Question Answering via Integer Programming over Semi-Structured Knowledge
Daniel Khashabi, Tushar Khot, Ashish Sabharwal et al. · arXiv (Cornell University) · 2016
Answering science questions posed in natural language is an important AI challenge. Answering such questions often requires non-trivial inference and knowledge that goes beyond factoid retrieval. Yet, most systems for this task are based on relatively shallow Information Retrieval (IR) and statistical correlation techniques operating on large unstructured corpora. We propose a structured inference system for this task, formulated as an Integer Linear Program (ILP), that answers natural language questions using a semi-structured knowledge base derived from text, including questions requiring multi-step inference and a combination of multiple facts. On a dataset of real, unseen science questions, our system significantly outperforms (+14%) the best previous attempt at structured reasoning for this task, which used Markov Logic Networks (MLNs). It also improves upon a previous ILP formulation by 17.7%. When combined with unstructured inference methods, the ILP system significantly boosts overall performance (+10%). Finally, we show our approach is substantially more robust to a simple answer perturbation compared to statistical correlation methods.
Cited by 76 works. doi:10.48550/arxiv.1604.06076 Open-access PDF
Authors
References
- WordNet
- Statistical Methods for Psychology.
- Freebase
- Word association norms, mutual information, and lexicography
- Markov logic networks
- Toward an Architecture for Never-Ending Language Learning
- The Seventh PASCAL Recognizing Textual Entailment Challenge.
- Open information extraction from the web
- Building Watson: An Overview of the DeepQA Project
- Distributional Semantics Beyond Words: Supervised Learning of Analogy and Paraphrase