Papers by Mihir Kale

7 papers
TicketTalk: Toward human-level performance with end-to-end, transaction-based dialog systems (2021.acl-long)

Copied to clipboard

Challenge: TicketTalk dataset with 23,789 annotated dialogs is a data-driven, end-to-end approach to transaction-based dialog systems that performs at near-human levels in terms of verbal response quality and factual grounding accuracy.
Approach: They propose a data-driven, end-to-end approach to transaction-based dialog systems that performs at near-human levels in terms of verbal response quality and factual grounding accuracy.
Outcome: The proposed model generates verbal responses and API call predictions on a movie ticketing dialog dataset with 23,789 annotated conversations.
nmT5 - Is parallel data still relevant for pre-training massively multilingual language models? (2021.acl-short)

Copied to clipboard

Challenge: Recent studies have shown that cross-lingual transfer learning in pre-trained multilingual models could be improved further by incorporating parallel data.
Approach: They propose to integrate parallel data into mT5 pre-training to improve results on downstream multilingual and cross-lingual tasks.
Outcome: The proposed model improves cross-lingual transfer significantly in small fine-tuning datasets and small model sizes.
XTREME-UP: A User-Centric Scarce-Data Benchmark for Under-Represented Languages (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing datasets are often informed by established research directions in the NLP community.
Approach: They propose a benchmark to evaluate the capabilities of language models across 88 under-represented languages over 9 key user-centric technologies including ASR, OCR, MT, and information access tasks.
Outcome: The proposed benchmark evaluates the capabilities of language models across 88 under-represented languages over 9 key user-centric technologies including ASR, OCR, MT, and information access tasks.
Template Guided Text Generation for Task-Oriented Dialogue (2020.emnlp-main)

Copied to clipboard

Challenge: a new study examines the use of templates to generate natural language utterances for a large number of APIs.
Approach: They propose a schema-guided approach which conditions the generation on a natural language schema.
Outcome: The proposed method improves over strong baselines, is robust to out-of-domain inputs and shows improved sample efficiency.
ByT5: Towards a Token-Free Future with Pre-trained Byte-to-Byte Models (2022.tacl-1)

Copied to clipboard

Challenge: a number of pre-trained language models use sequences of tokens corresponding to word units . token-free models that operate directly on raw text have many advantages .
Approach: They propose a standard Transformer architecture that can be used to process byte sequences . they also characterize trade-offs in terms of parameter count, training FLOPs, and inference speed .
Outcome: The proposed model is more robust to noise and more robust on spelling and pronunciation tasks.
mT5: A Massively Multilingual Pre-trained Text-to-Text Transformer (2021.naacl-main)

Copied to clipboard

Challenge: Current natural language processing pipelines often use transfer learning, where a model is pre-trained on a data-rich task before being fine-tuned on . this significantly limits their use given that roughly 80% of the world population does not speak English.
Approach: They introduce a multilingual variant of T5 that was pre-trained on a new Common Crawl-based dataset covering 101 languages.
Outcome: The proposed model achieves state-of-the-art on multilingual benchmarks and a simple technique to prevent accidental translation in the zero-shot setting.
Improving Compositional Generalization with Self-Training for Data-to-Text Generation (2022.acl-long)

Copied to clipboard

Challenge: Data-to-text generation focuses on generating fluent natural language responses from structured meaning representations (MRs).
Approach: They propose a template-based input representation that greatly improves the model’s generalization capability.
Outcome: The proposed model improves tree accuracy by 46%+ and reduces slot error rates by 73%+ over the strong baselines on SGD and Weather benchmarks.

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