Papers by Prathyusha Jwalapuram
Pronoun-Targeted Fine-tuning for NMT with Hybrid Losses (2020.emnlp-main)
Copied to clipboard
| Challenge: | Popular machine translation model training uses backtranslation to improve BLEU scores . we use generative-discriminative hybrid losses to fine-tune a trained model . |
| Approach: | They propose a class of conditional generative-discriminative hybrid losses to fine-tune a machine translation model. |
| Outcome: | The proposed model improves on a sentence-level and contextual model without additional data. |
Pulling Out All The Full Stops: Punctuation Sensitivity in Neural Machine Translation and Evaluation (2023.findings-acl)
Copied to clipboard
| Challenge: | Several studies have documented the sensitivity of machine translation models to noise, including spelling errors and dialects. |
| Approach: | They propose to test machine translation systems for punctuation sensitivity by performing sentence-final perturbation tests with full stops, exclamation and questions marks. |
| Outcome: | The proposed tests show that commercial translation systems are vulnerable to single punctuation insertion or deletion, resulting in unreliable translations. |
Rethinking Self-Supervision Objectives for Generalizable Coherence Modeling (2022.acl-long)
Copied to clipboard
| Challenge: | Prior work on text generation models focused on new architectures for permuted document tasks. |
| Approach: | They propose to use a basic model architecture to improve coherence evaluation of machine generated text. |
| Outcome: | The proposed model improves on a task-independent test set and shows significant improvements in coherence evaluations of downstream tasks. |
Rethinking Coherence Modeling: Synthetic vs. Downstream Tasks (2021.eacl-main)
Copied to clipboard
| Challenge: | Coherence models are typically evaluated only on synthetic tasks, which may not be representative of their performance in downstream applications. |
| Approach: | They compare models' performance on synthetic sentences with those on retrieval-based dialog. |
| Outcome: | The proposed models perform poorly on synthetic sentences and retrieval-based dialog tasks. |
A Unified Linear-Time Framework for Sentence-Level Discourse Parsing (P19-1)
Copied to clipboard
| Challenge: | a new neural framework for sentence-level discourse analysis is proposed . a discourse segmenter and a parser are based on pointer networks and operate in linear time . |
| Approach: | They propose a neural framework for sentence-level discourse analysis in accordance with Rhetorical Structure Theory . they use a discourse segmenter and a parser to construct a discursive tree in a top-down fashion . |
| Outcome: | The proposed framework surpasses previous approaches on both tasks and human agreement on both. |
Evaluating Pronominal Anaphora in Machine Translation: An Evaluation Measure and a Test Suite (D19-1)
Copied to clipboard
| Challenge: | Currently, machine translation is performed at the level of individual sentences, in isolation from the rest of the document. |
| Approach: | They propose a dataset that can be used as a test suite for pronoun translation . they propose an evaluation measure to differentiate good and bad pronounce translations . |
| Outcome: | The proposed dataset can be used as a test suite for pronoun translation in English . it covers multiple source languages and different pronouner errors drawn from real system translations . |