Named Entity Recognition Experiments on Turkish Texts
Dilek Küçük
1and Adnan Yazıcı
21
TÜBİTAK - Uzay Institute, Ankara - Turkey dilek.kucuk@uzay.tubitak.gov.tr
2
Dept. of Computer Engineering, METU, Ankara - Turkey
yazici@ceng.metu.edu.tr
Outline
Introduction
Named Entity Recognition in Turkish
Evaluation
Evaluation on News Texts
Evaluation on Child Stories and Historical Texts
Evaluation on Video Texts
Future Work
Conclusion
Introduction [1]
Named entity recognition (NER) is one of the main information extraction (IE) tasks
recognition of names of people, locations,
organizations as well as temporal and numeric expressions in texts (Nadeau and Sekine, 2007).
NER task is known to be a solved problem
especially for English with state-of-the-art
performance above 90 %.
Introduction [2]
NER research in Turkish is known to be rare.
Language-independent IE system (Cucerzan and Yarowsky, 1999)
Statistical name tagger for Turkish (Tür et al, 2003)
Person name tagger for financial news texts (Bayraktar and Taşkaya-Temizel, 2008)
Person mention extractor and a string matching based
coreference resolver (Küçük and Yazıcı, 2008)
Introduction [3]
In this study, we present a rule-based system for named entity recognition from Turkish texts.
Proposed for the domain of news texts.
Evaluated on
Newswire texts
Child stories and historical texts
News video transcriptions
Named Entity Recognition in Turkish [1]
The domain is determined as news texts.
News texts from METU Turkish corpus (Say et al., 2002) are examined.
Capitalization and punctuation clues are not utilized
Since they may be missing in automatic speech
recognition (ASR) outputs and texts obtained
from the Web.
Named Entity Recognition in Turkish [2]
A set of information sources has been compiled.
Named Entity Recognition in Turkish [3]
The lexical resources include
a dictionary of person names in Turkish comprising about 8300 entries,
a list of well-known political people,
a list of well-known locations (the names of cities and towns) in Turkey as well as in the world,
a list of well-known organizations in Turkey and
those in the world.
Named Entity Recognition in Turkish [4]
Pattern bases for the extraction of location/organization names as well as that of the numeric/temporal expressions.
The system makes use of a simple morphological analyzer to
validate candidates.
Evaluation [1]
The system tags its output with Message
Understanding Conference (MUC) style named entity tags:
ENAMEX, TIMEX, and NUMEX
An annotation tool is developed to annotate the evaluation texts with the same tags to create
answer sets.
Evaluation is performed by comparing the
Evaluation [2]
The Annotation Tool
Evaluation [3]
Evaluation is performed in terms of precision, recall,
and f-measure
Evaluation on News Text [1]
Evaluation on News Text [2]
Evaluation on News Text [3]
The precision of person name recognition using only a dictionary of person names turns out to be too low.
Savaş („war‟), barış („peace‟), özen („care‟)…
During location and organization name recognition, the system performs erroneous extractions.
anlatmanın yolu (the way to tell),
ilk üniversitesi (first university)…
Organization name recognition also suffers from the erroneous extractions in case of compound organization names.
İstanbul Üniversitesi Siyasal Bilgiler Fakültesi…
„İstanbul University Political Science Faculty‟
as „İstanbul Üniversitesi‟ and „Bilgiler Fakültesi‟
Evaluation on News Text [4]
As opposed to the statistical system (Tür et al., 2003), the rule based system considers numeric and temporal expressions
in addition to the person, location, organization names.
The statistical system has been trained on a set of news articles with 492821 words (37277 NEs).
The statistical system has been tested on a news article set of about 28000 words (2197 NEs) and has achieved a best performance of 91.56 % in f-measure.
The rule-based system has been tested on a set of 20131 words (1591 NEs) and achieved an f-measure of 78.7 %.
The statistical system performs deeper language
Evaluation on Child Stories and Historical Texts [1]
The child stories set comprises two stories by the same author (Ilgaz, 2003a-b).
The historical text includes the first three chapters of a
book describing five cities mostly on their historical basis
(Tanpınar, 2007).
Evaluation on Child Stories and Historical Texts [2]
The main problem for child stories data set is the existence of foreign person names throughout the stories.
The performance drop for historical text is due to the
nonexistence of historical person names and organizations (such as the names of empires) in the lexical resources.
The results are in line with the well-known finding that rule-
Evaluation on Video Texts [1]
An important research area which can benefit from IE techniques is automatic multimedia annotation.
Several studies are carried out on employing especially NER output for semantic multimedia annotation.
Multimedia indexing system for English, German and Dutch football videos (Saggion et al., 2004)
Video annotation system for Italian news videos (Basili et al., 2005)
Automatic annotation system for BBC radio and TV news
(Dowman et al., 2005)
Evaluation on Video Texts [2]
We have compiled a video data set of Turkish news videos
From the Web site of Turkish Radio and Television Company (TRT).
Comprising 16 videos with a total duration of two hours.
The videos are manually transcribed leading to a text of 9804 words
Since no general purpose automatic speech recognizer
exists for Turkish.
Evaluation on Video Texts [3]
The transcription text is annotated with named entity tags
resulting in 1090 named entities (256 person, 479 location, and 222 organization names, 70 numeric and 63 temporal expressions).
Evaluation of the recognizer on the text resulted in a
precision of 73.3%, a recall of 77.0%, and so an f-measure of 75.1%.
The results on video transcriptions are satisfactory for a first attempt of named entity recognition on genuine video texts
It is significant step towards the employment of IE
techniques for semantic annotation of videos in Turkish.
Future Work
Future work based on the current study includes
Improvement of the system benefiting from the error analyses.
Extending the system to output finer grained named entity classes employing a named entity ontology.
Employment of machine learning algorithms for the NER task
The results can be compared with that of the rule
Conclusion [1]
Information extraction in Turkish is a rarely studied research area.
In this study, we have presented a rule-based system for named entity recognition from Turkish texts.
Initially engineered for news texts.
Employs a set of lexical resources and pattern bases.
Being a rule-based system, needs no training data.
Evaluated on diverse text types including news texts, child stories, historical texts, and news video
transcriptions.
Conclusion [2]
The evaluation results for the news texts and news video transcriptions are satisfactory for a first attempt
Yet, the results for child stories and historical texts are very low.
In line with the finding that rule-based IE systems
suffer from considerable performance drop when
evaluated on other domains.
References [1]
1.
Roberto Basili, Marco Cammisa, and Emanuale Donati. RitroveRAI: A web application for semantic indexing and hyperlinking of multimedia news. In Proceedings of International Semantic Web Conference, 2005.
2.
Özkan Bayraktar and Tuğba Taşkaya-Temizel. Person name extraction from Turkish Financial news text using local grammar based approach.
In Proceedings of the International Symposium on Computer and Information Sciences, 2008.
3.
Silviu Cucerzan and David Yarowsky. Language independent named
entity recognition combining morphological and contextual evidence. In Proceedings of the Joint SIGDAT Conference on Empirical Methods in Natural Language Processing and Very Large Corpora, 1999.
4.
Mike Dowman, Valentin Tablan, Hamish Cunningham, and Borislav Popov. Web-assisted annotation, semantic indexing and search of
television and radio news. In Proceedings of the International Conference on World Wide Web (WWW), 2005.
5.
Rıfat Ilgaz. Bacaksız Kamyon Sürücüsü. Çınar Publications, 2003.
6.
Rıfat Ilgaz. Bacaksız Tatil Köyünde. Çınar Publications, 2003.
References [2]
7.
Dilek Küçük and Adnan Yazıcı. Identification of coreferential chains in video texts for semantic annotation of news videos. In Proceedings of the International Symposium on Computer and Information Sciences, 2008.
8.
David Nadeau and Satoshi Sekine. “A Survey of Named Entity
Recognition and Classification”, Linguistica Investigationes, 2007, vol.
30, no. 1, pp.3-26.
9.
Bilge Say, Deniz Zeyrek, Kemal Oflazer, and Umut Özge. Development of a corpus and a treebank for present-day written Turkish. In Proceedings of the 11th International Conference of Turkish Linguistics (ICTL), 2002.
10.
Ahmet Hamdi Tanpınar. Beş Şehir. Dergah Publications, 2007.
11.
Horacio Saggion, Hamish Cunningham, Kalina Bontcheva, Diana
Maynard, Oana Hamza, and Yorick Wilks. Multimedia indexing through multi-source and multi-language information extraction: MUMIS project.
Data and Knowledge Engineering, 48:247-264, 2004.
12.