Papers by Sneha Kudugunta

7 papers
Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference (2021.findings-emnlp)

Copied to clipboard

Challenge: Sparse Mixture-of-Experts (MoE) is a successful approach for scaling multilingual translation models to billions of parameters without a proportional increase in training computation.
Approach: They propose to use a task-level routing approach to extract smaller, ready-to-deploy sub-networks from large sparse models by ignoring distillation.
Outcome: Experiments on WMT and a web-scale dataset show that task-level routing outperforms token-level MoE models by +1.0 BLEU on average across 30 language pairs.
MiTTenS: A Dataset for Evaluating Gender Mistranslation (2024.emnlp-main)

Copied to clipboard

Challenge: Existing studies on gender mistranslation in translation systems have highlighted the problem . a dataset of 26 languages is presented to measure the extent of such errors .
Approach: They propose a dataset that measures the extent of gender mistranslation in translation systems . they use handcrafted passages that target known failure patterns and synthetically generated passages .
Outcome: The proposed dataset covers 26 languages from a variety of language families and scripts, including several traditionally under-represented in digital resources.
Investigating Multilingual NMT Representations at Scale (D19-1)

Copied to clipboard

Challenge: Multilingual Neural Machine Translation models have shown success in transfer learning settings, but their mode of transfer remains elusive.
Approach: They propose to use a representation similarity framework to compare multilingual representations using a SVCCA representation similar to the previous work.
Outcome: The proposed model can be used to compare representations across languages and layers.
BUFFET: Benchmarking Large Language Models for Few-shot Cross-lingual Transfer (2024.naacl-long)

Copied to clipboard

Challenge: Recent advances in few-shot generalization in natural language processing focus on English.
Approach: They propose a benchmark that unifies 15 diverse tasks across 54 languages in a sequence-to-sequence format and provides a fixed set of few-shot examples and instructions.
Outcome: The proposed framework unifies 15 diverse tasks across 54 languages in a sequence-to-sequence format and provides a fixed set of few-shot examples and instructions.
MURAL: Multimodal, Multitask Representations Across Languages (2021.findings-emnlp)

Copied to clipboard

Challenge: Image-caption pairs and translation pairs provide the means to learn deep representations of and connections between languages.
Approach: They propose a dual encoder that integrates image-text matching and translation pairs to solve two tasks by learning from billions of pairs.
Outcome: The proposed encoder outperforms ALIGN's cross-modal retrieval performance on well-resourced languages and significantly improves on under-resource languages.
Leveraging Monolingual Data with Self-Supervision for Multilingual Neural Machine Translation (2020.acl-main)

Copied to clipboard

Challenge: Existing multilingual NMT approaches do not utilize the abundance of monolingual data, especially in low-resource languages.
Approach: They propose to combine monolingual data with self-supervision to pre-train translation models and fine-tune on small amounts of supervised data.
Outcome: The proposed approach improves translation quality of low-resource languages and zero-shot translation quality.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations