Text2Story
Extracting journalistic narratives from text and representing them in a narrative modeling language.
MorePicture: Morning News by Francis Luis Mora
About
Nowadays journalistic content is distributed in multiple formats, mostly through the web and specific internet based applications running on smartphones and tablets. Text is a very important format, but readers (or more accurately users or information consumers) heavily rely on images, videos, slideshows, charts and infographics. Textual content is still the main representation for information. Any journalistic subject (e.g. Trump and Russia) is described in one or more texts produced by journalists and possibly commented by readers. Many of those subjects are followed during days, weeks or months. To grasp a possibly vast and somewhat complex set of interconnected news articles, readers would greatly benefit from tools that summarize those articles by showing main actors, their interplay and their trajectories in time and space, their motivations, main events, causal relations of events and outcomes. In other words, tools that extract narrative elements and re-represent them in formats that convey the essential story but that are more efficiently consumed by the users.
This vibrant research line poses many challenging problems in information extraction and automatic production of media content. At this project want to be able to extract narratives/stories from news articles or collections of related news articles (unstructured data) about the same (or related) subject, representing those narratives in intermediate data structures (structured data) and making this available to subsequent media production processes (semi-automatic generation of slide shows, infographics and other visualizations, video sequences, games, etc.). In summary, our aim in Text2Story project is to develop a conceptual framework and operational pipeline for the extraction of narratives from textual sources. The project focuses on the automatic processing of journalistic text in written Portuguese.
Team
Alípio Jorge
Principal Investigator
U. Porto and INESC TEC
His aim is to make the computer get the essential of a narrative, represent it and show the narrative as a timeline, a slide-show, a video or a game. The plan is to apply Machine Learning and NLP
Alexandre Ribeiro
MSc Researcher
U. Porto and INESC TEC
Ana Cardoso
PhD Student
U. Porto and INESC TEC
António Leal
PhD Researcher
U. Porto and CLUP
António is mainly interested in the formal representation of meaning in Portuguese news, namely how tense, aspect and nominal reference can be encoded.
Brenda Santana
PhD Student
UFRGS and INESC TEC
Brenda is studying NLP and is also our webmaster. In the project she is focusing on extracting the relation between time and events.
Catarina Fernandes
MSc Student
U. Porto
Daniel Oliveira
PhD Student
U. Porto and INESC TEC
Evelin Amorim
PhD Researcher
INESC TEC
My main interests are NLP related research. Specifically, extraction of information of text, automatic essay scoring, and all the subtasks related to these two fields.
Fátima Oliveira
PhD Researcher
U. Porto and CLUP
Fátima Silva
PhD Researcher
U. Porto and CLUP
Filipe Cunha
PhD Student
U. Porto and INESC TEC
Hugo Sousa
PhD Student
U. Porto and INESC TEC
Looking for a away to make models temporally aware.
Inês Cantante
MSc Researcher
U. Porto and CLUP
Joana Valente
MSc Student
U.Porto
João Nogueira
MSc Student
U.Porto
His aim is to boost NLP models for Portuguese using transfer learning and data augmentation.
João Paulo Cordeiro
PhD Researcher
UBI and INESC TEC
Mariana Costa
MSc Student
U.Porto
Nuno Guimarães
PhD Researcher
U. Porto and INESC TEC
Pavel Brazdil
PhD Researcher
U. Porto and INESC TEC
Pedro Botelho
MSc Student
U. Porto and SAPO24
Looking at the inner workings of news stories and how people interact with them, his aim is to find innovative ways to present journalism.
Pedro Mota
BSc Student
U. Porto and INESC TEC
Purificação Silvano
PhD Researcher
U. Porto and CLUP
Her aim is to study temporal relations in news articles and contribute to the representation of the timeline comprised in the narratives.
Ricardo Campos
Co-Investigator
IPT and INESC TEC
His aim is to get new insights from news articles. In particular, he is interested in applying nlp as a means to understand how events relate to the temporal dimension.
Rúben Almeida
MSc Student
U. Porto and INESC TEC
Sérgio Nunes
PhD Researcher
U. Porto and INESC TEC
Sofia Oliveira
MSc Student
U. Porto and INESC TEC
Institutions
Partners
Events & Special Issues
Past Workshops:
Special Issues:
Talks:
- YAKE: Extração de keywords a partir de documentos. by Ricardo Campos, June 3rd, 2022.
- Timeline summarization for large-scale past-web events with Python: the case of Arquivo.pt. by Ricardo Campos Tutorial available at The Programming History website and at github, May 5th, 2022.
- Invited Talk at Banco de Portugal (Escola de Data Science) about “Narrative Extraction From Text: An Overview (and some more info)” by Alípio Jorge, Mar 25th, 2022
- Invited Talk at III Jornadas de Gestão de Informação about “Timeline Summarization for Large-scale Past-web Events” by Ricardo Campos, Nov 19th, 2021
- Masterclass at Festival Internacional de Ciência (FICA 2021) about “Text2Story: Narrative Extraction from Texts” by Ricardo Campos, October 15th, 2021.
- Invited Talk at TempWeb@WWW'21 about “Telling Stories Through Timelines” by Ricardo Campos, April 12th, 2021.
- Invited Talk at XVII Jornadas Ciência da Informação about “Telling Stories Through Timelines” by Ricardo Campos, May 17th, 2021.
- Invited Talk at DaSSWeb, Data Science and Statistics Webinar about “Text2Story: Narrative Extraction from Texts” by Alípio Jorge, January 26th, 2021.
- Invited Talk at Refinitiv Labs about “YAKE! Keyword Extractor” by Ricardo Campos, December 18th, 2020.
Outcomes
Demos
Packages
Presentations
Publications
- Sousa, H., Campos, R., Jorge, A. (2023) tieval: An Evaluation Framework for Temporal Information Extraction Systems In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 2871-2879, ACM.
- Gonçalves, F., Campos, R., and Jorge, A. (2023) Text2Storyline: generating enriched storylines from text. In European Conference on Information Retrieval, pp. 248-254.
- Castro, M., Jorge, A., and Campos, R. (2023) TweetStream2Story: Narrative Extraction from Tweets in Real Time. In European Conference on Information Retrieval, pp. 217-223.
- Silvano, P., Amorim, E., Leal, A., Cantante, I., Silva, M., Jorge, A., Campos, R., and Nunes, S. (2023) Annotation and visualisation of reporting events in textual narratives. In Proceedings of Text2Story 2023: Sixth Workshop on Narrative Extraction From Texts.
- Santana, B., Campos, R., Amorim, E., Jorge, A., Silvano, P., and Nunes, S. (2023) A survey on narrative extraction from textual data. In Artificial Intelligence Review. Springer.
- Loureiro, D., Jorge, A., and Camacho-Collados, J. (2022) LMMS reloaded: Transformer-based sense embeddings for disambiguation and beyond. In Artificial Intelligence Volume 305. Springer.
- Leal, A., Silvano, P., Amorim, E., Cantante, I., Fátima Silva, Jorge, A., and Campos, R. (2022) The place of ISO-Space in Text2Story multilayer annotation scheme. In LREC 2022 Workshop Language Resources and Evaluation Conference 20-25 June 2022, p. 61.
- Valente, J., Jorge, A., and Nunes, S. (2022) Text2Icons: linking icons to narrative participants. In Text2Story@ECIR, pp. 111-116.
- Luria, S., and Campos, R. (2022) Greening a Post-Industrial City: Applying Keyword Extractor Methods to Monitor a Fast-Changing Environmental Narrative. In: Unlocking Environmental Narratives: Towards Understanding Human Environment Interactions through Computational Text Analysis. Ed. by Ross S. Purves, Olga Koblet, and Benjamin Adams. London: Ubiquity Press, pp. 109–132.
- Jatowt, A., Doucet, A., and Campos, R. (2022) Diachronic Analysis of Time References in News Articles. In Companion Proceedings of The Web Conference 2022 (WWW2022). Lyon, France, April 25-29. ACM Press.
- Campos, V., Campos, R., Mota, P., and Jorge, A. (2022) Tweet2Story: A web app to Extract Narratives from Twitter. In: Mathias Hagen, Suzan Verberne, Craig Macdonald, Christin Seifert, Krisztian Balog, Kjetil Vorvag, Vinay Setty (eds), Advances in Information Retrieval. ECIR'22, Stavanger, Norway. April 10 - 14. Lecture Notes in Computer Science, vol 13186, pp. 270 - 275. Springer.
- Campos, R., Jorge, A., Jatowt, A., Sumit, B., and Litvak, M. (2022) Fifth International Workshop on Narrative Extraction from Texts (Text2Story'22). In: Mathias Hagen, Suzan Verberne, Craig Macdonald, Christin Seifert, Krisztian Balog, Kjetil Vorvag, Vinay Setty (eds), Advances in Information Retrieval. ECIR'22, Stavanger, Norway. April 10 - 14. Lecture Notes in Computer Science, vol 13186, pp. 552 - 556. Springer.
- Sato, M., Jatowt, A., Duan, Y., Campos, R., and Yoshikawa, M. (2021) Estimating Contemporary Relevance of Past News. In Joint Conference on Digital Libraries. JCDL’21. (pp. 70 - 79). 🏆 Vannevar Bush Best Paper Award 🏆
- Sousa, H. O. (2021) Temporal Relation Extraction: The Event Ordering Task. In Design of Experimental Search & Information REtrieval Systems 2021 (DESIRES'21), Padua, Italy.
- Silvano, P., Leal, A., Silva, F., Cantante, I., Oliveira, F., & Jorge, A. M. (2021) Developing a multilayer semantic annotation scheme based on ISO standards for the visualization of a newswire corpus. In 17th Joint ACL-ISO Workshop on Interoperable Semantic (p. 1).
- Purificação, S., Leal, A., Silva, F., Cantante, I., Oliveira, F., and Jorge, A. (2021) Developing a multilayer semantic annotation scheme based on ISO standards for the visualization of a newswire corpus. In Proceedings of the 17th Joint ACL-ISO Workshop on Interoperable Semantic Annotation, pp. 1-13.
- Campos, R., Pasquali, A., Jatowt, A., Mangaravite, V., & Jorge, A. M. (2021) Automatic Generation of Timelines for Past-Web Events. In The Past Web (pp. 225-242). Springer, Cham.
- Amorim E., Ribeiro, A., Cantante, I., Jorge, A., Santana, B., Nunes, S., Silvano, P., Leal, A., and Campos, R. (2021) Brat2Viz: a Tool and Pipeline for Visualizing Narratives from Annotated Texts. In Proceedings of the 4th International Workshop on Narrative Extraction from Texts (Text2Story 2021) associated to 43rd International Conference on Information Retrieval (ECIR2021). Online, April, 1st.
- Pasquali, A., Campos, R., Ribeiro, A., Santana, B., Jorge, A., and Jatowt, A. (2021) TLS-Covid19: A New Annotated Corpus for Timeline Summarization. In: Hiemstra D., Moens M-F., Mothe J., Perego R., Potthast M., Sebastiani F. (eds), Advances in Information Retrieval. ECIR'21 (Lucca, Italy. March 28 - April 1). Lecture Notes in Computer Science, vol 12656, pp. 497 - 512.
- Campos, R., Duque, J., Cândido, T., Mendes, J., Dias, G., Jorge, A., and Nunes, C. (2021) Time-Matters: Temporal Unfolding of Texts. In: Hiemstra D., Moens M-F., Mothe J., Perego R., Potthast M., Sebastiani F. (eds), Advances in Information Retrieval. ECIR'21 (Lucca, Italy. March 28 - April 1). Lecture Notes in Computer Science, vol 12657, pp. 492 - 497. Springer.
- Jatowt, A., Hung, I-C., Färber, M., Campos, R., and Yoshikawa, M. (2021) Exploding TV Sets & Disappointing Laptops: Archival Content Suggestion by Finding Interesting Content from the Past. In: Hiemstra D., Moens M-F., Mothe J., Perego R., Potthast M., Sebastiani F. (eds), Advances in Information Retrieval. ECIR'21 (Lucca, Italy. March 28 - April 1). Lecture Notes in Computer Science, vol 12656, pp. 254 - 269.
- Campos, R., Jorge, A., Jatowt, A., Sumit, B., and Finlayson, M. (2021) Fourth International Workshop on Narrative Extraction from Texts (Text2Story'21). In: Hiemstra D., Moens M-F., Mothe J., Perego R., Potthast M., Sebastiani F. (eds), Advances in Information Retrieval. ECIR'21 (Lucca, Italy. March 28 - April 1). Lecture Notes in Computer Science, vol 12657, pp. 701 - 704.
- Campos, R., Pasquali, A., Jatowt, A., Mangaravite, V., Jorge, A. (2021) Automatic Generation of Timelines for Past-Web Events. In Gomes, D., Demidova, E., Winters, J., Risse, T. (Eds.), The Past Web. Exploring Web Archives (pp. 225-242). Springer Nature Switzerland AG
- Balali, A., Asadpour, M., Campos, R., and Jatowt, A. (2020) Joint Event Extraction along Shortest Dependency Paths using Graph Convolutional Networks. In Knowledge-Based Systems Journal. Elsevier, Vol 210
MSc Dissertations
- Rúben Almeida (2023) Building Portuguese Language Resources for Natural Language Processing Tasks FEUP (orientador: Alípio Jorge, coorientador: Sérgio Nunes)
- Francisco Gonçalves (2022) Text2Storyline: Generating Enriched Storylines From Text FCUP (orientador: Ricardo Campos, coorientador: Alípio Jorge)
- Mafalda Castro (2022) How good are stories told by Twitter? An NLP Approach FCUP (orientador: Alípio Jorge, coorientador: Ricardo Campos)
- Vasco Campos (2021) Extracting narratives from Twitter FCUP (orientador: Alípio Jorge, coorientador: Ricardo Campos)
- Mariana Costa (2021) Narrative Visualization of News Stories FCUP (orientador: Sérgio Nunes)
- Joana Valente (2021) Text2Icons: Using AI to Tell a Story with Icons FCUP (orientador: Alípio Jorge, coorientador: Sérgio Nunes)
- Sofia Oliveira (2020) Semantic Role Labeling in Portuguese: Improving the State of the Art with Transfer Learning and BERT - based Models. FCUP (orientador: Alípio Jorge, coorientador: Daniel Loureiro)
BSc Dissertations
- Pedro Mota (2021). Pipeline for narrative extraction. FCUP (orientador: Alípio Jorge)
Acknowledgements
This project is financed by the ERDF – European Regional Development Fund through the North Portugal Regional Operational Programme (NORTE 2020), under the PORTUGAL 2020 and by National Funds through the Portuguese funding agency, FCT - Fundação para a Ciência e a Tecnologia within project PTDC/CCI-COM/31857/2017 (NORTE-01-0145-FEDER-03185)
