Papers by Joshua Bambrick
NSTM: Real-Time Query-Driven News Overview Composition at Bloomberg (2020.acl-demos)
Copied to clipboard
Joshua Bambrick, Minjie Xu, Andy Almonte, Igor Malioutov, Guim Perarnau, Vittorio Selo, Iat Chong Chan
| Challenge: | aggregators consume millions of articles every day, making it difficult to quickly identify key events and miss less-reported stories. |
| Approach: | a new kind of summarization engine was needed to condense large volumes of news into short, easy to absorb points. |
| Outcome: | NSTM can be used to summarize news articles in seconds and quickly and efficiently. |
Falsesum: Generating Document-level NLI Examples for Recognizing Factual Inconsistency in Summarization (2022.naacl-main)
Copied to clipboard
| Challenge: | Neural abstractive summarization models generate factually inconsistent summaries . previous work has introduced the task of recognizing factual inconsistency as a downstream application of natural language inference (NLI). |
| Approach: | They propose a data generation pipeline that enables a task-oriented approach to detect factual inconsistencies in abstractive summarization models. |
| Outcome: | The proposed model improves the state-of-the-art performance across four benchmarks for recognizing factual inconsistency in generated summaries. |