University of Washington, NAVER
Author pages are created from data sourced from our academic publisher partnerships and public sources.
Share This Author
Bidirectional Attention Flow for Machine Comprehension
- Minjoon Seo, Aniruddha Kembhavi, Ali Farhadi, Hannaneh Hajishirzi
- Computer ScienceICLR
- 4 November 2016
The BIDAF network is introduced, a multi-stage hierarchical process that represents the context at different levels of granularity and uses bi-directional attention flow mechanism to obtain a query-aware context representation without early summarization.
Zero-Shot Relation Extraction via Reading Comprehension
It is shown that relation extraction can be reduced to answering simple reading comprehension questions, by associating one or more natural-language questions with each relation slot, and that zero-shot generalization to unseen relation types is possible, at lower accuracy levels.
A Comprehensive Exploration on WikiSQL with Table-Aware Word Contextualization
SQLova is presented, the first Natural-language-to-SQL (NL2SQL) model to achieve human performance in WikiSQL dataset, and it is shown that the model's performance is near the upper bound in Wiki SQL, where it is observed that a large portion of the evaluation errors are due to wrong annotations.
Query-Reduction Networks for Question Answering
Query-Reduction Network (QRN), a variant of Recurrent Neural Network (RNN) that effectively handles both short-term and long-term sequential dependencies to reason over multiple facts, is proposed.
A Diagram is Worth a Dozen Images
- Aniruddha Kembhavi, M. Salvato, Eric Kolve, Minjoon Seo, Hannaneh Hajishirzi, Ali Farhadi
- Computer ScienceECCV
- 24 March 2016
An LSTM-based method for syntactic parsing of diagrams and a DPG-based attention model for diagram question answering are devised and a new dataset of diagrams with exhaustive annotations of constituents and relationships is compiled.
Are You Smarter Than a Sixth Grader? Textbook Question Answering for Multimodal Machine Comprehension
- Aniruddha Kembhavi, Minjoon Seo, Dustin Schwenk, Jonghyun Choi, Ali Farhadi, Hannaneh Hajishirzi
- Computer ScienceIEEE Conference on Computer Vision and Pattern…
- 21 July 2017
The task of Multi-Modal Machine Comprehension (M3C), which aims at answering multimodal questions given a context of text, diagrams and images, is introduced and state-of-the-art methods for textual machine comprehension and visual question answering are extended to the TQA dataset.
Solving Geometry Problems: Combining Text and Diagram Interpretation
- Minjoon Seo, Hannaneh Hajishirzi, Ali Farhadi, Oren Etzioni, Clint Malcolm
- Computer ScienceEMNLP
- 1 September 2015
GEOS is introduced, the first automated system to solve unaltered SAT geometry questions by combining text understanding and diagram interpretation, and it is shown that by integrating textual and visual information, GEOS boosts the accuracy of dependency and semantic parsing of the question text.
Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Index
- Minjoon Seo, Jinhyuk Lee, T. Kwiatkowski, Ankur P. Parikh, Ali Farhadi, Hannaneh Hajishirzi
- Computer ScienceACL
- 13 June 2019
This paper introduces query-agnostic indexable representations of document phrases that can drastically speed up open-domain QA, and introduces dense-sparse phrase encoding, which effectively captures syntactic, semantic, and lexical information of the phrases and eliminates the pipeline filtering of context documents.
Question Answering through Transfer Learning from Large Fine-grained Supervision Data
It is shown that the task of question answering (QA) can significantly benefit from the transfer learning of models trained on a different large, fine-grained QA dataset and that finer supervision provides better guidance for learning lexical and syntactic information than coarser supervision.
Neural Speed Reading via Skim-RNN
Skim-RNN, a recurrent neural network that dynamically decides to update only a small fraction of the hidden state for relatively unimportant input tokens, gives computational advantage over an RNN that always updates the entire hidden state.