Papers by Emily Saldanha
Unsupervised Keyphrase Extraction via Interpretable Neural Networks (2023.findings-eacl)
Copied to clipboard
Rishabh Joshi, Vidhisha Balachandran, Emily Saldanha, Maria Glenski, Svitlana Volkova, Yulia Tsvetkov
| Challenge: | Prior approaches for unsupervised keyphrase extraction relied on heuristic notions of phrase importance via embedding clustering or graph centrality. |
| Approach: | They propose an approach which defines keyphrases as document phrases that are salient for predicting the topic of the document. |
| Outcome: | The proposed method alleviates the need for ad-hoc heuristics and achieves state-of-the-art results in scientific publications and news articles. |
Extracting Material Property Measurement Data from Scientific Articles (2021.emnlp-main)
Copied to clipboard
| Challenge: | a lack of large training datasets hampers machine learning-based prediction of material properties . relevant measurements and information exist only in unstructured formats such as the published literature . |
| Approach: | They propose a framework for automatic property extraction using material solubility as the target property. |
| Outcome: | The proposed framework extracts solubility data from scientific literature and compares it with other frameworks. |