Introducing MathQA - A Math-Aware Question Answering System

@article{Schubotz2018IntroducingM,
  title={Introducing MathQA - A Math-Aware Question Answering System},
  author={Moritz Schubotz and Philipp Scharpf and Kaushal Dudhat and Yashwant Nagar and Felix Hamborg and Bela Gipp},
  journal={ArXiv},
  year={2018},
  volume={abs/1907.01642}
}
Purpose This paper aims to present an open source math-aware Question Answering System based on Ask Platypus. [...] Key Method The authors translate these formulae to computable data by integrating the calculation engine sympy into the system. This way, users can enter numeric values for the variables occurring in the formula. Moreover, the system loads numeric values for constants occurring in the formula from Wikidata. Findings In a user study, this system outperformed a…Expand
Mathematics in Wikidata
TLDR
The current state, challenges, and discussions related to integrating Mathematical Entity Linking into Wikidata and Wikipedia are summarized and some data mining methods and applications of the mathematical information are outlined.
Mathematical World Knowledge Contained in the Multilingual Wikipedia Project
TLDR
The number of times a formula is shared across a Wikipedia article in different languages is not a good indicator to determine the defining formula with the current approach and several ideas for further research are proposed which could improve the results.
AnnoMathTeX - a formula identifier annotation recommender system for STEM documents
TLDR
This work presents a first implementation of a recommender system that enables and accelerates formula annotation by displaying the most likely candidates for formula and identifier names from four different sources (arXiv, Wikipedia, Wikidata, or the surrounding text).
ARQMath Lab: An Incubator for Semantic Formula Search in zbMATH Open?
TLDR
The ARQMath Task at CLEF 2020 aims to tackle the problem of linking newly posted questions from Math Stack Exchange (MSE) to existing ones that were already answered by the community, and several formula retrieval methods were explored.
Ontology-Based Approach to Semantically Enhanced Question Answering for Closed Domain: A Review
TLDR
An ontological approach to semantically enhancing QA is found to be adopted in a limited way, as many of the studies reviewed concentrated instead on NLP and information retrieval (IR) processing.
Formula Concept Discovery and Recognition
TLDR
A method to discover and recognize formula concepts in Wikipedia articles and STEM documents using Wikidata as a semantic knowledge-base is developed, which is expected to improve search engines, recommender systems, plagiarism and novelty detection and ontology learning.
Towards Formula Concept Discovery and Recognition
TLDR
First Machine Learning based approaches to tackle the FCD and FCR tasks are presented, which will enable citing formulae within mathematical documents and facilitate semantic search as well as similarity computations for plagiarism detection or document recommender systems.
Generating OpenMath Content Dictionaries from Wikidata (short paper)
TLDR
This work presents an OpenMath content dictionary, which is generated automatically from Wikidata, and proposes the WikidATA property P5610, which provides multilingual background information for symbols in MathML formulae.
Mathematical Formulae in Wikimedia Projects 2020
TLDR
This poster summarizes the contributions to Wikimedia's processing pipeline for mathematical formulae and describes the plans to improve the accessibility and discoverability of mathematical knowledge in Wikimedia projects further.
Towards Explaining STEM Document Classification using Mathematical Entity Linking
TLDR
First advances towards STEM document classification explainability using classical and mathematical Entity Linking are presented and it is indicated that mathematical entities have the potential to provide high explainability as they are a crucial part of a STEM document.
...
1
2
...

References

SHOWING 1-10 OF 49 REFERENCES
Natural language question answering: the view from here
TLDR
The best systems are now able to answer more than two thirds of factual questions in this evaluation, with recent successes reported in a series of question-answering evaluations.
Mathematical Language Processing Project
TLDR
Two approaches to discover identifier-definition tuples are compared and a simple pattern matching approach is used and a approach that uses part-of-speech tag based distances as well as sentence positions to calculate identifier- definition probabilities is presented.
Scaling question answering to the web
TLDR
Mulder is introduced, which is believed to be the first general-purpose, fully-automated question-answering system available on the web, and its architecture is described, which relies on multiple search-engine queries, natural-language parsing, and a novel voting procedure to yield reliable answers coupled with high recall.
Answering English questions by computer: a survey
TLDR
It is concluded that the data-base question-answerer has passed from initial research into the early developmental ~4 phase and the most difficult and important research questions for general-purpose language processors are seen to be concerned with measuring meaning, dealing with ambiguities, translating into formal languages and searching large tree structures.
Semantic Wikipedia
TLDR
This paper provides an extension to be integrated in Wikipedia, that allows the typing of links between articles and the specification of typed data inside the articles in an easy-to-use manner, and presents the design, implementation, and possible uses of this extension.
A Web-based Question Answering System
TLDR
This paper describes a Web-based question answering system LAMP, which is publicly accessible, and thinks its performance is comparable to the best state-of-the-art question answering systems.
A Search Engine for Mathematical Formulae
TLDR
A search engine for mathematical formulae and a generic language extension approach that allows constructing queries by minimally annotating existing representations that results in a scalable application are presented.
Contextual Analysis of Mathematical Expressions for Advanced Mathematical Search
TLDR
A way to use mathematical search to provide better navigation for reading papers on computers and present how to extract a natural language description, such as variable names or function definitions that refer to mathematical expressions with various experimental results.
Beyond Information Retrieval - Medical Question Answering
TLDR
The authors address physicians' information needs and described the design, implementation, and evaluation of the medical question answering system (MedQA), which aims to enable MedQA to answer all types of medical questions.
The TREC-8 Question Answering Track
The Text REtrieval Conference (TREC) question answering track is an effort to bring the benefits of large-scale evaluation to bear on a question answering (QA) task. The track has run twice so far,
...
1
2
3
4
5
...