Information Extraction System

An Information Extraction System is a data processing system that can solve an information extraction task (by implementing an information extraction algorithm).

• AKA: Information Extractor, IE System.
• Context:
  • It can range from being a Heuristic Information Extraction System to being a Data-Driven Information Extraction System.
  • It can be, depending on the data source, range from being an IE from Text System to being an IE from Audio System to being an IE from Images System to being an IE from Semi-Structured Data System.
  • It can be an Ontology-based IE System.
  • It can be an Information Extraction Software Framework, such as ANNIE and cTAKES.
  • It can range from being a Open Information Extraction System to being a Closed Information Extraction System.
• Example(s):
  • a Template Filling System,
  • a Knowledge Base Population System, or an Ontology Population System;
  • a Definitional Sentence Extraction System.
  • a Semi-structured Information Extraction System,
  • a General Architecture for Text Engineering (GATE) System,
  • an ANNIE System which is part of the GATE System,
  • a Apache OpenNLP,
  • an OpenCalais,
  • a Machine Learning for Language Toolkit (Mallet),
  • a DBpedia Spotlight,
  • a Natural Language Toolkit,
  • a DeepDive.
  • a Geoparsepy
  • a Read the Web
  • a CogComp Relation Extraction.
  • a cTAKES System.
  • …
• Counter-Example(s):
  • an Information Retrieval System,
  • a Named Entity Recognition System,
  • a Part-Of-Speech (POS) Tagging System.
  • a Sentence Segmentation System,
  • a Tokenization System,
  • a Word Sense Disambiguation System.
• See: Semantic Relation Recognition System, Pattern Extractor, Natural Language Processing System.

---

---

References

2023

• (Wei, Cui et al., 2023) ⇒ Xiang Wei, Xingyu Cui, Ning Cheng, Xiaobin Wang, Xin Zhang, Shen Huang, Pengjun Xie, Jinan Xu, Yufeng Chen, Meishan Zhang and others. (2023). “Zero-shot Information Extraction via Chatting with Chatgpt.” In: arXiv preprint arXiv:2302.10205. doi:10.48550/arXiv.2302.10205
  • QUOTE: Zero-shot information extraction (IE) aims to build IE systems from the unannotated text. ...

2019

• (Wikipedia, 2019) ⇒ https://en.wikipedia.org/wiki/Information_extraction Retrieved:2019-3-10.
  • Information extraction (IE) is the task of automatically extracting structured information from unstructured and/or semi-structured machine-readable documents. In most of the cases this activity concerns processing human language texts by means of natural language processing (NLP). Recent activities in multimedia document processing like automatic annotation and content extraction out of images/audio/video/documents could be seen as information extraction

    Due to the difficulty of the problem, current approaches to IE focus on narrowly restricted domains. An example is the extraction from newswire reports of corporate mergers, such as denoted by the formal relation:

    [math]\displaystyle{ \mathrm{MergerBetween}(company_1, company_2, date) }[/math] ,

    from an online news sentence such as:

    "Yesterday, New York based Foo Inc. announced their acquisition of Bar Corp."

    A broad goal of IE is to allow computation to be done on the previously unstructured data. A more specific goal is to allow logical reasoning to draw inferences based on the logical content of the input data. Structured data is semantically well-defined data from a chosen target domain, interpreted with respect to category and context.

    Information Extraction is the part of a greater puzzle which deals with the problem of devising automatic methods for text management, beyond its transmission, storage and display. The discipline of information retrieval (IR) has developed automatic methods, typically of a statistical flavor, for indexing large document collections and classifying documents. Another complementary approach is that of natural language processing (NLP) which has solved the problem of modelling human language processing with considerable success when taking into account the magnitude of the task. In terms of both difficulty and emphasis, IE deals with tasks in between both IR and NLP. In terms of input, IE assumes the existence of a set of documents in which each document follows a template, i.e. describes one or more entities or events in a manner that is similar to those in other documents but differing in the details. An example, consider a group of newswire articles on Latin American terrorism with each article presumed to be based upon one or more terroristic acts. We also define for any given IE task a template, which is a(or a set of) case frame(s) to hold the information contained in a single document. For the terrorism example, a template would have slots corresponding to the perpetrator, victim, and weapon of the terroristic act, and the date on which the event happened. An IE system for this problem is required to “understand” an attack article only enough to find data corresponding to the slots in this template.

2009

• (Bird et al., 2009) ⇒ Steven Bird, Ewan Klein, and Edward Loper. (2009). "Extracting Information from Text". In:“Natural Language Processing with Python." O'Reilly Media. ISBN:9780596555719 (Chapter 7).
  • QUOTE: Figure 7-1 shows the architecture for a simple information extraction system. It begins by processing a document using several of the procedures discussed in Chapters 3 and 5: first, the raw text of the document is split into sentences using a sentence segmenter, and each sentence is further subdivided into words using a tokenizer. Next, each sentence is tagged with part-of-speech tags, which will prove very helpful in the next step, named entity recognition. In this step, we search for mentions of potentially interesting entities in each sentence. Finally, we use relation recognition to search for likely relations between different entities in the text.
    

    Figure 7-1. Simple pipeline architecture for an information extraction system. This system takes the raw text of a document as its input, and generates a list of (entity, relation, entity) tuples as its output. For example, given a document that indicates that the company Georgia-Pacific is located in Atlanta, it might generate the tuple ([ORG: 'Georgia-Pacific'] 'in' [LOC: 'Atlanta']).

---