---

Invited Speakers

• Tim Baldwin (The University of Melbourne)

  Title: Text Mining of Social Media: Going beyond the Text and Only the Text [slides]
  Abstract: As a field, NLP is inevitably fixated on the analysis of textual content, but this is all too often to the exclusion of context, whether textual or otherwise. Text mining over social media sources provides a myriad of opportunities to integrate text and context analysis, as I will explore in this talk.

• Brendan O'Connor (University of Massachusetts Amherst)

  Title: Are Minority Dialects "Noisy Text"?: Implications of Social and Linguistic Diversity for Social Media NLP [slides]
  Abstract: Social media, SMS, and other genres of online conversational text look different than newspapers or academic papers. They feature tremendous lexical diversity, alternate spellings, and grammatical constructs not seen in standard English. Is this “noisy” text? Do we see this because users are lazy? Because of different input affordances? Or different speech acts and performative contexts? I argue that a simple look at the data reveals a largely ignored source of linguistic diversity: the massive *sociodemographic* diversity of these texts’ authors, and the fact they use these forums to communicate in ways consistent with these markers of social identity.

• Anders Søgaard (University of Copenhagen)

  Title: Where is language?
  Abstract: In NLP, we typically want to show that system A is better than system B for some language L, but in practice, that’s never what we do. This talk questions whether the enterprise makes sense, but also proposes a more robust framework for evaluating NLP systems.

• Joel Tetreault (Yahoo! Labs)

  Title: Automated Grammatical Error Co rrection for Language Learners: Where are we, and where do we go from there?
  Abstract: A fast growing area in Natural Language Processing is the use of automated tools for identifying and correcting grammatical errors made by language learners. While there have been many exciting developments in GEC over the last few years, there is still considerable room for improvement as state-of-the-art performance in detecting and correcting several important error types is still inadequate for many real world applications. In this talk, I will provide an overview of the field of automated grammatical error correction, including its history, leading methodologies and its particular set of challenges.

Program

Friday, July 31, 2015
9:00–10:30	Invited Talks
9:00–9:45	Text Mining of Social Media: Going beyond the Text and Only the Text Tim Baldwin
9:45–10:30	Where is Language? Anders Søgaard
10:30–11:00	Coffee Break
11:00–12:30	Long Papers and Abstracts
11:00–11:15	Learning finite state word representations for unsupervised Twitter adaptation of POS taggers Julie Wulff and Anders Søgaard
11:15–11:30	Towards POS Tagging for Arabic Tweets Fahad Albogamy and Allan Ramasy
11:30–11:45	Minority Language Twitter: Part-of-Speech Tagging and Analysis of Irish Tweets Teresa Lynn, Kevin Scannell and Eimear Maguire
11:45–11:00	Challenges of studying and processing dialects in social media Anna Jørgensen, Dirk Hovy and Anders Søgaard
12:00–12:15	Toward Tweets Normalization Using Maximum Entropy Mohammad Arshi Saloot, Norisma Idris, Liyana Shuib, Ram Gopal Raj and AiTi Aw
12:15–12:30	Five Shades of Noise: Analyzing Machine Translation Errors in User-Generated Text Marlies van der Wees, Arianna Bisazza and Christof Monz
12:30–14:00	Poster Session and Lunch
	Learning finite state word representations for unsupervised Twitter adaptation of POS taggers Julie Wulff and Anders Søgaard
	Towards POS Tagging for Arabic Tweets Fahad Albogamy and Allan Ramasy
	Minority Language Twitter: Part-of-Speech Tagging and Analysis of Irish Tweets Teresa Lynn, Kevin Scannell and Eimear Maguire
	Challenges of studying and processing dialects in social media Anna Jørgensen, Dirk Hovy and Anders Søgaard
	Toward Tweets Normalization Using Maximum Entropy Mohammad Arshi Saloot, Norisma Idris, Liyana Shuib, Ram Gopal Raj and AiTi Aw
	Five Shades of Noise: Analyzing Machine Translation Errors in User-Generated Text Marlies van der Wees, Arianna Bisazza and Christof Monz
	A Normalizer for UGC in Brazilian Portuguese Magali Sanches Duran, Maria das Graças Volpe Nunes and Lucas Avanço
	USFD: Twitter NER with Drift Compensation and Linked Data Leon Derczynski, Isabelle Augenstein and Kalina Bontcheva
	Enhancing Named Entity Recognition in Twitter Messages Using Entity Linking Ikuya Yamada, Hideaki Takeda and Yoshiyasu Takefuji
	Improving Twitter Named Entity Recognition using Word Representations Zhiqiang Toh, Bin Chen and Jian Su
	NRC: Infused Phrase Vectors for Named Entity Recognition in Twitter Colin Cherry, Hongyu Guo and Chengbi Dai
	IITP: Multiobjective Differential Evolution based Twitter Named Entity Recognition Md Shad Akhtar, Utpal Kumar Sikdar and Asif Ekbal
	Multimedia Lab @ ACL WNUT NER Shared Task: Named Entity Recognition for Twitter Microposts using Distributed Word Representations Fréderic Godin, Baptist Vandersmissen, Wesley De Neve and Rik Van de Walle
	Data Adaptation for Named Entity Recognition on Tweets with Features-Rich CRF Tian Tian, Marco Dinarelli and Isabelle Tellier
	Hallym: Named Entity Recognition on Twitter with Word Representation Eun-Suk Yang and Yu-Seop Kim
	IHS_RD: Lexical Normalization for English Tweets Dmitry Supranovich and Viachaslau Patsepnia
	Bekli:A Simple Approach to Twitter Text Normalization. Russell Beckley
	NCSU-SAS-Ning: Candidate Generation and Feature Engineering for Supervised Lexical Normalization Ning Jin
	DCU-ADAPT: Learning Edit Operations for Microblog Normalisation with the Generalised Perceptron Joachim Wagner and Jennifer Foster
	LYSGROUP: Adapting a Spanish microtext normalization system to English. Yerai Doval Mosquera, Jesús Vilares and Carlos Gómez-Rodríguez
	IITP: Hybrid Approach for Text Normalization in Twitter Md Shad Akhtar, Utpal Kumar Sikdar and Asif Ekbal
	NCSU_SAS_WOOKHEE: A Deep Contextual Long-Short Term Memory Model for Text Normalization Wookhee Min and Bradford Mott
	NCSU_SAS_SAM: Deep Encoding and Reconstruction for Normalization of Noisy Text Samuel Leeman-Munk, James Lester, and James Cox
	USZEGED: Correction Type-sensitive Normalization of English Tweets Using Efficiently Indexed n-gram Statistics Gábor Berend and Ervin Tasnádi
14:00–15:30	Shared Task Session
14:00–14:30	Shared Tasks of the 2015 Workshop on Noisy User-generated Text: Twitter Lexical Normalization and Named Entity Recognition Timothy Baldwin, Marie-Catherine de Marneffe, Bo Han, Young-Bum Kim, Alan Ritter and Wei Xu
14:30–14:45	Enhancing Named Entity Recognition in Twitter Messages Using Entity Linking Ikuya Yamada, Hideaki Takeda and Yoshiyasu Takefuji
14:45–15:00	Improving Twitter Named Entity Recognition using Word Representations Zhiqiang Toh, Bin Chen and Jian Su
15:00–15:15	Multimedia Lab @ ACL WNUT NER Shared Task: Named Entity Recognition for Twitter Microposts using Distributed Word Representations Fréderic Godin, Baptist Vandersmissen, Wesley De Neve and Rik Van de Walle
15:15–15:30	NCSU_SAS_SAM: Deep Encoding and Reconstruction for Normalization of Noisy Text Samuel Leeman-Munk, James Lester and James Cox
15:30–16:00	Coffee Break
16:00–17:30	Invited Talks
16:00–16:45	Automated Grammatical Error Correction for Language Learners: Where are we, and where do we go from there? Joel Tetreault
16:45–17:30	Are Minority Dialects "Noisy Text"?: Implications of Social and Linguistic Diversity for Social Media NLP Brendan O’Connor

---

Important Dates

• January 11 2015: First call for workshop papers
• March 31-May 11 2015: Shared-task evaluations
• May 11, 2015: Workshop paper due
• June 8, 2015: Notification of acceptance
• June 21 2015: Camera-ready due
• July 31 2015: Workshop date
• January 2016: estimated time for announcement of WNUT 2016

check this website or follow the organizers @cocoweixu @alan_ritter @BrooklynHAN on Twitter for updates

---

Call for Papers

We seek submissions of long papers on original and unpublished work (up to 8 pages of content plus 2 extra pages for references). Abstracts (2-4 pages including references) on work-in-progress or work published elsewhere are also welcome and will *not* be included in the conference proceedings. All accepted submissions will be presented as posters. Additionally, a small number of selected submissions will be presented orally.

Topics of interest include but are not limited to:

• NLP Preprocessing of Noisy Text
• Part of speech tagging
• Named entity tagging, including a wide range of categories, e.g. product names
• Chunking of user-generated text
• Parsing
• Text Normalization and Error Correction
• Normalizing noisy text for downstream tasks and for human readability
• Error detection and correction
• Paraphrase extraction and detection in noisy text
• Bilingual translation of noisy text
• Multilingual NLP in noisy text
• Colloquial language, e.g. idiom detection
• Domain adaptation to user-generated text

All submissions should conform to ACL 2015 style guidelines. Long paper submissions must be anonymized. Abstract submissions should include author information (and where the work was published in a footnote on front page, if applicable). Please submit your papers at https://www.softconf.com/acl2015/WNUT/.

---

Shared task #1: Named Entity Recognition in Twitter

Task #1 Details: here
Register by clicking here
Evaluation Period: May 1 - May 8
Contacts: Marie-Catherine de Marneffe, Young-Bum Kim and Alan Ritter

---

Shared task #2: Normalization of Noisy Text

Task #2 Details: here
Register by clicking here
Evaluation Period: May 7- May 11
Contact: Bo Han, Tim Baldwin

---

Workshop Organizers

• Wei Xu (University of Pennsylvania)
• Bo Han (IBM Research)
• Alan Ritter (The Ohio State University)

Program Committee

• David Bamman (Carnegie Mellon University)
• Kalina Bontcheva (University of Sheffield)
• Claire Cardie (Cornell University)
• Colin Cherry (National Research Council Canada)
• Grzegorz Chrupała (Tilburg University)
• Leon Derczynski (University of Sheffield)
• Jacob Eisenstein (Georgia Institute of Technology)
• Jennifer Foster (Dublin City University)
• Eric Fosler-Lussier (The Ohio State University)
• Kevin Gimpel (Toyota Technological Institute at Chicago)
• Weiwei Guo (Columbia University)
• Dirk Hovy (University of Copenhagen)
• Jing Jiang (Singapore Management University)
• Emre Kiciman (Microsoft Research)
• Wang Ling (Carnegie Mellon University)
• Xiaohua Liu (University of Montreal)
• Preslav Nakov (Qatar Computing Research Institute)
• Miles Osborne (Bloomberg)
• Kristen Parton (Facebook)
• Ellie Pavlick (University of Pennsylvania)
• Daniel Preoţiuc-Pietro (University of Pennsylvania)
• Roi Reichart (Technion-IIT)
• Alla Rozovskaya (Columbia University)
• Nathan Schneider (University of Edinburgh)
• Djamé Seddah (University Paris-Sorbonne)
• Richard Sproat (Google)
• Maosong Sun (Tsinghua University)
• Joel Tetreault (Yahoo!)
• Oren Tsur (Harvard University)
• Benjamin Van Durme (Johns Hopkins University)
• Svitlana Volkova (Johns Hopkins University)
• Lu Wang (Cornell University)
• Jun-Ming Xu (University of Wisconsin-Madison)
• Xiaojin Zhu (University of Wisconsin-Madison)

---

Registration Awards

Thanks to the kind support of our sponsors, WNUT 2015 will provide several student registration grants ($150 each) to cover the registration fee and lunch for students to attend the workshop. Both undergraduate and graduate students are eligible to apply. Award receipts must attend the full-day WNUT workshop (9:00 - 17:30 July 31st, 2015) at China National Convention Center (CNCC) in Beijing. The application is due on July 26th. The workshop organization committee will review the applications and notify the winners by July 28th via email. Please email your application to xwe@cis.upenn.edu that includes the following documents :

- Copy of valid student ID
- Copy of proof of travel plan to Beijing, if the student is not currently enrolled in universities in Beijing.
- 500-word essay in the topic "Why do I deserve the registration grant?", including student's basic information (full name, email, which year in what program in which university and department).

ACL 2015 WNUT Workshop Student Registration Awards winners are:

• Fahad Albogamy (University of Manchester)
• Junwei Bao (Harbin Institute of Technology University)
• Danqing Huang (Sun Yat-Sen University)
• Marlies van der Wees (University of Amsterdam)

Sponsored by