no code implementations • NAACL (DeeLIO) 2021 • Vidhisha Balachandran, Bhuwan Dhingra, Haitian Sun, Michael Collins, William Cohen
We create a subset of the NQ data, Factual Questions (FQ), where the questions have evidence in the KB in the form of paths that link question entities to answer entities but still must be answered using text, to facilitate further research into KB integration methods.
no code implementations • 3 Jan 2024 • Hexiang Hu, Kelvin C. K. Chan, Yu-Chuan Su, Wenhu Chen, Yandong Li, Kihyuk Sohn, Yang Zhao, Xue Ben, Boqing Gong, William Cohen, Ming-Wei Chang, Xuhui Jia
We introduce *multi-modal instruction* for image generation, a task representation articulating a range of generation intents with precision.
no code implementations • 25 Jan 2023 • Michiel de Jong, Yury Zemlyanskiy, Nicholas FitzGerald, Joshua Ainslie, Sumit Sanghai, Fei Sha, William Cohen
Retrieval-augmented language models such as Fusion-in-Decoder are powerful, setting the state of the art on a variety of knowledge-intensive tasks.
no code implementations • 15 Dec 2022 • Michiel de Jong, Yury Zemlyanskiy, Joshua Ainslie, Nicholas FitzGerald, Sumit Sanghai, Fei Sha, William Cohen
Fusion-in-Decoder (FiD) is a powerful retrieval-augmented language model that sets the state-of-the-art on many knowledge-intensive NLP tasks.
Ranked #3 on Question Answering on WebQuestions
no code implementations • 10 Apr 2022 • Wenhu Chen, Pat Verga, Michiel de Jong, John Wieting, William Cohen
Retrieval augmented language models have recently become the standard for knowledge intensive tasks.
1 code implementation • ICLR 2022 • Michiel de Jong, Yury Zemlyanskiy, Nicholas FitzGerald, Fei Sha, William Cohen
We propose to address this problem by integrating a semi-parametric representation of a large text corpus into a Transformer model as a source of factual knowledge.
Ranked #1 on Passage Retrieval on EntityQuestions
no code implementations • NAACL 2021 • Pat Verga, Haitian Sun, Livio Baldini Soares, William Cohen
Past research has demonstrated that large neural language models (LMs) encode surprising amounts of factual information: however, augmenting or modifying this information requires modifying a corpus and retraining, which is computationally expensive.
1 code implementation • 31 Jan 2019 • Yifeng Tao, Chunhui Cai, William Cohen, Xinghua Lu
Here, we present a deep neural network model with encoder-decoder architecture, referred to as genomic impact transformer (GIT), to infer the functional impact of SGAs on cellular signaling systems through modeling the statistical relationships between SGA events and differentially expressed genes (DEGs) in tumors.
no code implementations • WS 2018 • Qiao Jin, Bhuwan Dhingra, William Cohen, Xinghua Lu
There are millions of articles in PubMed database.
no code implementations • WS 2018 • Balach, Vidhisha ran, Dheeraj Rajagopal, Rose Catherine Kanjirathinkal, William Cohen
One way to test a person{'}s knowledge of a domain is to ask them to define domain-specific terms.
no code implementations • 12 Jul 2017 • Rose Catherine, Kathryn Mazaitis, Maxine Eskenazi, William Cohen
Explainable recommendation is an important task.
2 code implementations • 7 Apr 2017 • Rose Catherine, William Cohen
For example, a recent model, DeepCoNN, uses neural nets to learn one latent representation for the text of all reviews written by a target user, and a second latent representation for the text of all reviews for a target item, and then combines these latent representations to obtain state-of-the-art performance on recommendation tasks.
no code implementations • 20 Mar 2016 • Zhilin Yang, Ruslan Salakhutdinov, William Cohen
We present a deep hierarchical recurrent neural network for sequence tagging.
no code implementations • 4 Aug 2015 • Zhilin Yang, Jie Tang, William Cohen
GenVector leverages large-scale unlabeled data with embeddings and represents data of two modalities---i. e., social network users and knowledge concepts---in a shared latent topic space.
no code implementations • 10 Oct 2013 • Partha Pratim Talukdar, William Cohen
Graph-based Semi-supervised learning (SSL) algorithms have been successfully used in a large number of applications.