1.6k citations · 4.5k across the 123 of their papers we have counts for
16 papers · 1 filter
DeFINE: DEep Factorized INput Token Embeddings for Neural Sequence Modeling
Sachin Mehta, Rik Koncel-Kedziorski, Mohammad Rastegari +1
For sequence models with large vocabularies, a majority of network parameters lie in the input and output layers. In this work, we describe a new method, DeFINE, for learning deep…
Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering
Akari Asai, Kazuma Hashimoto, Hannaneh Hajishirzi +2
Answering questions that require multi-hop reasoning at web-scale necessitates retrieving multiple evidence documents, one of which often has little lexical or semantic relationshi…
Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering
Sewon Min, Danqi Chen, Luke Zettlemoyer +1
We introduce an approach for open-domain question answering (QA) that retrieves and reads a passage graph, where vertices are passages of text and edges represent relationships tha…
Contextualized Sparse Representations for Real-Time Open-Domain Question Answering
Jinhyuk Lee, Minjoon Seo, Hannaneh Hajishirzi +1
Open-domain question answering can be formulated as a phrase retrieval problem, in which we can expect huge scalability and speed benefit but often suffer from low accuracy due to…
Question Answering is a Format; When is it Useful?
Matt Gardner, Jonathan Berant, Hannaneh Hajishirzi +2
Recent years have seen a dramatic expansion of tasks and datasets posed as question answering, from reading comprehension, semantic role labeling, and even machine translation, to…
A Discrete Hard EM Approach for Weakly Supervised Question Answering
Sewon Min, Danqi Chen, Hannaneh Hajishirzi +1
Many question answering (QA) tasks only provide weak supervision for how the answer should be computed. For example, TriviaQA answers are entities that can be mentioned multiple ti…
Entity, Relation, and Event Extraction with Contextualized Span Representations
David Wadden, Ulme Wennberg, Yi Luan +1
We examine the capabilities of a unified, multi-task framework for three information extraction tasks: named entity recognition, relation extraction, and event extraction. Our fram…
Mixture Content Selection for Diverse Sequence Generation
Jaemin Cho, Minjoon Seo, Hannaneh Hajishirzi
Generating diverse sequences is important in many NLP applications such as question generation or summarization that exhibit semantically one-to-many relationships between source a…
Potential-Based Advice for Stochastic Policy Learning
Baicen Xiao, Bhaskar Ramasubramanian, Andrew Clark +3
This paper augments the reward received by a reinforcement learning agent with potential functions in order to help the agent learn (possibly stochastic) optimal policies. We show…
Multi-hop Reading Comprehension through Question Decomposition and Rescoring
Sewon Min, Victor Zhong, Luke Zettlemoyer +1
Multi-hop Reading Comprehension (RC) requires reasoning and aggregation across several paragraphs. We propose a system for multi-hop RC that decomposes a compositional question int…
Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Index
Minjoon Seo, Jinhyuk Lee, Tom Kwiatkowski +3
Existing open-domain question answering (QA) models are not suitable for real-time usage because they need to process several long documents on-demand for every input query. In thi…
Compositional Questions Do Not Necessitate Multi-hop Reasoning
Sewon Min, Eric Wallace, Sameer Singh +3
Multi-hop reading comprehension (RC) questions are challenging because they require reading and reasoning over multiple paragraphs. We argue that it can be difficult to construct l…
DiCENet: Dimension-wise Convolutions for Efficient Networks
Sachin Mehta, Hannaneh Hajishirzi, Mohammad Rastegari
We introduce a novel and generic convolutional unit, DiCE unit, that is built using dimension-wise convolutions and dimension-wise fusion. The dimension-wise convolutions apply lig…
MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms
Aida Amini, Saadia Gabriel, Peter Lin +3
We introduce a large-scale dataset of math word problems and an interpretable neural math problem solver that learns to map problems to operation programs. Due to annotation challe…
A General Framework for Information Extraction using Dynamic Span Graphs
Yi Luan, Dave Wadden, Luheng He +3
We introduce a general framework for several information extraction tasks that share span representations using dynamically constructed span graphs. The graphs are constructed by s…
Text Generation from Knowledge Graphs with Graph Transformers
Rik Koncel-Kedziorski, Dhanush Bekal, Yi Luan +2
Generating texts which express complex ideas spanning multiple sentences requires a structured representation of their content (document plan), but these representations are prohib…