To Extend or Not to Extend? Context-Specific Corpus Enrichment

Felix Kuhr; Tanya Braun; Magnus Bender; R. Möller

doi:10.1007/978-3-030-35288-2_29

To Extend or Not to Extend? Context-Specific Corpus Enrichment

Felix Kuhr
, Tanya Braun
, Magnus Bender
, R. Möller

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

14 Citations (Scopus)

Abstract

An agent in pursuit of a task may work with a corpus of documents with linked subjective content descriptions. Faced with a new document, an agent has to decide whether to include that document in its corpus or not. Basing the decision on only words, topics, or entities, has shown to not lead to a balanced performance for varying documents. Therefore, this paper presents an approach for an agent to decide if a new document adds value to its existing corpus by combining texts and content descriptions. Furthermore, an agent can use the approach as a starting point for high quality content descriptions for new documents. A case study shows the effectiveness of our approach given varying types of new documents.

Original language	English
Title of host publication	AI 2019 : Advances in Artificial Intelligence - 32nd Australasian Joint Conference, 2019, Proceedings
Editors	Jixue Liu, James Bailey
Number of pages	12
Volume	11919
Publication date	25 Nov 2019
Pages	357-368
ISBN (Print)	9783030352875
DOIs	https://doi.org/10.1007/978-3-030-35288-2_29
Publication status	Published - 25 Nov 2019
Externally published	Yes
Event	Australasian Joint Conference: Advances in Artificial Intelligence - Adelaide, Australia Duration: 2 Dec 2019 → 5 Dec 2019 Conference number: 32

Conference

Conference	Australasian Joint Conference
Number	32
Country/Territory	Australia
City	Adelaide
Period	02/12/2019 → 05/12/2019

Keywords

Named Entity Recognition
Semantics
Text mining
Subjective content description
Recommender Systems
Models
Entailment
Embedding

Access to Document

10.1007/978-3-030-35288-2_29

Citation Styles

@inproceedings{9bdc0c65b0bd4433a7f3891b5f0576ae,

title = "To Extend or Not to Extend? Context-Specific Corpus Enrichment",

abstract = "An agent in pursuit of a task may work with a corpus of documents with linked subjective content descriptions. Faced with a new document, an agent has to decide whether to include that document in its corpus or not. Basing the decision on only words, topics, or entities, has shown to not lead to a balanced performance for varying documents. Therefore, this paper presents an approach for an agent to decide if a new document adds value to its existing corpus by combining texts and content descriptions. Furthermore, an agent can use the approach as a starting point for high quality content descriptions for new documents. A case study shows the effectiveness of our approach given varying types of new documents.",

keywords = "Named Entity Recognition, Semantics, Text mining, Subjective content description, Recommender Systems, Models, Entailment, Embedding, Embedding, Entailment, Named Entity Recognition, Recommender Systems, Semantics, Models, Text mining, Subjective content description",

author = "Felix Kuhr and Tanya Braun and Magnus Bender and R. M{\"o}ller",

year = "2019",

month = nov,

day = "25",

doi = "10.1007/978-3-030-35288-2\_29",

language = "English",

isbn = "9783030352875",

volume = "11919",

pages = "357--368",

editor = "Jixue Liu and James Bailey",

booktitle = "AI 2019",

note = "Australasian Joint Conference : Advances in Artificial Intelligence , AI 2019 ; Conference date: 02-12-2019 Through 05-12-2019",

}

Kuhr, F, Braun, T, Bender, M & Möller, R 2019, To Extend or Not to Extend? Context-Specific Corpus Enrichment. in J Liu & J Bailey (eds), AI 2019: Advances in Artificial Intelligence - 32nd Australasian Joint Conference, 2019, Proceedings. vol. 11919, pp. 357-368, Australasian Joint Conference, Adelaide, South Australia, Australia, 02/12/2019. https://doi.org/10.1007/978-3-030-35288-2_29

To Extend or Not to Extend? Context-Specific Corpus Enrichment. / Kuhr, Felix; Braun, Tanya; Bender, Magnus et al.
AI 2019: Advances in Artificial Intelligence - 32nd Australasian Joint Conference, 2019, Proceedings. ed. / Jixue Liu; James Bailey. Vol. 11919 2019. p. 357-368.

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - To Extend or Not to Extend? Context-Specific Corpus Enrichment

AU - Kuhr, Felix

AU - Braun, Tanya

AU - Bender, Magnus

AU - Möller, R.

N1 - Conference code: 32

PY - 2019/11/25

Y1 - 2019/11/25

N2 - An agent in pursuit of a task may work with a corpus of documents with linked subjective content descriptions. Faced with a new document, an agent has to decide whether to include that document in its corpus or not. Basing the decision on only words, topics, or entities, has shown to not lead to a balanced performance for varying documents. Therefore, this paper presents an approach for an agent to decide if a new document adds value to its existing corpus by combining texts and content descriptions. Furthermore, an agent can use the approach as a starting point for high quality content descriptions for new documents. A case study shows the effectiveness of our approach given varying types of new documents.

AB - An agent in pursuit of a task may work with a corpus of documents with linked subjective content descriptions. Faced with a new document, an agent has to decide whether to include that document in its corpus or not. Basing the decision on only words, topics, or entities, has shown to not lead to a balanced performance for varying documents. Therefore, this paper presents an approach for an agent to decide if a new document adds value to its existing corpus by combining texts and content descriptions. Furthermore, an agent can use the approach as a starting point for high quality content descriptions for new documents. A case study shows the effectiveness of our approach given varying types of new documents.

KW - Named Entity Recognition

KW - Semantics

KW - Text mining

KW - Subjective content description

KW - Recommender Systems

KW - Models

KW - Entailment

KW - Embedding

KW - Entailment

KW - Named Entity Recognition

KW - Recommender Systems

KW - Semantics

KW - Models

KW - Text mining

KW - Subjective content description

U2 - 10.1007/978-3-030-35288-2_29

DO - 10.1007/978-3-030-35288-2_29

M3 - Article in proceedings

SN - 9783030352875

VL - 11919

SP - 357

EP - 368

BT - AI 2019

A2 - Liu, Jixue

A2 - Bailey, James

T2 - Australasian Joint Conference

Y2 - 2 December 2019 through 5 December 2019

ER -