Answering Elementary Science Questions by Constructing Coherent Scenes using Background Knowledge

@inproceedings{Li2015AnsweringES,
  title={Answering Elementary Science Questions by Constructing Coherent Scenes using Background Knowledge},
  author={Yang Li and P. Clark},
  booktitle={EMNLP},
  year={2015}
}
  • Yang Li, P. Clark
  • Published in EMNLP 2015
  • Computer Science
Much of what we understand from text is not explicitly stated. Rather, the reader uses his/her knowledge to fill in gaps and create a coherent, mental picture or “scene” depicting what text appears to convey. The scene constitutes an understanding of the text, and can be used to answer questions that go beyond the text. Our goal is to answer elementary science questions, where this requirement is pervasive; A question will often give a partial description of a scene and ask the student about… Expand
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. Expand
Learning From Unannotated QA Pairs to Analogically Disambiguate and Answer Questions
TLDR
An analogy-based approach that adapts an existing general purpose semantic parser to answer questions in a novel domain by jointly learning disambiguation heuristics and query construction templates from purely textual question-answer pairs. Expand
Grounding proposition stores for question answering over linked data
TLDR
This article proposes a methodology to enable a standalone evaluation of grounding natural language propositions into semantic relations by fixing all the components of a question answering system other than the lexicon itself. Expand
Encoding Explanatory Knowledge for Zero-shot Science Question Answering
TLDR
It is demonstrated that NXKT is able to improve accuracy and generalization on science Question Answering (QA) and can be fine-tuned on a target QA dataset, enabling faster convergence and more accurate results. Expand
Teaching Pretrained Models with Commonsense Reasoning: A Preliminary KB-Based Approach
TLDR
This work proposes a simple yet effective method to teach pretrained models with commonsense reasoning by leveraging the structured knowledge in ConceptNet, the largest commonsense knowledge base (KB). Expand
Towards Literate Artificial Intelligence
Standardized tests are used to test students as they progress in the formal education system. These tests are readily available and have clear evaluation procedures.Hence, it has been proposed thatExpand
Crowdsourcing Multiple Choice Science Questions
TLDR
This work presents a novel method for obtaining high-quality, domain-targeted multiple choice questions from crowd workers by leveraging a large corpus of domain-specific text and a small set of existing questions and shows that humans cannot distinguish the crowdsourced questions from original questions. Expand
Representing scientific knowledge for quantitative analysis of physical systems
Representation of scientific knowledge in ontologies suffers so often from the lack of computational knowledge required for inference. This article aims to perform quantitative analysis on physicalExpand
Propositional Knowledge: Acquisition and Application to Syntactic and Semantic Parsing
La interpretacion de lenguaje natural es uno de los retos centrales en el desarrollo de la inteligencia artificial. En general, la interpretacion requiere construir un contexto de informacionExpand
Front matter
TLDR
The present collection of papers from the 3rd International Conference on Universal Design (UD 2016) is testament to the fact that Universal Design is now benefitting from a climate that is more knowledgeable about, and possibly more accommodating of, individual differences between people. Expand
...
1
2
...

References

SHOWING 1-10 OF 19 REFERENCES
Large-scale extraction and use of knowledge from text
TLDR
This work has created a new, publically available knowledge resource for language processing and other data interpretation tasks, and provides empirical evidence of the utility of this type of knowledge, going beyond Schubert et al's earlier evaluations which were based solely on human inspection of its contents. Expand
Discourse Complements Lexical Semantics for Non-factoid Answer Reranking
We propose a robust answer reranking model for non-factoid questions that integrates lexical semantics with discourse information, driven by two representations of discourse: a shallow representationExpand
Elementary School Science and Math Tests as a Driver for AI: Take the Aristo Challenge!
TLDR
This work is working on a specific version of this challenge, namely having the computer pass Elementary School Science and Math exams, the most difficult requiring significant progress in AI. Expand
Information Extraction over Structured Data: Question Answering with Freebase
TLDR
It is shown that relatively modest information extraction techniques, when paired with a webscale corpus, can outperform these sophisticated approaches by roughly 34% relative gain. Expand
Coherence and Coreference
TLDR
In this paper, formal definitions are given for several coherence relations, based on the operations of an inference system; that is, the relations between successive portions of a discourse are characterized in terms of the inferences that can be drawn from each. Expand
Semantics of Paragraphs
We present a computational theory of the paragraph. Within it we formally define coherence, give semantics to the adversative conjunction "but" and to the Gricean maxim of quantity, and present someExpand
Interpretation as Abduction
TLDR
An approach to abductive inference, called “weighted abduction”, that has resulted in a significant simplification of how the problem of interpreting texts is conceptualized, can be combined with the older view of “parsing as deduction” to produce an elegant and thorough integration of syntax, semantics, and pragmatics. Expand
Abductive Reasoning with a Large Knowledge Base for Discourse Processing
TLDR
A discourse processing framework based on weighted abduction and implement the abductive inference procedure in a system called Mini-TACITUS, taking the Frame-Annotated Corpus for Textual Entailment as a gold standard is presented. Expand
Indirect anaphora resolution as semantic path search
TLDR
A generic tool for finding semantic paths between two concepts to resolve indirect anaphora achieved approximately twice the recall of the best previous system without loss of precision. Expand
TextNet - A text-based intelligent system
TLDR
This paper presents a system that contains a core knowledge base structured around WordNet, a lexical database, capable of extracting contextual information from a given input text, and the acquisition of new knowledge from corpora. Expand
...
1
2
...