subhro roy - Academia.edu (original) (raw)
Uploads
Papers by subhro roy
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, 2016
Identifying mathematical relations expressed in text is essential to understanding a broad range ... more Identifying mathematical relations expressed in text is essential to understanding a broad range of natural language text from election reports, to financial news, to sport commentaries to mathematical word problems. This paper focuses on identifying and understanding mathematical relations described within a single sentence. We introduce the problem of Equation Parsing-given a sentence, identify noun phrases which represent variables, and generate the mathematical equation expressing the relation described in the sentence. We introduce the notion of projective equation parsing and provide an efficient algorithm to parse text to projective equations. Our system makes use of a high precision lexicon of mathematical expressions and a pipeline of structured predictors, and generates correct equations in 70% of the cases. In 60% of the time, it also identifies the correct noun phrase → variables mapping, significantly outperforming baselines. We also release a new annotated dataset for task evaluation.
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, 2016
Identifying mathematical relations expressed in text is essential to understanding a broad range ... more Identifying mathematical relations expressed in text is essential to understanding a broad range of natural language text from election reports, to financial news, to sport commentaries to mathematical word problems. This paper focuses on identifying and understanding mathematical relations described within a single sentence. We introduce the problem of Equation Parsing-given a sentence, identify noun phrases which represent variables, and generate the mathematical equation expressing the relation described in the sentence. We introduce the notion of projective equation parsing and provide an efficient algorithm to parse text to projective equations. Our system makes use of a high precision lexicon of mathematical expressions and a pipeline of structured predictors, and generates correct equations in 70% of the cases. In 60% of the time, it also identifies the correct noun phrase → variables mapping, significantly outperforming baselines. We also release a new annotated dataset for task evaluation.