |
| Outcome: | The proposed model exceeds baselines set by existing methods on English corpora and performs well on average on new multilingual evaluation set. |
PyMarian: Fast Neural Machine Translation and Evaluation in Python (2024.emnlp-demo)
Copied to clipboard
| Challenge: | a Python interface to Marian NMT is available in PyPI via pip install pymarian . the interface provides a speedup factor of up to 7.8 the existing implementations . |
| Approach: | They propose a Python interface to Marian NMT, a C++-based training and inference toolkit for sequence-to-sequence models. |
| Outcome: | The proposed interface enables models trained with Marian to be connected to Python tools with a speedup factor of up to 7.8 the existing implementations. |
Do GPTs Produce Less Literal Translations? (2023.acl-short)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are general-purpose language models capable of many natural language generation or understanding tasks. |
| Approach: | They investigate how LLMs differ qualitatively from standard Neural Machine Translation models by measuring literalness and monotonicity. |
| Outcome: | The proposed models achieve close to state-of-the-art translation performance under few-shot prompting . the results are backed up by human evaluations and a newer MT quality metrics . |
Robust Open-Vocabulary Translation from Visual Text Representations (2021.emnlp-main)
Copied to clipboard
| Challenge: | MT models have discrete vocabularies and often use subword segmentation to achieve an ‘open vocabulary’. |
| Approach: | They propose to use visual text representations to create continuous vocabularies by processing visually rendered text with sliding windows. |
| Outcome: | The proposed models achieve 25.9 BLEU on character permuted German–English task, compared with traditional models on smaller and larger datasets. |
Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation (N18-1)
Copied to clipboard
| Challenge: | Existing approaches to neural machine translation have computational complexities that are either linear or exponential in the number of constraints. |
| Approach: | They propose an algorithm for lexically constrained decoding with a complexity of O(1) in the number of constraints. |
| Outcome: | The proposed algorithm can place constraints and improve results in simulated post-editing tasks. |
Membership Inference Attacks on Sequence-to-Sequence Models: Is My Data In Your Machine Translation System? (2020.tacl-1)
Copied to clipboard
| Challenge: | Data privacy is an important issue for “machine learning as a service” providers. |
| Approach: | They propose an attack on membership inference attacks using a sequence-to-sequence model and a machine translation dataset to investigate the feasibility of a privacy attack. |
| Outcome: | The proposed model can infer sentence-level membership from the output of the model, but it is difficult to infer it. |