no code implementations • 2 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.
no code implementations • 16 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.
1 code implementation • 5 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.
2 code implementations • 2 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.
no code implementations • 17 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.
Ranked #1 on Long-range modeling on SCROLLS
no code implementations • 10 Oct 2022 • Cicero Nogueira dos santos, Zhe Dong, Daniel Cer, John Nham, Siamak Shakeri, Jianmo Ni, Yun-Hsuan Sung
The resulting soft knowledge prompts (KPs) are task independent and work as an external memory of the LMs.
1 code implementation • Findings (NAACL) 2022 • Mandy Guo, Joshua Ainslie, David Uthus, Santiago Ontanon, Jianmo Ni, Yun-Hsuan Sung, Yinfei Yang
Recent work has shown that either (1) increasing the input length or (2) increasing model size can improve the performance of Transformer-based neural models.
Ranked #1 on Text Summarization on BigPatent
no code implementations • ACL 2020 • Yinfei Yang, Daniel Cer, Amin Ahmad, Mandy Guo, Jax Law, Noah Constant, Gustavo Hernandez Abrego, Steve Yuan, Chris Tar, Yun-Hsuan Sung, Brian Strope, Ray Kurzweil
We introduce two pre-trained retrieval focused multilingual sentence encoding models, respectively based on the Transformer and CNN model architectures.
no code implementations • WS 2019 • Mandy Guo, Yinfei Yang, Keith Stevens, Daniel Cer, Heming Ge, Yun-Hsuan Sung, Brian Strope, Ray Kurzweil
We explore using multilingual document embeddings for nearest neighbor mining of parallel data.
no code implementations • 22 Feb 2019 • Yinfei Yang, Gustavo Hernandez Abrego, Steve Yuan, Mandy Guo, Qinlan Shen, Daniel Cer, Yun-Hsuan Sung, Brian Strope, Ray Kurzweil
On the UN document-level retrieval task, document embeddings achieve around 97% on P@1 for all experimented language pairs.
no code implementations • WS 2019 • Muthuraman Chidambaram, Yinfei Yang, Daniel Cer, Steve Yuan, Yun-Hsuan Sung, Brian Strope, Ray Kurzweil
A significant roadblock in multilingual neural language modeling is the lack of labeled non-English data.
no code implementations • WS 2018 • Mandy Guo, Qinlan Shen, Yinfei Yang, Heming Ge, Daniel Cer, Gustavo Hernandez Abrego, Keith Stevens, Noah Constant, Yun-Hsuan Sung, Brian Strope, Ray Kurzweil
This paper presents an effective approach for parallel corpus mining using bilingual sentence embeddings.
1 code implementation • WS 2018 • Yinfei Yang, Steve Yuan, Daniel Cer, Sheng-yi Kong, Noah Constant, Petr Pilar, Heming Ge, Yun-Hsuan Sung, Brian Strope, Ray Kurzweil
We present a novel approach to learn representations for sentence-level semantic similarity using conversational data.
23 code implementations • 29 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.
Ranked #2 on Text Classification on TREC-6
Conversational Response Selection Semantic Textual Similarity +7
no code implementations • 1 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.
no code implementations • 1 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.