William W. Cohen

research

∙ 08/28/2023

MEMORY-VQ: Compression for Tractable Internet-Scale Memory

Retrieval augmentation is a powerful but expensive method to make langua...

0 Yury Zemlyanskiy, et al. ∙

research

∙ 08/16/2023

Answering Ambiguous Questions with a Database of Questions, Answers, and Revisions

Many open-domain questions are under-specified and thus have multiple po...

0 Haitian Sun, et al. ∙

research

∙ 06/17/2023

GLIMMER: generalized late-interaction memory reranker

Memory-augmentation is a powerful approach for efficiently incorporating...

0 Michiel de Jong, et al. ∙

research

∙ 04/01/2023

Subject-driven Text-to-Image Generation via Apprenticeship Learning

Recent text-to-image generation models like DreamBooth have made remarka...

0 Wenhu Chen, et al. ∙

research

∙ 12/21/2022

Beyond Contrastive Learning: A Variational Generative Model for Multilingual Retrieval

Contrastive learning has been successfully used for retrieval of semanti...

0 John Wieting, et al. ∙

research

∙ 11/22/2022

Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks

Recently, there has been significant progress in teaching language model...

0 Wenhu Chen, et al. ∙

research

∙ 10/06/2022

MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Text

While language Models store a massive amount of world knowledge implicit...

0 Wenhu Chen, et al. ∙

research

∙ 09/29/2022

Re-Imagen: Retrieval-Augmented Text-to-Image Generator

Research on text-to-image generation has witnessed significant progress ...

0 Wenhu Chen, et al. ∙

research

∙ 07/01/2022

QA Is the New KR: Question-Answer Pairs as Knowledge Bases

In this position paper, we propose a new approach to generating a type o...

0 Wenhu Chen, et al. ∙

research

∙ 05/25/2022

Reasoning over Logically Interacted Conditions for Question Answering

Some questions have multiple answers that are not equally correct, i.e. ...

0 Haitian Sun, et al. ∙

research

∙ 12/17/2021

Explain, Edit, and Understand: Rethinking User Study Design for Evaluating Model Explanations

In attempts to "explain" predictions of machine learning models, researc...

0 Siddhant Arora, et al. ∙

research

∙ 10/13/2021

ConditionalQA: A Complex Reading Comprehension Dataset with Conditional Answers

We describe a Question Answering (QA) dataset that contains complex ques...

0 Haitian Sun, et al. ∙

research

∙ 09/29/2021

Multilingual Fact Linking

Knowledge-intensive NLP tasks can benefit from linking natural language ...

0 Keshav Kolluru, et al. ∙

research

∙ 09/09/2021

MATE: Multi-view Attention for Table Transformer Efficiency

This work presents a sparse-attention Transformer architecture for model...

10 Julian Martin Eisenschlos, et al. ∙

research

∙ 06/29/2021

Time-Aware Language Models as Temporal Knowledge Bases

Many facts come with an expiration date, from the name of the President ...

0 Bhuwan Dhingra, et al. ∙

research

∙ 06/01/2021

End-to-End Multihop Retrieval for Compositional Question Answering over Long Documents

Answering complex questions from long documents requires aggregating mul...

0 Haitian Sun, et al. ∙

research

∙ 04/05/2021

What's the best place for an AI conference, Vancouver or ______: Why completing comparative questions is difficult

Although large neural language models (LMs) like BERT can be finetuned t...

0 Avishai Zagoury, et al. ∙

research

∙ 02/14/2021

Reasoning Over Virtual Knowledge Bases With Open Predicate Relations

We present the Open Predicate Query Language (OPQL); a method for constr...

0 Haitian Sun, et al. ∙

research

∙ 12/01/2020

Evaluating Explanations: How much do explanations from the teacher aid students?

While many methods purport to explain predictions by highlighting salien...

8 Danish Pruthi, et al. ∙

research

∙ 10/20/2020

Open Question Answering over Tables and Text

In open question answering (QA), the answer to a question is produced by...

0 Wenhu Chen, et al. ∙

research

∙ 07/02/2020

Facts as Experts: Adaptable and Interpretable Neural Memory over Symbolic Knowledge

Massive language models are the core of modern NLP modeling and have bee...

0 Pat Verga, et al. ∙

research

∙ 04/07/2020

Guessing What's Plausible But Remembering What's True: Accurate Neural Reasoning for Question-Answering

Neural approaches to natural language processing (NLP) often fail at the...

7 Haitian Sun, et al. ∙

research

∙ 02/25/2020

Differentiable Reasoning over a Virtual Knowledge Base

We consider the task of answering complex multi-hop questions using a co...

0 Bhuwan Dhingra, et al. ∙

research

∙ 02/14/2020

Scalable Neural Methods for Reasoning With a Symbolic Knowledge Base

We describe a novel way of representing a symbolic knowledge base (KB) c...

0 William W. Cohen, et al. ∙

research

∙ 12/12/2019

Game Design for Eliciting Distinguishable Behavior

The ability to inferring latent psychological traits from human behavior...

6 Fan Yang, et al. ∙

research

∙ 11/08/2019

Instance-based Transfer Learning for Multilingual Deep Retrieval

Perhaps the simplest type of multilingual transfer learning is instance-...

0 Andrew O. Arnold, et al. ∙

research

∙ 09/13/2019

PubMedQA: A Dataset for Biomedical Research Question Answering

We introduce PubMedQA, a novel biomedical question answering (QA) datase...

0 Qiao Jin, et al. ∙

research

∙ 06/03/2019

Handling Divergent Reference Texts when Evaluating Table-to-Text Generation

Automatically constructed datasets for generating text from semi-structu...

0 Bhuwan Dhingra, et al. ∙

research

∙ 05/24/2019

Differentiable Representations For Multihop Inference Rules

We present efficient differentiable implementations of second-order mult...

0 William W. Cohen, et al. ∙

research

∙ 05/15/2019

Neural Query Language: A Knowledge Base Query Language for Tensorflow

Large knowledge bases (KBs) are useful for many AI tasks, but are diffic...

0 William W. Cohen, et al. ∙

research

∙ 04/21/2019

PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text

We consider open-domain queston answering (QA) where answers are drawn f...

0 Haitian Sun, et al. ∙

research

∙ 04/03/2019

Probing Biomedical Embeddings from Language Models

Contextualized word embeddings derived from pre-trained language models ...

0 Qiao Jin, et al. ∙

research

∙ 01/15/2019

Incremental Reading for Question Answering

Any system which performs goal-directed continual learning must not only...

0 Samira Abnar, et al. ∙

research

∙ 01/09/2019

Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context

Transformer networks have a potential of learning longer-term dependency...

2 Zihang Dai, et al. ∙

research

∙ 09/25/2018

HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering

Existing question answering (QA) datasets fail to train QA systems to pe...

0 Zhilin Yang, et al. ∙

research

∙ 09/04/2018

Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text

Open Domain Question Answering (QA) is evolving from complex pipelined s...

0 Haitian Sun, et al. ∙

research

∙ 06/14/2018

GLoMo: Unsupervisedly Learned Relational Graphs as Transferable Representations

Modern deep transfer learning approaches have mainly focused on learning...

0 Zhilin Yang, et al. ∙

research

∙ 04/24/2018

Semi-Supervised Learning with Declaratively Specified Entropy Constraints

We propose a technique for declaratively specifying strategies for semi-...

0 Haitian Sun, et al. ∙

research

∙ 04/16/2018

Neural Models for Reasoning over Multiple Mentions using Coreference

Many problems in NLP require aggregating information from multiple menti...

0 Bhuwan Dhingra, et al. ∙

research

∙ 11/17/2017

Learning to Organize Knowledge with N-Gram Machines

Deep neural networks (DNNs) had great success on NLP tasks such as langu...

0 Fan Yang, et al. ∙

research

∙ 11/10/2017

Breaking the Softmax Bottleneck: A High-Rank RNN Language Model

We formulate language modeling as a matrix factorization problem, and sh...

0 Zhilin Yang, et al. ∙

research

∙ 07/17/2017

TensorLog: Deep Learning Meets Probabilistic DBs

We present an implementation of a probabilistic first-order logic called...

0 William W. Cohen, et al. ∙

research

∙ 07/12/2017

Quasar: Datasets for Question Answering by Search and Reading

We present two new large-scale datasets aimed at evaluating systems desi...

0 Bhuwan Dhingra, et al. ∙

research

∙ 05/27/2017

Good Semi-supervised Learning that Requires a Bad GAN

Semi-supervised learning methods based on generative adversarial network...

0 Zihang Dai, et al. ∙

research

∙ 03/18/2017

Transfer Learning for Sequence Tagging with Hierarchical Recurrent Networks

Recent papers have shown that neural networks obtain state-of-the-art pe...

0 Zhilin Yang, et al. ∙

research

∙ 03/07/2017

Linguistic Knowledge as Memory for Recurrent Neural Networks

Training recurrent neural networks to model long term dependencies is di...

0 Bhuwan Dhingra, et al. ∙

research

∙ 03/05/2017

Using Graphs of Classifiers to Impose Declarative Constraints on Semi-supervised Learning

We propose a general approach to modeling semi-supervised learning (SSL)...

0 Lidong Bing, et al. ∙

research

∙ 03/02/2017

A Comparative Study of Word Embeddings for Reading Comprehension

The focus of past machine learning research for Reading Comprehension ta...

0 Bhuwan Dhingra, et al. ∙

research

∙ 02/27/2017

Differentiable Learning of Logical Rules for Knowledge Base Reasoning

We study the problem of learning probabilistic first-order logical rules...

0 Fan Yang, et al. ∙

research

∙ 02/07/2017

Semi-Supervised QA with Generative Domain-Adaptive Nets

We study the problem of semi-supervised question answering----utilizing ...

0 Zhilin Yang, et al. ∙

William W. Cohen

Featured Co-authors