Usefulness of temporal information automatically extracted from news articles for topic tracking. Kim, P. and Myaeng, S., H. Acm Transactions On Asian Language Information Processing, 3(4):227-242, 2004.
Usefulness of temporal information automatically extracted from news articles for topic tracking [link]Website  abstract   bibtex   
Temporal information plays an important role in natural language processing (NLP) applications such as information extraction, discourse analysis, automatic summarization, and question-answering. In the topic detection and tracking (TDT) area, the temporal information often used is the publication date of a message, which is readily available but limited in its usefulness. We developed a relatively simple NLP method for extracting temporal information from Korean news articles, with the goal of improving performance of TDT tasks. To extract temporal information, we make use of finite state automata and a lexicon containing timerevealing vocabulary. Extracted information is converted into a canonicalized representation of a time point or a time duration. We first evaluated and investigated the extraction and canonicalization methods for their accuracy and the extent to which temporal information extracted as such can help TDT tasks. The experimental results show that time information extracted from the text does indeed help to significantly improve both precision and recall.
@article{
 title = {Usefulness of temporal information automatically extracted from news articles for topic tracking},
 type = {article},
 year = {2004},
 identifiers = {[object Object]},
 keywords = {event detection tracking,temporal information extraction},
 pages = {227-242},
 volume = {3},
 websites = {http://portal.acm.org/citation.cfm?id=1039621.1039624},
 id = {a2fdde93-66d5-3264-b83a-7843f2605991},
 created = {2012-02-28T00:51:15.000Z},
 file_attached = {false},
 profile_id = {5284e6aa-156c-3ce5-bc0e-b80cf09f3ef6},
 group_id = {066b42c8-f712-3fc3-abb2-225c158d2704},
 last_modified = {2017-03-14T14:36:19.698Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {Kim2004},
 private_publication = {false},
 abstract = {Temporal information plays an important role in natural language processing (NLP) applications such as information extraction, discourse analysis, automatic summarization, and question-answering. In the topic detection and tracking (TDT) area, the temporal information often used is the publication date of a message, which is readily available but limited in its usefulness. We developed a relatively simple NLP method for extracting temporal information from Korean news articles, with the goal of improving performance of TDT tasks. To extract temporal information, we make use of finite state automata and a lexicon containing timerevealing vocabulary. Extracted information is converted into a canonicalized representation of a time point or a time duration. We first evaluated and investigated the extraction and canonicalization methods for their accuracy and the extent to which temporal information extracted as such can help TDT tasks. The experimental results show that time information extracted from the text does indeed help to significantly improve both precision and recall.},
 bibtype = {article},
 author = {Kim, Pyung and Myaeng, Sung Hyon},
 journal = {Acm Transactions On Asian Language Information Processing},
 number = {4}
}
Downloads: 0