EmpiriST 2015: A Shared Task on the Automatic Linguistic Annotation
            of Computer-Mediated Communication and Web Corpora

Beißwenger, Michael; Bartsch, Sabine; Evert, Stefan; Würzner, Kay-Michael

doi:10.18653/v1/w16-2606

Cited by 15 publications

(14 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We evaluate our approach on the dataset of the EmpiriST 2015 shared task on automatic linguistic annotation of computer-mediated communication and social media (Beißwenger et al 2016) and compare it to the two systems that performed best on the share task as baselines.…”

Section: Discussionmentioning

confidence: 99%

“…Results on the EmpiriST 2015 shared task dataset (Beißwenger et al 2016) show that our approach improves accuracy on out-of-vocabulary words by up to 5.8%; overall, we improve state-of-the-art by 0.4% to 90.9% accuracy.…”

Section: Introductionmentioning

confidence: 86%

“…For "non-standard" texts like social media or web texts, however, tagger performance is usually much lower. For the EmpiriST 2015 shared task dataset considered in this paper, Beißwenger et al (2016) report accuracy scores of 80-82% for off-the-shelf taggers.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Fine-Grained POS Tagging of German Social Media and Web Texts

Thater

2018

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. This paper presents work on part-of-speech tagging of German social media and web texts. We take a simple Hidden Markov Model based tagger as a starting point, and extend it with a distributional approach to estimating lexical (emission) probabilities of out-ofvocabulary words, which occur frequently in social media and web texts and are a major reason for the low performance of off-the-shelf taggers on these types of text. We evaluate our approach on the recent EmpiriST 2015 shared task dataset and show that our approach improves accuracy on out-of-vocabulary tokens by up to 5.8%; overall, we improve state-ofthe-art by 0.4% to 90.9% accuracy.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 86%

See 1 more Smart Citation

Fine-Grained POS Tagging of German Social Media and Web Texts

Thater

2018

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…For example, Ljubešić et al (2017) show that performing normalization, in addition to using external resources, can remove half of the errors of a standard POS tagger for South Slavic languages. Quite surprisingly, instead, of all systems participating in shared tasks on POS tagging of Twitter data for both Italian (Bosco et al, 2016) and German (Beißwenger et al, 2016), none of the participating systems incorporated any normalization strategy before performing POS tagging.…”

Section: Related Workmentioning

confidence: 99%

Proceedings of the 3rd Workshop on Noisy User-generated Text

Derczynski¹,

Xu²,

Ritter³

et al. 2017

View full text Add to dashboard Cite

ii Introduction The W-NUT 2017 workshop focuses on a core set of natural language processing tasks on top of noisy user-generated text, such as that found on social media, web forums and online reviews. Recent years have seen a significant increase of interest in these areas. The internet has democratized content creation leading to an explosion of informal user-generated text, publicly available in electronic format, motivating the need for NLP on noisy text to enable new data analytics applications. The workshop is an opportunity to bring together researchers interested in noisy text with different backgrounds and encourage crossover. The workshop this year features a shared task on Emerging and Rare entity recognition.The workshop received 27 main track submissions, 17 of which were accepted, in addition to 6 system description papers for the shared task and a task overview paper. There are 3 invited speakers, Bill Dolan, Dirk Hovy and Miles Osborne with each of their talks covering a different aspect of NLP for user-generated text. We would like to thank the Program Committee members who reviewed the papers this year. We would also like to thank the workshop participants. AbstractThis work presents a fine-grained, textchunking algorithm designed for the task of multiword expressions (MWEs) segmentation. As a lexical class, MWEs include a wide variety of idioms, whose automatic identification are a necessity for the handling of colloquial language. This algorithm's core novelty is its use of non-word tokens, i.e., boundaries, in a bottom-up strategy. Leveraging boundaries refines token-level information, forging highlevel performance from relatively basic data. The generality of this model's feature space allows for its application across languages and domains. Experiments spanning 19 different languages exhibit a broadly-applicable, stateof-the-art model. Evaluation against recent shared-task data places text partitioning as the overall, best performing MWE segmentation algorithm, covering all MWE classes and multiple English domains (including usergenerated text). This performance, coupled with a non-combinatorial, fast-running design, produces an ideal combination for implementations at scale, which are facilitated through the release of open-source software.

show abstract

“…The trial corpus contains around 3,600 tokens (2,100 CMC 8 , 1,500 Web) and was PoS tagged by one annotator (without systematic error checks). See Beißwenger et al (2016) for more details.…”

Section: German Wikipedia (W2v)mentioning

confidence: 99%

bot.zen $@$ EmpiriST 2015 - A minimally-deep learning PoS-tagger (trained for German CMC and Web data)

Stemle¹

2016

Proceedings of the 10th Web as Corpus Workshop

View full text Add to dashboard Cite

This article describes the system that participated in the Part-of-speech tagging subtask of the EmpiriST 2015 shared task on automatic linguistic annotation of computer-mediated communication / social media.The system combines a small assertion of trending techniques, which implement matured methods, from NLP and ML to achieve competitive results on PoS tagging of German CMC and Web corpus data; in particular, the system uses word embeddings and character-level representations of word beginnings and endings in a LSTM RNN architecture. Labelled data (Tiger v2.2 and EmpiriST) and unlabelled data (German Wikipedia) were used for training.The system is available under the APLv2 open-source license.

show abstract

EmpiriST 2015: A Shared Task on the Automatic Linguistic Annotation of Computer-Mediated Communication and Web Corpora

Cited by 15 publications

References 24 publications

Fine-Grained POS Tagging of German Social Media and Web Texts

Fine-Grained POS Tagging of German Social Media and Web Texts

Proceedings of the 3rd Workshop on Noisy User-generated Text

bot.zen $@$ EmpiriST 2015 - A minimally-deep learning PoS-tagger (trained for German CMC and Web data)

Contact Info

Product

Resources

About