Know-Center at SemEval-2016 Task 5: Using Word Vectors with Typed Dependencies for Opinion Target Expression Extraction

Stefan Falk; Andi Rexha; Roman Kern

doi:10.18653/v1/s16-1042

Know-Center at SemEval-2016 Task 5: Using Word Vectors with Typed Dependencies for Opinion Target Expression Extraction

Stefan Falk, Andi Rexha, Roman Kern

Publikation: Beitrag in Buch/Bericht/Konferenzband › Beitrag in einem Konferenzband › Begutachtung

Abstract

This paper describes our participation in SemEval-2016 Task 5 for Subtask 1, Slot 2. The challenge demands to find domain specific target expressions on sentence level that refer to reviewed entities. The detection of target words is achieved by using word vectors and their grammatical dependency relationships to classify each word in a sentence into target or non-target. A heuristic based function then expands the classified target words to the whole target phrase. Our system achieved an F1 score of 56.816% for this task. © 2016 Association for Computational Linguistics.

Originalsprache	deutsch
Titel	Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016)
DOIs	https://doi.org/10.18653/v1/s16-1042
Publikationsstatus	Veröffentlicht - 2016
Veranstaltung	10th International Workshop on Semantic Evaluation: SemEval 2016 - San Diego, USA / Vereinigte Staaten Dauer: 16 Juni 2016 → 17 Juni 2016

Konferenz

Konferenz	10th International Workshop on Semantic Evaluation
Land/Gebiet	USA / Vereinigte Staaten
Ort	San Diego
Zeitraum	16/06/16 → 17/06/16

Zugriff auf Dokument

10.18653/v1/s16-1042Lizenz: CC BY 4.0

Dieses zitieren

Falk, S, Rexha, A & Kern, R 2016, Know-Center at SemEval-2016 Task 5: Using Word Vectors with Typed Dependencies for Opinion Target Expression Extraction. in Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016). 10th International Workshop on Semantic Evaluation, San Diego, USA / Vereinigte Staaten, 16/06/16. https://doi.org/10.18653/v1/s16-1042

@inproceedings{e454834f75bf4324ad37936a9eac64d9,

title = "Know-Center at SemEval-2016 Task 5: Using Word Vectors with Typed Dependencies for Opinion Target Expression Extraction",

abstract = "This paper describes our participation in SemEval-2016 Task 5 for Subtask 1, Slot 2. The challenge demands to find domain specific target expressions on sentence level that refer to reviewed entities. The detection of target words is achieved by using word vectors and their grammatical dependency relationships to classify each word in a sentence into target or non-target. A heuristic based function then expands the classified target words to the whole target phrase. Our system achieved an F1 score of 56.816% for this task. {\textcopyright} 2016 Association for Computational Linguistics.",

author = "Stefan Falk and Andi Rexha and Roman Kern",

year = "2016",

doi = "10.18653/v1/s16-1042",

language = "deutsch",

booktitle = "Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016)",

note = "10th International Workshop on Semantic Evaluation : SemEval 2016 ; Conference date: 16-06-2016 Through 17-06-2016",

}

TY - GEN

T1 - Know-Center at SemEval-2016 Task 5: Using Word Vectors with Typed Dependencies for Opinion Target Expression Extraction

AU - Falk, Stefan

AU - Rexha, Andi

AU - Kern, Roman

PY - 2016

Y1 - 2016

N2 - This paper describes our participation in SemEval-2016 Task 5 for Subtask 1, Slot 2. The challenge demands to find domain specific target expressions on sentence level that refer to reviewed entities. The detection of target words is achieved by using word vectors and their grammatical dependency relationships to classify each word in a sentence into target or non-target. A heuristic based function then expands the classified target words to the whole target phrase. Our system achieved an F1 score of 56.816% for this task. © 2016 Association for Computational Linguistics.

AB - This paper describes our participation in SemEval-2016 Task 5 for Subtask 1, Slot 2. The challenge demands to find domain specific target expressions on sentence level that refer to reviewed entities. The detection of target words is achieved by using word vectors and their grammatical dependency relationships to classify each word in a sentence into target or non-target. A heuristic based function then expands the classified target words to the whole target phrase. Our system achieved an F1 score of 56.816% for this task. © 2016 Association for Computational Linguistics.

U2 - 10.18653/v1/s16-1042

DO - 10.18653/v1/s16-1042

M3 - Beitrag in einem Konferenzband

BT - Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016)

T2 - 10th International Workshop on Semantic Evaluation

Y2 - 16 June 2016 through 17 June 2016

ER -