Papers by Sebastião Miranda
Multilingual Clustering of Streaming News (D18-1)
Copied to clipboard
| Challenge: | a novel method for clustering news across languages is proposed . a key challenge in handling news streams is that they must be generated on the fly . |
| Approach: | They propose a method for clustering news across languages into monolingual and crosslingual clusters . they use real news datasets in multiple languages to find an ever growing number of cluster labels . |
| Outcome: | The proposed method produces state-of-the-art results on real news datasets in German, English and Spanish. |
The SUMMA Platform: A Scalable Infrastructure for Multi-lingual Multi-media Monitoring (P18-4)
Copied to clipboard
| Challenge: | The SUMMA Platform is a highly scalable distributed architecture for monitoring a large number of media broadcasts in parallel, with a lag behind actual broadcast time of at most a few minutes. |
| Approach: | The open-source SUMMA Platform is a highly scalable distributed architecture for monitoring a large number of media broadcasts in parallel . it offers a fully automated media ingestion pipeline capable of recording live broadcasts, detection and transcription of spoken content, translation of all text (original or transcribed) into English, recognition and linking of Named Entities, topic detection, clustering and cross-lingual multi-document summarization of related media items and extraction and storage of factual claims in these news items. |
| Outcome: | The SUMMA Platform is a highly scalable distributed architecture for monitoring a large number of media broadcasts in parallel, with a lag behind actual broadcast time of at most a few minutes. |
Jointly Extracting and Compressing Documents with Summary State Representations (N19-1)
Copied to clipboard
| Challenge: | Text summarization is an important NLP problem with a wide range of applications in data-driven industries. |
| Approach: | They propose a neural model that extracts sentences from a document and compresses them. |
| Outcome: | The proposed model generates concise and informa-tive summaries on CNN/DailyMail and Newsroom datasets and human evaluations show it outperforms existing methods. |