Reasoning-Driven Question-Answering for Natural Language Understanding
Explore this paper's citation graph
Summary
This thesis proposes a formulation for abductive reasoning in natural language and shows its effectiveness, especially in domains with limited training data, and presents the first formal framework for multi-step reasoning algorithms, in the presence of a few important properties of language use.
- Type
- preprint
- Published
- 2019-08-14
- Cited by
- 12
- References
- 246
- Access
- Open access
- OpenAlex
- https://openalex.org/W2967994095
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:199577708
Keywords
Question answering, Computer science, Natural language understanding, Natural language, Ambiguity
References
- Using Semantic Roles to Improve Question Answering
- From TreeBank to PropBank
- Mapping Dependencies Trees: An Application to Question Answering
- VerbOcean: Mining the Web for Fine-Grained Semantic Verb Relations
- Representations of Knowledge in a Program for Solving Physics Problems
- Interpretation as Abduction
- The NomBank Project: An Interim Report
- MASC: the Manually Annotated Sub-Corpus of American English
- The Limitations of Standardized Science Tests as Benchmarks for Artificial Intelligence Research: Position Paper
- Random Graphs: Notation
- Human Reasoning: The Psychology Of Deduction
- The Process of Question Answering
- Learning representations by back-propagating errors
- Natural Language Input for a Computer Problem Solving System
- Generating Typed Dependency Parses from Phrase Structure Parses
- Toward an Architecture for Never-Ending Language Learning
- Using Query Patterns to Learn the Duration of Events
- Reasoning about Quantities in Natural Language
- Teaching Machines to Read and Comprehend
- Driving Semantic Parsing from the World’s Response
Cited by
- Voice assistants and how they affect consumer behavior
- Prerequisites for Explainable Machine Reading Comprehension: A Position Paper
- Temporal Reasoning in Natural Language Inference
- Designing an Educational Chatbot with Joint Intent Classification and Slot Filling
- LLMs' Reading Comprehension Is Affected by Parametric Knowledge and Struggles with Hypothetical Statements
- Multi-LogiEval: Towards Evaluating Multi-Step Logical Reasoning Ability of Large Language Models
- LogicBench: Towards Systematic Evaluation of Logical Reasoning Ability of Large Language Models
- Multi-Hop Question Answering over Knowledge Graphs
- Temporal reasoning for timeline summarisation in social media
- PARSE: An Open-Domain Reasoning Question Answering Benchmark for Persian
- Enhancing LLM Reasoning Abilities with Code
- QaN We Pay More Attention?
Related papers
- Reasoning about Quantities in Natural Language
- Practical Approach to Knowledge-based Question Answering with Natural Language Understanding and Advanced Reasoning
- AR-LSAT: Investigating Analytical Reasoning of Text
- A Generative Symbolic Model for More General Natural Language Understanding and Reasoning
- Learning to reason
- Relation-aware Bidirectional Path Reasoning for Commonsense Question Answering
- Integrating Natural Language Processing and Knowledge Based Processing