Papers by Litton J Kurisinkel
Set to Ordered Text: Generating Discharge Instructions from Medical Billing Codes (D19-1)
Copied to clipboard
| Challenge: | a neural architecture learns to generate content in a specific order without explicit specifications of the relations between input entities and output entities. |
| Approach: | They propose a natural language generation task that generates discharge instructions from ICD codes . they propose to model content ordering and text generation in a specific order . |
| Outcome: | The proposed model outperforms baseline models in BLEU scores and human evaluation. |
Coherent and Concise Radiology Report Generation via Context Specific Image Representations and Orthogonal Sentence States (2021.naacl-industry)
Copied to clipboard
| Challenge: | Neural models for text generation are often designed in an end-to-end fashion, limiting their practical usability in downstream applications. |
| Approach: | They propose a method to compute image representations specific to each sentential context and exploiting diverse sentence states to ensure topical continuity and content diversity of generated radiology reports. |
| Outcome: | The proposed method outperforms baselines on objective metrics and human evaluations by 18% and 29% respectively in the evaluation for informativeness and content ordering respectively. |
Tractable & Coherent Multi-Document Summarization: Discrete Optimization of Multiple Neural Modeling Streams via Integer Linear Programming (2022.emnlp-industry)
Copied to clipboard
| Challenge: | Multi-document summarization generates summary of corpus of documents consisting of related topics. |
| Approach: | They propose a generic framework to jointly consider coherence and informativeness in multi-document summarization and offers provisions to replace individual components based on the domain of source text. |
| Outcome: | The proposed framework consistently performs better than baselines for objective metrics and human evaluation. |