Loading...
Please wait, while we are loading the content...
Similar Documents
Temporal Information Extraction Extracting Events and Temporal Expressions A Literature Survey
| Content Provider | Semantic Scholar |
|---|---|
| Author | Gupta, Naman |
| Copyright Year | 2015 |
| Abstract | Introduction Information on web is increasing at infinitum. There exists plethora of data on World Wide Web (WWW) in various electronic and digital form. Thus, web has become an unstructured global area where information even if available, cannot be directly used for desired applications. One is often faced with an information overload and demands for some automated help. Information extraction (IE) is the task of automatically extracting structured information from unstructured and/or semi-structured machine-readable documents by means of Text Mining and Natural Language Processing (NLP) techniques. Extracted structured information can be used for variety of enterprise or personal level task of varying complexity. In this survey report we will discuss literature related to temporal expressions and event extraction. Temporal Expression Recognition (TER) is the process of locating phrases that denote temporal information. Temporal expressions may be an expressed point in time, a duration or a frequency. These expressions can be used in information extraction and question-answering to (a) answer time-specific queries, (b) arrange information in a chronological manner, etc. Research in TER mostly exists in news domain text, arguably because of availability of large corpora and presence of temporal expressions in news documents. In recent times, TER has also been applied to other domains like medical (Sohn et al., were considered a type of named entities and their identification was part of the named entity recognition task. Since the Automatic Content Extraction program 1 in 2004 there has been a separate task identified and called Temporal Expression Recognition and Normalisation (TERN). Timex evaluation is now evaluated in two major temporal annotation challenges: TempEval 2 and i2b2 3 , both of which prefer the TimeML-level TIMEX3 standard. Recently, Temporal Expression Recog-1 nition was a track in Clinical TempEval of SemEval 2015 4 challenge. It aims at extracting temporal information from clinical notes and pathology reports for cancer patients from the Mayo Clinic. Based on what temporal information expression refers to, there are different temporal expressions. a point in time or a duration. In addition, there are different realizations of temporal expressions in natural language. Depending on the realization, different types of information are required to determine the normalized meaning of an expression. Types of Temporal Expressions • Date Expressions: A date expression refers to a point in time of the granularity " day " (e.g. " June 18, 2015 " or any other coarser granularity, like " month " (e.g., " … |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | http://www.cfilt.iitb.ac.in/resources/surveys/Temporal_Information_Extraction-Naman-June15.pdf |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
