• Corpus ID: 52286955

Answering Science Exam Questions Using Query Rewriting with Background Knowledge

@article{Musa2018AnsweringSE,
  title={Answering Science Exam Questions Using Query Rewriting with Background Knowledge},
  author={Ryan Musa and Xiaoyang Wang and Achille Fokoue and Nicholas Mattei and Maria Chang and Pavan Kapanipathi and Bassem Makni and Kartik Talamadupula and M. Witbrock},
  journal={ArXiv},
  year={2018},
  volume={abs/1809.05726}
}
Open-domain question answering (QA) is an important problem in AI and NLP that is emerging as a bellwether for progress on the generalizability of AI methods and techniques. [] Key Method We present a system that rewrites a given question into queries that are used to retrieve supporting text from a large corpus of science-related text. Our rewriter is able to incorporate background knowledge from ConceptNet and -- in tandem with a generic textual entailment system trained on SciTail that identifies support…

Figures and Tables from this paper

Improving Question Answering with External Knowledge
TLDR
This work explores simple yet effective methods for exploiting two sources of externalknowledge for exploiting unstructured external knowledge for subject-area QA on multiple-choice question answering tasks in subject areas such as science.
Careful Selection of Knowledge to Solve Open Book Question Answering
TLDR
This paper addresses QA with respect to the OpenBookQA dataset and combines state of the art language models with abductive information retrieval (IR), information gain based re-ranking, passage selection and weighted scoring to achieve 72.0% accuracy.
Repurposing Entailment for Multi-Hop Question Answering Tasks
TLDR
Multee is introduced, a general architecture that can effectively use entailment models for multi-hop QA tasks and outperforms QA models trained only on the target QA datasets and the OpenAI transformer models when using an entailment function pre-trained on NLI datasets.
Alignment over Heterogeneous Embeddings for Question Answering
TLDR
A simple meta-classifier that learns how much to trust the predictions over each representation improves the performance of unsupervised AHE, and error analysis indicates that alignments over character, word, and sentence embeddings capture substantially different semantic information.
Infusing Knowledge into the Textual Entailment Task Using Graph Convolutional Networks
TLDR
This work presents an approach that complements text-based entailment models with information from KGs by using Personalized PageRank to generate contextual subgraphs with reduced noise and encoding these sub graphs using graph convolutional networks to capture the structural and semantic information in KGs.

References

SHOWING 1-10 OF 55 REFERENCES
Learning to Attend On Essential Terms: An Enhanced Retriever-Reader Model for Open-domain Question Answering
TLDR
This paper proposes a retriever-reader model that learns to attend on essential terms during the question answering process, and builds an essential term selector which first identifies the most important words in a question, then reformulates the query and searches for related evidence.
Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
TLDR
A new question set, text corpus, and baselines assembled to encourage AI research in advanced question answering constitute the AI2 Reasoning Challenge (ARC), which requires far more powerful knowledge and reasoning than previous challenges such as SQuAD or SNLI.
Question Answering via Integer Programming over Semi-Structured Knowledge
TLDR
This work proposes a structured inference system for this task, formulated as an Integer Linear Program (ILP), that answers natural language questions using a semi-structured knowledge base derived from text, including questions requiring multi-step inference and a combination of multiple facts.
Learning to Attend On Essential Terms: An Enhanced Retriever-Reader Model for Scientific Question Answering
TLDR
This paper proposes a retriever-reader model that learns to attend on essential terms during the question answering process and builds an essential-term-aware ‘retriever’ and an enhanced ‘reader’ to distinguish between essential terms and distracting words to predict the answer.
R3: Reinforced Ranker-Reader for Open-Domain Question Answering
TLDR
This paper proposes a new pipeline for open-domain QA with a Ranker component, which learns to rank retrieved passages in terms of likelihood of extracting the ground-truth answer to a given question, and proposes a novel method that jointly trains the Ranker along with an answer-extraction Reader model, based on reinforcement learning.
Improving Natural Language Inference Using External Knowledge in the Science Questions Domain
TLDR
A combination of techniques that harness knowledge graphs to improve performance on the NLI problem in the science questions domain and achieves the new state-of-the-art performance over the SciTail science questions dataset.
Learning What is Essential in Questions
TLDR
This paper develops a classifier that reliably identifies and ranks essential terms in questions and demonstrates that the notion of question term essentiality allows state-of-the-art QA solver for elementary-level science questions to make better and more informed decisions, improving performance by up to 5%.
KG^2: Learning to Reason Science Exam Questions with Contextual Knowledge Graph Embeddings
TLDR
This paper proposes a novel framework for answering science exam questions, which mimics human solving process in an open-book exam and outperforms the previous state-of-the-art QA systems.
SciTaiL: A Textual Entailment Dataset from Science Question Answering
TLDR
A new dataset and model for textual entailment, derived from treating multiple-choice question-answering as an entailment problem, is presented, and it is demonstrated that one can improve accuracy on SCITAIL by 5% using a new neural model that exploits linguistic structure.
SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine
TLDR
It is shown that there is a meaningful gap between the human and machine performances, which suggests that the proposed dataset could well serve as a benchmark for question-answering.
...
1
2
3
4
5
...