Call for Papers
Submission deadline: 15/7/2015 extended to 30/7/2015
The second edition of the Italian Computational Linguistics Conference is located in Trento on December 3-4 2015 and follows the first successful edition, held in Pisa in December 2014. The conference will also be the first meeting of the newly established Association for Italian Computational Linguistics.
CLiC-it aims at becoming a reference forum for discussion about Computational Linguistics research in the Italian community. Therefore CLiC-it covers all aspects of automatic language understanding, both written and spoken, and targets state-of-art theoretical results, experimental methodologies, technologies, as well as application perspectives, which may contribute to the advancement of the field.
CLiC-it is an inclusive conference as the complexity of language phenomena needs cross-disciplinary competences. Thus, CLiC-it intends to bring together researchers of related disciplines such as Computational Linguistics, Linguistics, Cognitive Science, Machine Learning, Computer Science, Knowledge Representation, Information Retrieval and Digital Humanities. CLiC-it is open to contributions on all languages, with a particular emphasis on Italian.
CLiC-it 2015 Co-Chairs
- Cristina Bosco (Università di Torino)
- Sara Tonelli (Fondazione Bruno Kessler, Trento)
- Fabio Massimo Zanzotto (Università di Roma Tor Vergata)
CALL FOR PAPERS
CLIC-It invites submissions of papers on research in all aspects of automated Natural Language Processing. Relevant topics for the conference include, but are not limited to, the following areas:
Information Extraction and Information Retrieval
Topics: information extraction; relation extraction; natural language interfaces; question answering and interactive IR; information retrieval and seeking; document representation; indexing and content analysis; text and document classification; document summarization; queries and query analysis; query completion; IR architectures; retrieval models and ranking; distributional semantics and semantic similarity for IE &IR; entity search; semantic search; aspect-based Information retrieval; opinion mining and sentiment analysis; textual entailment for IE &IR; evaluation of IE & IR systems; semantic web applications; machine learning for IE&IR; statistical methods & deep learning.
Topics: corpora (written, spoken, mixed, domain specific, mutilingual); computational lexica (methods, domain specific adaptation, coverage, typology, multilingual, wordnets); annotation schemes (creation, adaptation, annotation specifications); standard for language resources (best practices, standardization initiatives, annotation guidelines , metadata); innovative methods for the acquisition, creation and annotation of language resources (crowdsourcing, gamification, collaborative approaches); evaluation and validation methods; interoperability and re-usability (merging, derivation/construction of language resources, including multingual approaches).
Topics: empirical studies on translation data; advances in various machine translation (MT) paradigms: data-driven, rule-based, and hybrids; approaches to MT and computer assisted translation (CAT) tools (integration, interactive and adaptive MT, MT quality estimation, automatic post-editing, etc.); language resources for MT and CAT tools (parallel and comparable corpora, dictionaries, grammars, translation memories, terminological databases, etc.); machine learning for MT (online learning, Deep Learning, etc.); crowd-sourcing methods for MT; MT evaluation techniques and evaluation results; text and speech translation; use of NLP technologies in MT (paraphrasing, cross-language information retrieval, information extraction, etc.)
Morphology, Syntax and Parsing
Topics: morphological analysis; part-of-speech tagging; syntactic analysis and parsing; dependency-based syntactic analysis versus constituency-based syntactic analysis; linguistic ambiguity and syntactic complexity; systems for the analysis of Italian; methodologies for evaluation of parsing systems; partial/shallow/skeleton parsing, chunking; syntactic analysis of domain languages (biomedicine texts, law texts, technical documentation, etc) and non canonical varieties of the language (blogs, microblogs, bad format text etc.).
NLP for Digital Humanities
Topics: text readability; language complexity; annotation and NLP for historical and literary texts; NLP and digital libraries; attribution studies; topic modelling; sentiment analysis and text mining in humanities; named entity recognition for historical and literary texts; OCR in ancient texts.
NLP for Web and Social Media
Area chair: Francesca Chiusaroli (Università di Macerata), Daniele Pighin (Google Inc.).
Topics: world modeling and language understanding; content filtering and relevance, identity and reputation; social network analysis, sentiment and opinion; linguistic analysis of noisy web data; construction and analysis of web corpora; word selection for ranking in web search; linguistic peculiarities of social network language: syntax, morphology, vocabulary and semantics, symbols and punctuation; reading levels and readability; language detection, multilingualism and automatic translation; accessibility and cross-mediality.
Pragmatics and Creativity
Topics: anaphora; metaphor; discourse; emotions; linguistic creativity; figurative language.
Semantics and Knowledge Acquisition
Topics: word sense disambiguation; semantic role labeling; entity recognition; ontology alignment & entity linking; textual entailment; ontology learning & population; distributional semantics; lexical linked data; lexical ontologies; ontology - lexicon interfaces; semantic annotation.
Spoken language processing
Topics: automatic translation of spoken language (automatic translation, cross-linguistic applications); spoken language processing (detection and synthesis of spoken language, spoken language understanding, dialogue systems, technologies and systems for new ASR and TTS applications).
CALL FOR PAPER TRACK: Towards EVALITA 2016: challenges, methodologies and tasks
Although the EVALITA workshop will not take place in 2015 (next edition will be after CliC-it 2016, http://www.evalita.it), the conference aims also at keeping alive the discussion about the evaluation of tools for Italian NLP and speech technologies. Therefore, together with the call for papers, we present a call for the Track “Towards EVALITA 2016: challenges, methodologies and tasks” mainly devoted to creating a forum for discussion on existing and new evaluation methodologies. The track will include also, but will not be limited to, the proposal of possible tasks and the description of experiences in industrial contexts. This new track can be therefore seen as a bridge between EVALITA 2014 and EVALITA 2016. This will prepare the ground for the new edition of the campaign, taking into account the hints from the previous edition and widening the involvement of the community by fostering the cooperation among researchers interested in the organization and participation to the EVALITA.
Towards EVALITA 2016: challenges, methodologies and tasks
Topics: development, extension and discussion of evaluation methodologies and metrics; classical NLP tasks (e.g. parsing, Named Entity Recognition, temporal information processing) and speech technology tasks (e.g. speaker identity recognition, speech forced alignment) also inspired by previous Evalita editions and other international evaluation campaigns; tasks combining NLP and speech technologies (e.g. Named Entity Recognition or Sentiment Analysis on speech transcriptions); tasks based on non-computational evaluation methods (e.g. prosodic evaluation and comparison, qualitative evaluation of automatic summarization systems).
- 30/7/2015: Deadline for paper submission
- 15/7/2015: Deadline for paper submission
- 21/9/2015: Notification to authors and proponents
- 15/9/2015: Notification to authors and proponents
- 15/10/2015: Camera ready version of the accepted papers and proposals
- 3-4/12/2015: CLiC-it Conference