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

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 (called EU-CLID) 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% recall and 91% precision) on SAT algebra word problems. We also apply EUCLID to the public Dolphin algebra question set, and improve the state-of-the-art F 1 -score from 73.9% to 77.0%.