newsLens: building and visualizing long-ranging news stories

@inproceedings{Laban2017newsLensBA,
  title={newsLens: building and visualizing long-ranging news stories},
  author={Philippe Laban and Marti A. Hearst},
  booktitle={NEWS@ACL},
  year={2017}
}
We propose a method to aggregate and organize a large, multi-source dataset of news articles into a collection of major stories, and automatically name and visualize these stories in a working system. [...] Key Method The visual interface consists of lanes of timelines, each annotated with information that is deemed important for the story, including extracted quotations. The working system allows a user to search and navigate 8 years of story information.Expand
A framework for a text-centric user interface for navigating complex news stories
Many news articles are part of larger news stories that unfold over a period of time. Detecting these news stories, and presenting them to news readers is appealing, as it allows the reader to accessExpand
Batch Clustering for Multilingual News Streaming
TLDR
This work introduces a novel "replaying" strategy to link monolingual local topics into stories and proposes new fine tuned multilingual embedding using SBERT to create crosslingual stories. Expand
Automatic Story Construction from News Articles in an Online Fashion
TLDR
A novel story construction system to track the evolution of stories in an online fashion using a novel sliding window solution, named Inching Window, allowing the processing of each new data element on-the-fly. Expand
What’s The Latest? A Question-driven News Chatbot
TLDR
The algorithmic framework for an automatic news chatbot is described and the results of a usability study are presented that shows that news readers using the system successfully engage in multi-turn conversations about specific news stories. Expand
Dense vs. Sparse Representations for News Stream Clustering
TLDR
The evaluation results on a standard dataset show a sizeable improvement over the state of the art both for the standard F1 as well as for a BCubed version thereof, which is argued is more suitable for the task. Expand
The Summary Loop: Learning to Write Abstractive Summaries Without Examples
TLDR
This work introduces a novel method that encourages the inclusion of key terms from the original document into the summary that attains higher levels of abstraction with copied passages roughly two times shorter than prior work, and learns to compress and merge sentences without supervision. Expand
Using Generative Pretrained Transformer-3 Models for Russian News Clustering and Title Generation tasks
The paper presents a methodology for news clustering and news headline generation based on the zero-shot approach and minimal tuning of the RuGPT-3 architecture (Generative Pretrained Transformer 3Expand
Event-Driven News Stream Clustering using Entity-Aware Contextual Embeddings
TLDR
It is shown that the use of a suitable fine-tuning objective and external knowledge in pre-trained transformer models yields significant improvements in the effectiveness of contextual embeddings for clustering. Expand
Real-time Claim Detection from News Articles and Retrieval of Semantically-Similar Factchecks
TLDR
This method allows us to compare incoming claims to an existing corpus and return similar, factchecked, claims in a live system-allowing factcheckers to work simultaneously without duplicating their work. Expand
Event-Centric Natural Language Processing
  • Muhao Chen, Hongming Zhang, +4 authors D. Roth
  • Computer Science
  • Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: Tutorial Abstracts
  • 2021
TLDR
This tutorial will provide audience with a systematic introduction of knowledge representations of events, various methods for automated extraction, conceptualization and prediction of events and their relations, and a wide range of NLU and commonsense understanding tasks that benefit from aforementioned techniques. Expand
...
1
2
...

References

SHOWING 1-10 OF 13 REFERENCES
Story Tracker: Incremental visual text analytics of news story development
TLDR
A visual analytics system for temporal analysis of news stories in dynamic information streams, which combines interactive visualization and text mining techniques to facilitate the analysis of similar topics that split and merge over time is presented. Expand
Storylines for structuring massive streams of news
TLDR
A formal model for representing storylines to handle streams of news and a first implementation of a system that automatically extracts the ingredients of a storyline from news articles according to the model are described. Expand
Unified analysis of streaming news
TLDR
This paper presents a unified framework to group incoming news articles into temporary but tightly-focused storylines, to identify prevalent topics and key entities within these stories, and to reveal the temporal structure of stories as they evolve. Expand
Story tracking: linking similar news over time and across languages
TLDR
The evaluation of the monolingual aggregation of historical clusters into stories and of the linking of stories across languages yielded mostly satisfying results. Expand
Automatic generation of overview timelines
TLDR
A statistical model of feature occurrence over time is presented, and tests based on classical hypothesis testing for significance of term appearance on a given date are developed, to generate "topics" as defined by the Topic Detection and Tracking study. Expand
Trains of thought: generating information maps
TLDR
This work proposes a methodology for creating structured summaries of information, which is able to produce maps which help users acquire knowledge efficiently and integrates user interaction into the framework, allowing users to alter the maps to better reflect their interests. Expand
A Sequence Labelling Approach to Quote Attribution
TLDR
This work treats the quote extraction and attribution problem as a sequence labelling task, which allows it to incorporate sequence features without using gold standard information, achieving a new state-of-the-art for systems using only realistic features. Expand
Automatic Detection of Quotations in Multilingual News
TLDR
Automatic news analysis software that identifies direct speech quotations as part of its automatic analysis of more than 20,000 news articles per day in currently 11 languages is presented. Expand
Can Social Tagging Improve Web Image Search?
TLDR
A method that replaces an abstract query term given by a user with a set of concrete terms and that uses these terms in queries input into Web image search engines to improve the recall ratio of Web image searches. Expand
Fast unfolding of communities in large networks
TLDR
This work proposes a heuristic method that is shown to outperform all other known community detection methods in terms of computation time and the quality of the communities detected is very good, as measured by the so-called modularity. Expand
...
1
2
...