Paper—Event-Time Relationship in Natural Language Text Event Time Relationship in Natural Language Text https://doi.org/10.3991/ijes.v7i3.10985 Vanitha Guda () Chaithanya Bharathi Institute of Technology (A), Hyderabad, India gvanitha_cse@cbit.ac.in SureshKumar Sanampudi JNTUH College of Engg. Jagityal, Karimnagar, India Abstract—Due to the numerous information needs, retrieval of events from a giv- en natural language text is inevitable. In natural language processing (NLP) perspec- tive, "Events" are situations, occurrences, real-world entities or facts. Extraction of events and arranging them on a timeline is helpful in various NLP application like building the summary of news articles, processing health records, and Question An- swering System (QA) systems. This paper presents a framework for identifying the events and times from a given document and representing them using a graph data structure. As a result, a graph is derived to show event-time relationships in the given text. Events form the nodes in a graph, and edges represent the temporal relations among the nodes. Time of an event occurrence exists in two forms namely qualitative (like before, after, duringetc) and quantitative (exact time points/periods). To build the event-time-event structure quantitative time is normalized to qualitative form. Thus obtained temporal information is used to label the edges among the events. Data set released in the shared task EvTExtract of (Forum for Information Retrieval Extrac- tion) FIRE 2018 conference is identified to evaluate the framework. Precision and recall are used as evaluation metrics to access the performance of the proposed framework with other methods mentioned in state of the art with 85% of accuracy and 90% of precision. Keywords—Natural language processing, Temporal Events, Event-Time Graph, Ques- tion Answering, Time Graph. 1 Introduction In the present digital information era, there is exploitation of data which is resulting in a massive number of textual information sources (e.g., web, majorly news, tweets, historical texts, electronic health records, legal reports) that are mostly with the de- scriptions of events, extracting and analyzing events from a given document is found to be an essential task. In linguistic terms events in the text are referred to as event mentions. Due to ambiguities and vagueness of text representation in natural lan- guage, the mapping of real-world events and their relations counterparts causes some loss of information. Existing works of NLP mainly discuss the sentence-level event mentions and doc- ument level events within the topic. In Topic Detection and Tracking (TDT), "event" 4 http://www.i-jes.org