# Question Answering as Global Reasoning over Semantic Abstractions

arXiv: https://arxiv.org/abs/1906.03672 · HTML: https://mlsanity.com/paper/1906.03672/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jun 2019.

## Built on by (most cited first, 14 of 14)

- [MAVEN-ERE: A Unified Large-scale Dataset for Event Coreference, Temporal, Causal, and Subevent Relation Extraction](https://mlsanity.com/paper/2211.07342/) (2022)
- [Diff-Explainer: Differentiable Convex Optimization for Explainable Multi-hop Inference](https://mlsanity.com/paper/2105.03417/) (2021)
- [Are LLMs Good Annotators for Discourse-level Event Relation Extraction?](https://mlsanity.com/paper/2407.19568/) (2024)
- [Quasi-symbolic Semantic Geometry over Transformer-based Variational AutoEncoder](https://mlsanity.com/paper/2210.06230/) (2022)
- [ProtoEM: A Prototype-Enhanced Matching Framework for Event Relation Extraction](https://mlsanity.com/paper/2309.12892/) (2023)
- [Fine-Tuning vs. RAG for Multi-Hop Question Answering with Novel Knowledge](https://mlsanity.com/paper/2601.07054/) (2026)
- [Encoding Explanatory Knowledge for Zero-shot Science Question Answering](https://mlsanity.com/paper/2105.05737/) (2021)
- [M-QALM: A Benchmark to Assess Clinical Reading Comprehension and Knowledge Recall in Large Language Models via Question Answering](https://mlsanity.com/paper/2406.03699/) (2024)
- [TacoERE: Cluster-aware Compression for Event Relation Extraction](https://mlsanity.com/paper/2405.06890/) (2024)
- [COMBO: a new module for EUD parsing](https://mlsanity.com/paper/2107.03809/) (2021)
- [Going Beyond Approximation: Encoding Constraints for Explainable Multi-hop Inference via Differentiable Combinatorial Solvers](https://mlsanity.com/paper/2208.03339/) (2022)
- [Adverbs, Surprisingly](https://mlsanity.com/paper/2305.19650/) (2023)
- [A Differentiable Integer Linear Programming Solver for Explanation-Based Natural Language Inference](https://mlsanity.com/paper/2404.02625/) (2024)
- [NLPre: a revised approach towards language-centric benchmarking of Natural Language Preprocessing systems](https://mlsanity.com/paper/2403.04507/) (2024)

## Abstract (arXiv)

We propose a novel method for exploiting the semantic structure of text to answer multiple-choice questions. The approach is especially suitable for domains that require reasoning over a diverse set of linguistic constructs but have limited training data. To address these challenges, we present the first system, to the best of our knowledge, that reasons over a wide range of semantic abstractions of the text, which are derived using off-the-shelf, general-purpose, pre-trained natural language modules such as semantic role labelers, coreference resolvers, and dependency parsers. Representing multiple abstractions as a family of graphs, we translate question answering (QA) into a search for an optimal subgraph that satisfies certain global and local properties. This formulation generalizes several prior structured QA systems. Our system, SEMANTICILP, demonstrates strong performance on two domains simultaneously. In particular, on a collection of challenging science QA datasets, it outperforms various state-of-the-art approaches, including neural models, broad coverage information retrieval, and specialized techniques using structured knowledge bases, by 2%-6%.