Beyond Sentential Semantic Parsing: Tackling the Math SAT with a Cascade of Tree Transducers

  title={Beyond Sentential Semantic Parsing: Tackling the Math SAT with a Cascade of Tree Transducers},
  author={Mark Hopkins and Cristian Petrescu-Prahova and Roie Levin and Ronan Le Bras and Alvaro Herrasti and Vidur Joshi},
We present an approach for answering questions that span multiple sentences and exhibit sophisticated cross-sentence anaphoric phenomena, evaluating on a rich source of such questions – the math portion of the Scholastic Aptitude Test (SAT). By using a tree transducer cascade as its basic architecture, our system propagates uncertainty from multiple sources (e.g. coreference resolution or verb interpretation) until it can be confidently resolved. Experiments show the first-ever results 43… Expand
A Neural Semantic Parser for Math Problems Incorporating Multi-Sentence Information
Experimental results show that the proposed two-encoder architecture and word-level selective mechanism could bring significant improvement and can achieve better performance than the state-of-the-art methods. Expand
Mapping to Declarative Knowledge for Word Problem Solving
  • Subhro Roy, D. Roth
  • Computer Science
  • Transactions of the Association for Computational Linguistics
  • 2018
Declarative rules which govern the translation of natural language description of these concepts to math expressions are developed, and a framework for incorporating such declarative knowledge into word problem solving is presented. Expand
SemEval-2019 Task 10: Math Question Answering
This work provided a question set derived from Math SAT practice exams, including 2778 training questions and 1082 test questions, and provided SMT-LIB logical form annotations and an interpreter that could solve these logical forms. Expand
Transliteration Better than Translation? Answering Code-mixed Questions over a Knowledge Base
This work proposes a Triplet-Siamese-Hybrid CNN (TSHCNN) to re-rank candidate answers to answer questions and demonstrates how effectively a machine can answer Code-mix questions. Expand
AiFu at SemEval-2019 Task 10: A Symbolic and Sub-symbolic Integrated System for SAT Math Question Answering
This paper is to describe how AiFu works technically and to report and analyze some essential experimental results. 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
Predicting Algorithm Classes for Programming Word Problems
The task of algorithm class prediction for programming word problems is introduced and the best classifier has an accuracy only 9 percent lower than that of a human on this task. Expand
Interactive Visualization for Linguistic Structure
The library is not tied to any particular linguistic representation, but provides a general-purpose API for the interactive exploration of hierarchical linguistic structure, and offers several important features, including expand/collapse functionality, positional and color cues, and explicit visual support for sequential structure. Expand
From 'F' to 'A' on the N.Y. Regents Science Exams: An Overview of the Aristo Project
Unprecedented success on the Grade 8 New York Regents Science Exam, where for the first time a system scores more than 90% on the exam's non-diagram, multiple choice (NDMC) questions, demonstrates that modern NLP methods can result in mastery on this task. Expand


Semantic Parsing on Freebase from Question-Answer Pairs
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
Semantic Parsing of Pre-university Math Problems
Experimental results show that the hybrid system produces a well-formed logical form with 88% precision and 56% recall. Expand
Learning Dependency-Based Compositional Semantics
A new semantic formalism, dependency-based compositional semantics (DCS) is developed and a log-linear distribution over DCS logical forms is defined and it is shown that the system obtains comparable accuracies to even state-of-the-art systems that do require annotated logical forms. Expand
Addressing a Question Answering Challenge by Combining Statistical Methods with Inductive Rule Learning and Reasoning
This work presents a system that excels at all the tasks except one and demonstrates that the introduction of a reasoning module significantly improves the performance of an intelligent agent. Expand
Annotating Derivations: A New Evaluation Strategy and Dataset for Algebra Word Problems
A new evaluation for automatic solvers for algebra word problems is proposed, which can identify mistakes that existing evaluations overlook, and derivation annotations can be semi-automatically added to existing datasets. Expand
Parsing Algebraic Word Problems into Equations
This paper formalizes the problem of solving multi-sentence algebraic word problems as that of generating and scoring equation trees. We use integer linear programming to generate equation trees andExpand
Solving General Arithmetic Word Problems
This is the first algorithmic approach that can handle arithmetic problems with multiple steps and operations, without depending on additional annotations or predefined templates, and it outperforms existing systems, achieving state of the art performance on benchmark datasets of arithmetic word problems. Expand
Learning to Parse Database Queries Using Inductive Logic Programming
Experimental results with a complete database-query application for U.S. geography show that CHILL is able to learn parsers that outperform a preexisting, hand-crafted counterpart, and provide direct evidence of the utility of an empirical approach at the level of a complete natural language application. Expand
The More Antecedents, the Merrier: Resolving Multi-Antecedent Anaphors
This work provides a formalization of the new task with preliminary insights into multi-antecedent noun-phrase anaphors, and offers a method for resolving such cases that outperforms a number of baseline methods by a significant margin. Expand
Learning to Automatically Solve Algebra Word Problems
An approach for automatically learning to solve algebra word problems by reasons across sentence boundaries to construct and solve a system of linear equations, while simultaneously recovering an alignment of the variables and numbers to the problem text. Expand