Corpus ID: 12626900

Question Answering from Unstructured Text by Retrieval and Comprehension

@article{Watanabe2017QuestionAF,
  title={Question Answering from Unstructured Text by Retrieval and Comprehension},
  author={Yusuke Watanabe and Bhuwan Dhingra and R. Salakhutdinov},
  journal={ArXiv},
  year={2017},
  volume={abs/1703.08885}
}
Open domain Question Answering (QA) systems must interact with external knowledge sources, such as web pages, to find relevant information. [...] Key Method For comprehension, we present an RNN based attention model with a novel mixture mechanism for selecting answers from either retrieved articles or a fixed vocabulary. For retrieval we introduce a hand-crafted model and a neural model for ranking relevant articles. We achieve state-of-the-art performance on W IKI M OVIES dataset, reducing the error by 40…Expand
Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text
TLDR
A novel model is proposed, GRAFT-Net, for extracting answers from a question-specific subgraph containing text and Knowledge Bases entities and relations that is competitive with the state-of-the-art when tested using either KBs or text alone, and vastly outperforms existing methods in the combined setting. Expand
PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text
TLDR
PullNet is described, an integrated framework for learning what to retrieve and reasoning with this heterogeneous information to find the best answer in an open-domain question answering setting. Expand
A survey on question answering systems over linked data and documents
TLDR
This paper surveys the recent work that has been done in the area of stateless QA systems with emphasis on methods that have been applied in RDF and Linked Data, documents, and mixtures of these. Expand
Quasar: Datasets for Question Answering by Search and Reading
We present two new large-scale datasets aimed at evaluating systems designed to comprehend a natural language query and extract its answer from a large corpus of text. The Quasar-S dataset consistsExpand
The Web as a Knowledge-Base for Answering Complex Questions
TLDR
This paper proposes to decompose complex questions into a sequence of simple questions, and compute the final answer from the sequence of answers, and empirically demonstrates that question decomposition improves performance from 20.8 precision@1 to 27.5 precision @1 on this new dataset. Expand
Learning to Search in Long Documents Using Document Structure
TLDR
A novel framework for reading comprehension is proposed, which represents documents as trees, and model an agent that learns to interleave quick navigation through the document tree with more expensive answer extraction. Expand
Document Gated Reader for Open-Domain Question Answering
TLDR
A document gated reader to generate the right answer from multiple documents is proposed with a document-level gate operation to determine the question-document relevance and embed it into the answer generation process, and optimize it with the global normalization objective. Expand
Identifying Supporting Facts for Multi-hop Question Answering with Document Graph Networks
TLDR
Document Graph Network is proposed, a message passing architecture for the identification of supporting facts over a graph-structured representation of text that obtains competitive results when compared to a reading comprehension baseline operating on raw text, confirming the relevance of structured representations for supporting multi-hop reasoning. Expand
Conversational QA for FAQs
The goal of this work is to access the large body of domain-specific information in the form of Frequently Asked Question sites via conversational Question Answering (QA) systems. Training systemsExpand
Arabic Question Answering: A Study on Challenges, Systems, and Techniques
TLDR
A review of the Arabic Question Answering Systems building processes and the challenges met by the researchers in this topic due to the Arabic language special characteristics are provided. Expand
...
1
2
...

References

SHOWING 1-10 OF 25 REFERENCES
Open question answering over curated and extracted knowledge bases
TLDR
This paper presents OQA, the first approach to leverage both curated and extracted KBs, and demonstrates that it achieves up to twice the precision and recall of a state-of-the-art Open QA system. Expand
Hierarchical Question Answering for Long Documents
TLDR
A framework for question answering is presented that can efficiently scale to longer documents while maintaining or even improving performance of state-of-the-art models and treats sentence selection as a latent variable trained jointly from the answer only using reinforcement learning. Expand
Key-Value Memory Networks for Directly Reading Documents
TLDR
This work introduces a new method, Key-Value Memory Networks, that makes reading documents more viable by utilizing different encodings in the addressing and output stages of the memory read operation. Expand
SQuAD: 100,000+ Questions for Machine Comprehension of Text
TLDR
A strong logistic regression model is built, which achieves an F1 score of 51.0%, a significant improvement over a simple baseline (20%). Expand
Building a question answering test collection
TLDR
The TREC-8 Question Answering (QA) Track was the first large-scale evaluation of domain-independent question answering systems and was used to investigate whether the evaluation methodology used for document retrieval is appropriate for a different natural language processing task. Expand
Knowledge base completion via search-based question answering
TLDR
A way to leverage existing Web-search-based question-answering technology to fill in the gaps in knowledge bases in a targeted way by learning the best set of queries to ask, such that the answer snippets returned by the search engine are most likely to contain the correct value for that attribute. Expand
Semantic Parsing on Freebase from Question-Answer Pairs
TLDR
This paper trains a semantic parser that scales up to Freebase and outperforms their state-of-the-art parser on the dataset of Cai and Yates (2013), despite not having annotated logical forms. Expand
Large-scale Simple Question Answering with Memory Networks
TLDR
This paper studies the impact of multitask and transfer learning for simple question answering; a setting for which the reasoning required to answer is quite easy, as long as one can retrieve the correct evidence given a question, which can be difficult in large-scale conditions. Expand
Text Understanding with the Attention Sum Reader Network
TLDR
A new, simple model is presented that uses attention to directly pick the answer from the context as opposed to computing the answer using a blended representation of words in the document as is usual in similar models, making the model particularly suitable for question-answering problems where the answer is a single word from the document. Expand
Gated-Attention Readers for Text Comprehension
TLDR
The model, the Gated-Attention (GA) Reader, integrates a multi-hop architecture with a novel attention mechanism, which is based on multiplicative interactions between the query embedding and the intermediate states of a recurrent neural network document reader, which enables the reader to build query-specific representations of tokens in the document for accurate answer selection. Expand
...
1
2
3
...