Papers by Prashant Mathur
Distilling Multiple Domains for Neural Machine Translation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Neural machine translation is a powerful tool for high-resource domains, but performance suffers when the input domain is low-resourced. |
| Approach: | They propose a framework for training a single multi-domain neural machine translation model that can translate multiple domains without increasing inference time or memory usage. |
| Outcome: | The proposed model improves translation on both high- and low-resource domains over strong multi-domain baselines and is robust under noisy data conditions. |
End-to-End Single-Channel Speaker-Turn Aware Conversational Speech Translation (2023.emnlp-main)
Copied to clipboard
Juan Pablo Zuluaga-Gomez, Zhaocheng Huang, Xing Niu, Rohit Paturi, Sundararajan Srinivasan, Prashant Mathur, Brian Thompson, Marcello Federico
| Challenge: | Conventional speech-to-text translation systems are trained on single-speaker utterances, but they may not be applicable to real-life scenarios where the audio contains conversations by multiple speakers. |
| Approach: | They propose a speaker-turn-aware conversational speech translation model that integrates automatic speech recognition, speech translation and speaker turn detection using special tokens in a serialized labeling format. |
| Outcome: | The proposed model outperforms the reference systems on the multi-speaker condition while attaining comparable performance on the single-speakspeaker conditions. |
Automatic Evaluation and Analysis of Idioms in Neural Machine Translation (2023.eacl-main)
Copied to clipboard
| Challenge: | Neural machine translation (NMT) struggles with the translation of rare multi-word expressions (MWEs). |
| Approach: | They propose a metric for automatically measuring the frequency of literal translation errors without human involvement. |
| Outcome: | The proposed metric measures the frequency of literal translation errors without human involvement with the models trained in different conditions and across a wide range of metrics and test sets. |
Improving Retrieval Augmented Neural Machine Translation by Controlling Source and Fuzzy-Match Interactions (2023.findings-eacl)
Copied to clipboard
| Challenge: | a general-domain model has access to customer or domain specific parallel data at inference time, but not during training. |
| Approach: | They propose a zero-shot adaptation approach where a general-domain model has access to customer or domain specific parallel data at inference time, but not during training. |
| Outcome: | The proposed architecture outperforms existing architectures in two language pairs . it consistently improves BLEU across language pair, domain, and number k of fuzzy matches . |
GFST: Gender-Filtered Self-Training for More Accurate Gender in Translation (2021.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies have focused on gender bias in neural machine translation (NMT) incorrectly gendered translations can reflect or amplify social biases. |
| Approach: | They propose to use a monolingual corpus to generate gender-specific pseudo-parallel corpora and filter them to improve gender translation accuracy. |
| Outcome: | The proposed approach improves gender accuracy without damaging generic quality on translations from English into five languages. |
Training Neural Machine Translation to Apply Terminology Constraints (P19-1)
Copied to clipboard
| Challenge: | Existing methods to integrate domain terminology into neural machine translation (NMT) are brittle when tested in real-world situations. |
| Approach: | They propose a method to inject custom terminology into neural machine translation at run time by using the target side of terminology entries whose source side match the input as decoding-time constraints. |
| Outcome: | The proposed method is faster than state-of-the-art decoding and more efficient than constraint-free decoding. |
Multi-lingual neural title generation for e-Commerce browse pages (N18-3)
Copied to clipboard
| Challenge: | e-Commerce websites are automatically generating millions of browse pages . manual creation of titles is infeasible due to the huge number of browse page types . |
| Approach: | They propose to use sequence-to-sequence models to generate titles for languages . they train the models on multi-lingual data, thereby creating one joint model . |
| Outcome: | The proposed model can generate titles in three different languages, with a focus on low-resource French. |
How to Talk to Language Models: Serialization Strategies for Structured Entity Matching (2025.findings-naacl)
Copied to clipboard
| Challenge: | Entity matching (EM) identifies whether two data records refer to the same entity . however, its performance heavily depends on how structured entities are “talked” through serialized text. |
| Approach: | They propose a novel serialization scheme for entities with complex relations in knowledge graphs based on random walks and use open-source LLMs to encode sampled semantic walks for matching. |
| Outcome: | The proposed scheme achieves leading performance on EM in canonical and heterogeneous KGs. |
Evaluating Robustness to Input Perturbations for Neural Machine Translation (2020.acl-main)
Copied to clipboard
| Challenge: | Recent work has shown that Neural Machine Translation models are brittle to small perturbations in the input. |
| Approach: | They propose to use subword regularization to measure the relative degradation and changes in translation when perturbations are added to the input. |
| Outcome: | The proposed measures show that the models are more robust to perturbations when subword regularization methods are used. |