Search Results for author: Yun-Hsuan Sung

Found 16 papers, 5 papers with code

Transforming LLMs into Cross-modal and Cross-lingual Retrieval Systems

no code implementations2 Apr 2024 Frank Palma Gomez, Ramon Sanabria, Yun-Hsuan Sung, Daniel Cer, Siddharth Dalmia, Gustavo Hernandez Abrego

Our multi-modal LLM-based retrieval system is capable of matching speech and text in 102 languages despite only training on 21 languages.

Machine Translation Retrieval +1

Characterizing Tradeoffs in Language Model Decoding with Informational Interpretations

no code implementations16 Nov 2023 Chung-Ching Chang, William W. Cohen, Yun-Hsuan Sung

We propose a theoretical framework for formulating language model decoder algorithms with dynamic programming and information theory.

Decoder Language Modelling

FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation

1 code implementation5 Oct 2023 Tu Vu, Mohit Iyyer, Xuezhi Wang, Noah Constant, Jerry Wei, Jason Wei, Chris Tar, Yun-Hsuan Sung, Denny Zhou, Quoc Le, Thang Luong

Specifically, we introduce FreshQA, a novel dynamic QA benchmark encompassing a diverse range of question and answer types, including questions that require fast-changing world knowledge as well as questions with false premises that need to be debunked.

Hallucination World Knowledge

KL-Divergence Guided Temperature Sampling

2 code implementations2 Jun 2023 Chung-Ching Chang, David Reitter, Renat Aksitov, Yun-Hsuan Sung

One common approach to mitigate hallucinations is to provide source/grounding documents and the model is trained to produce predictions that bind to and are attributable to the provided source.

Conversational Question Answering Language Modelling +1

CoLT5: Faster Long-Range Transformers with Conditional Computation

no code implementations17 Mar 2023 Joshua Ainslie, Tao Lei, Michiel de Jong, Santiago Ontañón, Siddhartha Brahma, Yury Zemlyanskiy, David Uthus, Mandy Guo, James Lee-Thorp, Yi Tay, Yun-Hsuan Sung, Sumit Sanghai

Many natural language processing tasks benefit from long inputs, but processing long documents with Transformers is expensive -- not only due to quadratic attention complexity but also from applying feedforward and projection layers to every token.

Long-range modeling

Universal Sentence Encoder

23 code implementations29 Mar 2018 Daniel Cer, Yinfei Yang, Sheng-yi Kong, Nan Hua, Nicole Limtiaco, Rhomni St. John, Noah Constant, Mario Guajardo-Cespedes, Steve Yuan, Chris Tar, Yun-Hsuan Sung, Brian Strope, Ray Kurzweil

For both variants, we investigate and report the relationship between model complexity, resource consumption, the availability of transfer task training data, and task performance.

Conversational Response Selection Semantic Textual Similarity +7

Efficient Natural Language Response Suggestion for Smart Reply

no code implementations1 May 2017 Matthew Henderson, Rami Al-Rfou, Brian Strope, Yun-Hsuan Sung, Laszlo Lukacs, Ruiqi Guo, Sanjiv Kumar, Balint Miklos, Ray Kurzweil

This paper presents a computationally efficient machine-learned method for natural language response suggestion.

Conversational Contextual Cues: The Case of Personalization and History for Response Ranking

no code implementations1 Jun 2016 Rami Al-Rfou, Marc Pickett, Javier Snaider, Yun-Hsuan Sung, Brian Strope, Ray Kurzweil

Unlike previous efforts, which focused on modeling messages and responses, we extend the modeling to long context and participant's history.

Cannot find the paper you are looking for? You can Submit a new open access paper.