- Corpora - ELRA lists

Call For Papers - InqBnB4
by valentin.richard＠loria.fr 13 Feb '23

13 Feb '23

Greetings, InqBnB4 workshop: Inquisitiveness Below and Beyond the Sentence Boundary Nancy (France), 20 June 2023, hosted by IWCS 2023 https://iwcs2023.loria.fr/inqbnb4-inquisitiveness-below-and-beyond-the-sent… InqBnB is a workshop series bringing together researchers interested in the semantics and pragmatics of interrogatives (questions or embedded interrogative clauses). This series was originally organized by the Inquisitive Semantics Group of the Institute for Logic, Language and Computation (ILLC) from the University of Amsterdam. As such, the focus point mainly revolves around analyses using or related to inquisitive semantics. After three successful editions in the Netherlands, we hope to open the inquisitive community to a wider audience. The 4th edition is planned on 20 June 2023, just before IWCS 2023 (Internation Conference on Computational Semantics). As invited speakers we are welcoming Wataru Uegaki (University of Edinburgh) and one other to be announced. InqBnB4 invites submissions on original and unpublished research focussed on the properties of inquisitive content. We are mainly interested in theoretical questions, formal models and empirical work. But we are also welcoming papers based on statistical or neural models, provided their main goal is to bring new insights regarding inquisitiveness. Here are some examples of questions of interest: * Which operators (connectives, quantifiers, modals, conditionals) generate inquisitiveness? * How do these operators project the inquisitive content of their arguments? * e.g. what triggers maximality, exhaustivity or uniqueness of readings? * How does inquisitive content interact with informative content in compositional semantics? * e.g. how do interrogative words interact with negative polarity items, free choice items, indefinites or plurality? * How do conventions of use interact with inquisitive content? * e.g. how can non-answering responses (e.g. clarification questions) be handled? * In which ways is pragmatics sensitive to inquisitive content? * e.g. how does answer bias and ignorance inferences arise? * What kind of discourse anaphora are licensed by inquisitive expressions? * e.g. does dynamic inquisitive semantics manage to correctly derive donkey anaphora? *Submission:* Submission link on SoftConf: https://softconf.com/iwcs2023/inqbnb4/ Sumitted papers must not exceed eight (8) pages (not counting acknowledgement, references and appendices). Accepted papers get an extra page in the camera-ready version. Submitted papers should be formatted following the common two-column structure as used by ACL. Please use the specific style-files or the Overleaf template for IWCS 2023, taken from ACL 2021. Initial submissions should be fully anonymous to ensure double-blind reviewing. The proceedings will be published in the ACL anthology. *Important dates:* * Submission deadline: 14 April * Author notification: 12 May * Camera ready: 9 June * Workshop day: 20 June *Organizers:* * Valentin D. Richard [1], Loria, Universit�� de Lorraine * Philippe de Groote [2], Loria, INRIA Nancy �� Grand Est * Floris Roelofsen [3], ILLC, Universiteit van Amsterdam *Programme committee:* * Local chair: Valentin D. Richard, Universit�� de Lorraine * Chair: Floris Roelofsen, Universiteit van Amsterdam * Lucas Champollion [4], New York University (NYU) * Jonathan Ginzburg [5], Universit�� Paris Cit�� * Philippe de Groote [2], INRIA Nancy �� Grand Est * Jakub Dotla��il [6], Universiteit Utrecht * Reinhard Muskens [7], Universiteit van Amsterdam * Maribel Romero [8], Universit��t Konstanz * Wataru Uegaki [9], University of Edinburgh * Yimei Xiang [10], Rutgers Linguistics [1] https://valentin-d-richard.fr/ [2] https://members.loria.fr/PdeGroote/ [3] https://www.florisroelofsen.com/ [4] https://champollion.com/ [5] http://www.llf.cnrs.fr/fr/Gens/Ginzburg [6] http://www.jakubdotlacil.com/ [7] http://freevariable.nl/ [8] https://ling.sprachwiss.uni-konstanz.de/pages/home/romero/ [9] https://www.wataruuegaki.com/ [10] https://yimeixiang.wordpress.com/

1 0

[PoliticIT@EVALITA2023] Call for participation EVALITA 2023 Task - PoliticIT: Political ideology detection in Italian texts
by Salud María Jiménez Zafra 13 Feb '23

13 Feb '23

CALL FOR PARTICIPATION EVALITA 2023 Task - PoliticIT: Political ideology detection in Italian texts Held as part of EVALITA 2023 <https://www.evalita.it/campaigns/evalita-2023/>, a periodic evaluation campaign of Natural Language Processing and speech tools for the Italian language September 7th-8th 2023, Parma Codalab link: https://codalab.lisn.upsaclay.fr/competitions/8507 Dear All, We are inviting researchers and students to participate in the shared-task PoliticIT: Political ideology detection in Italian texts held as part of EVALITA 2023, the evaluation campaign of Natural Language Processing and speech tools for the Italian language. The goal of this task is to extract political ideology information from Italian texts. For this, an automatic document classification task on clusters of texts is proposed. It consists of extracting the self-assigned gender as demographic trait, and the political ideology as a psychographic trait from a set of texts written in Italian from several authors that share those traits. Political ideology is considered as a binary and as a multiclass problem. The PoliticIT shared task is based on a previous task named PoliticES presented at IberLEF 2022 (García-Díaz et. al. 2022b) where the dataset was an extension of the PoliCorpus 2020 dataset (García-Díaz et al., 2022a). The participants will be provided development, development_test, training and test datasets in Italian. The corpus was collected between 2020 and 2022 from the Twitter accounts of politicians in Italy using the UMUCorpusClassifier (García-Díaz et al., 2020). We created clusters of texts mixing some of these extracted tweets in order to prevent ethical and privacy issues about author profiling in Twitter. Consequently, all the clusters are composed of texts written by different users that share all the traits under evaluation. We labelled each cluster with his or her self-assigned gender (male, female) and political spectrum on two axes: binary (left, right) and multiclass (left, moderate_left, moderate_right, right). Moreover, the Twitter mentions of the politicians were anonymised by replacing them with the token @user. In addition, other Twitter accounts mentions were also encoded as @user. Consequently, the text traits cannot be guessed trivially by reading politician's names and searching information on them on the Internet. The dataset is composed of different clusters with around 80-100 tweets. Moreover, in order to facilitate participation in the competition, a Google Colab notebook will be provided. In this notebook, it is shown how to load the development dataset and how to train 3 baselines models based on logistic regression with a simple Bag-of-Words (BoW) model for each trait (self_assigned_gender, ideology_binary and ideology_multiclass). In addition, it is shown how to calculate the final F1-score of each model and how to generate the final submission file. To download the data, the notebook and participate, go to https://codalab.lisn.upsaclay.fr/competitions/8507. Best regards, The PoliticIT 2023 organizing committee References - García-Díaz, J. A., Almela, Á., Alcaraz-Mármol, G., & Valencia-García, R. (2020). UMUCorpusClassifier: Compilation and evaluation of linguistic corpus for Natural Language Processing tasks. Procesamiento del Lenguaje Natural, 65, 139-142. - García-Díaz, J. A., Colomo-Palacios, R., & Valencia-García, R. (2022a). Psychographic traits identification based on political ideology: An author analysis study on Spanish politicians’ tweets posted in 2020. Future Generation Computer Systems, 130(1), 59-74. - García-Díaz, J. A., Jiménez Zafra, S. M., Martín Valdivia, M. T., García-Sánchez, F., Ureña López, L. A., & Valencia García, R. (2022b). Overview of PoliticEs 2022: Spanish Author Profiling for Political Ideology. Procesamiento del Lenguaje Natural, 69, 265-272. Important dates - Release of development corpora: Jan 31, 2023 - Release of training corpora: Feb 7, 2023 - Release of test corpora and start of evaluation campaign: May 2, 2023 - End of evaluation campaign (deadline for runs submission): May 19, 2023 - Publication of official results: May 30, 2023 - Paper submission: Jun 14, 2023 - Review notification: Jul 10, 2023 - Camera ready submission: Jul 25, 2023 - EVALITA Workshop: Parma, Sep 7th-8th, 2023 - Publication of proceedings: Sep ??, 2023 Organizing committee - Daniel Russo (Language and Dialogue Technologies group at Fondazione Bruno Kessler (FBK), UniTn) - Salud María Jiménez-Zafra (SINAI research group, Universidad de Jaén, Spain) - José Antonio García-Díaz (UMUTeam research group, Universidad de Murcia, Spain) - Tommaso Caselli (Faculty of Arts, Rijksuniveristeit Groningen) - Marco Guerini (Language and Dialogue Technologies group at Fondazione Bruno Kessler (FBK), UniTn) - L. Alfonso Ureña-López (SINAI research group, Universidad de Jaén, Spain) - Rafael Valencia-García (UMUTeam research group, Universidad de Murcia, Spain) [image: Universidad de Jaén] <http://www.uja.es/> *Salud María Jiménez Zafra* sjzafra(a)ujaen.es Universidad de Jaén Grupo de Investigación SINAI <http://sinai.ujaen.es/> | Departamento de Informática EPS Jaén, Edificio A3, Despacho 219 Campus Las Lagunillas s/n 23071 - Jaén | +34 953212992 [image: Universidad de Jaén] <http://www.uja.es/>

1 0

Shared Task on Speaker Attribution in German News Articles and Parliamentary Debates
by Fynn Petersen-Frey 13 Feb '23

13 Feb '23

*SpkAtt-2023: Shared Task on Speaker Attribution in German News Articles and Parliamentary Debates* We are happy to announce a newshared task on Speaker Attribution in German, as part of the GermEval Campaign, co-located with the Conference for Natural Language Processing (KONVENS 2023) in Ingolstadt, Germany, in Sep 2023. The goal of this shared task is the identification of speakers in political debates and in news articles, and the attribution of speech events to their respective speakers. Being able to identify this information automatically, i.e., identifying who says what to whom, is a necessary prerequisite for a deep semantic analysis of unstructured text. For more information about the shared task, including the task settings, datasets, evaluation metrics and link to the registration form, please visit the shared task website on CodaLab (https://codalab.lisn.upsaclay.fr/competitions/10431) Important dates: + April 1, 2023 - Training and development data release + June 15, 2023 - Test data release (blind) + July 1, 2023 - Submissions open + July 31, 2023 - Submissions close + August 14, 2023 - System descriptions due + September 7, 2023 - Camera-ready system paper deadline + September 18-22, 2023 - Workshop at KONVENS 2023 Organising Team:Ines Rehbein, Simone Ponzetto (U-Mannheim) Fynn Petersen-Frey, Chris Biemann (U-Hamburg) Josef Ruppenhofer, Annelen Brunner (IDS Mannheim) Contacts: fynn.petersen-frey(a)uni-hamburg.de, rehbein(a)uni-mannheim.de -- Fynn Petersen-Frey Universität Hamburg Language Technology Group (LT) House of Computing and Data Science (HCDS)

1 0

Call for Papers: SemDial 2023 - MariLogue
by Andy Lücking 13 Feb '23

13 Feb '23

* Apologies for cross-posting * Call for papers: SemDial 2023 Submissions date: June 16th, 2023 Submissions website: https://easychair.org/conferences/?conf=semdial2023marilogue # CALL FOR PAPERS SemDial 2023 -- MariLogue The 27th Workshop on the Semantics and Pragmatics of Dialogue 16--17 August, University of Maribor, Slovenia https://mezzanine.um.si/en/conference/semdial-2023-marilogue/ MariLogue will be the 27th edition of the SemDial workshop series, which aims to bring together researchers working on the semantics and pragmatics of dialogue in fields such as formal semantics and pragmatics, computational linguistics, artificial intelligence, philosophy, psychology, and neuroscience. We welcome submissions with formal, computational and empirical approaches to the semantics and pragmatics of dialogue, including, but not limited to: * the dynamics of agents' information states in dialogue * common ground/mutual belief * goals, intentions and commitments in communication * turn-taking and interaction control * semantic/pragmatic interpretation in dialogue * dialogue and discourse structure * categorisation of dialogue phenomena in corpora * child-adult interaction * language learning through dialogue * gesture, gaze, and intonational meaning in communication * multimodal dialogue * interpretation and reasoning in spoken dialogue systems * dialogue management * designing and evaluating dialogue systems * modelling miscommunication, disfluency and repair * dialogue/interaction studies from a psychological perspective * neuroscience of dialogue * Interactivist approaches to dialogue * animal communication # SUBMISSION INSTRUCTIONS: Long papers: Authors should submit an anonymous paper of at most 8 pages of content (up to 2 additional pages are allowed for references). Short papers: Authors should submit a non-anonymized paper of at most 2 pages of content (up to 1 additional page allowed for references). Submission to this track can be non-archival on request. Submissions should be pdf files and use the LaTeX (https://2023.aclweb.org/downloads/acl2023.zip) or Word (https://2023.aclweb.org/downloads/acl2023.docx) templates provided for ACL 2023 submissions. The LaTeX template is readily available on Overleaf (https://www.overleaf.com/latex/templates/acl-2023-proceedings-template/qjdg…). Concurrent submission policy: Papers that have been or will be submitted to other meetings or publications must provide this information, using a footnote on the title page of the submissions. SemDial 2023 cannot accept work for publication or presentation that will be (or has been) published elsewhere. Submission is electronic, using the EasyChair conference management system at our Easychair submission site (https://easychair.org/conferences/?conf=semdial2023marilogue). # IMPORTANT DATES: Note: All deadlines are 11:59PM UTC-12:00 ("anywhere on Earth"). * Long paper submissions due: June 16th, 2023 * Notification: July 14th, 2023 * Short paper submissions due: July 21st, 2023 * Final versions due: August 4th, 2023 * Registration Deadline for presenters/refund deadline: August 4th, 2023 * MariLogue Conference: August 16th--17th, 2023

1 0

PhD student position: Neuro-symolic synthesis of communication schemes
by Moa Johansson 13 Feb '23

13 Feb '23

PhD student position in Neuro-Symbolic Synthesis and Reinforcement Learning In this project we study a new approach to synthesis of efficient communication schemes in multi-agent systems, trained via reinforcement learning. We combine symbolic methods with machine learning, in what is referred to as a neuro-symbolic system, where a neural network learns to produce programs in a symbolic language to solve a task at hand. We believe this combination of neural and symbolic methods will be an important next step in the development of AI beyond todays capabilities. This project is a collaboration between researchers at the division of Data Science and AI<https://www.chalmers.se/en/departments/cse/research/dsai/Pages/default.aspx> at Chalmers and the Center for Linguistic Theory and Studies in Probability (CLASP) at Gothenburg University. Deadline for applications: 28 February: https://www.chalmers.se/en/about-chalmers/work-with-us/vacancies/

1 0

PhD scholarship in clinical NLP at the University of Melbourne
by Mike Conway 13 Feb '23

13 Feb '23

BRIEF DESCRIPTION The University of Melbourne's Department of General Practice, in collaboration with the University of Melbourne’s School of Computing and Information Systems invite applications for a 3.5 year funded PhD scholarship focused on the development and validation of NLP algorithms for the automatic extraction of adolescent risk-taking behaviours (e.g. substance use, risky sexual behaviours) and health conditions (e.g. depression, anxiety) from clinical notes. SELECTION CRITERIA Eligibility will be assessed on the following criteria: * Applicants must be an outstanding applicant with an Australian first class undergraduate degree (or international equivalent), or masters degree in Computer Science or a related discipline * Applicants must demonstrate strong Python skills * Applicants must have some experience with Natural Language Processing methods * Applicants must demonstrate an interest in medical and health research with a focus on data analysis skills * Applicants must demonstrate an openness to learn new things, versatility, creativity, problem solving skills, and attention to detail * Applications must demonstrate effective verbal and written English language communication skills It is also desirable, but not necessary, that applicants have experience working with data derived from electronic health records. FURTHER DETAILS AND HOW TO APPLY For more information regarding this opportunity, see: https://www.statsoc.org.au/forum-job-vacancies/13086448 To apply for this position, please email PCTU-enquiries(a)unimelb.edu.au<mailto:PCTU-enquiries@unimelb.edu.au> with a cover letter addressing the selection criteria, a CV, and academic transcripts SCHOLARSHIP VALUE & DURATION The scholarship consists of living allowance of AU$33,000 per year (2023, indexed annually) for up to a maximum of 3.5 years. Additional "top-up" funding may be available

1 0

Call for Papers & Participation: The ClinicalNLP 2023 Workshop & Shared Tasks at ACL 2023
by Kirk Roberts 13 Feb '23

13 Feb '23

Clinical text is growing rapidly as electronic health records become pervasive. Much of the information recorded in a clinical encounter is located exclusively in provider narrative notes, which makes them indispensable for supplementing structured clinical data in order to better understand patient state and care provided. The methods and tools developed for the clinical domain have historically lagged behind the scientific advances in the general-domain NLP. Despite the substantial recent strides in clinical NLP, a substantial gap remains. The goal of this workshop is to address this gap by establishing a regular event in CL conferences that brings together researchers interested in developing state-of-the-art methods for the clinical domain. The focus is on improving NLP technology to enable clinical applications, and specifically, information extraction and modeling of narrative provider notes from electronic health records, patient encounter transcripts, and other clinical narratives. Relevant topics for the workshop include, but are not limited to: - Modeling clinical text in standard NLP tasks (tagging, chunking, parsing, entity identification, entity linking/normalization, relation extraction, coreference, summarization, etc.) - De-identification and other handling of protected health information - Structure of clinical documents (e.g., section identification) - Information extraction from clinical text - Integration of structured and textual data for clinical tasks - Domain adaptation and transfer learning techniques for clinical data - Generation of clinical notes: summarization, image-to-text, generation of notes from clinical conversations, etc. - Annotation schemes and annotation methodology for clinical data - Evaluation techniques for the clinical domain - Bias and fairness in clinical text In 2023, Clinical NLP will encourage submissions from the following special tracks: - Clinical NLP in languages other than English - Clinical NLP in low-resource settings - Clinical NLP for clinical conversations (e.g., doctor-patient) The 5th Clinical NLP Workshop will be co-located with ACL 2023 <https://2023.aclweb.org/> in Toronto, Canada - July 13 or 14, 2023. Joint Track with MWE Clinical NLP 2023 is also co-organizing a special track with the 19th Workshop on Multiword Expressions (MWE 2023) <https://multiword.org/mwe2023/>. The goal is to foster future synergies that could address scientific challenges in the creation of resources, models and applications to deal with multiword expressions and related phenomena in the specialised domain of Clinical NLP. Submissions describing research on multi-word expressions in the specialized domain of Clinical NLP, especially introducing new datasets or new tools and resources, are welcome. Note that submissions to this track must be submitted to MWE, not Clinical NLP by their earlier submission deadline, 20 Feb 2023. Please visit the MWE 2023 website <https://multiword.org/mwe2023/> for more details. Submissions accepted to this “Multi-word expressions in Clinical NLP” special track will have the opportunity to present their work first at MWE 2023 at EACL and then also at Clinical NLP 2023 at ACL. Shared Task Clinical NLP 2023 is hosting the MEDIQA-Chat Shared Tasks <https://sites.google.com/view/mediqa2023/clinicalnlp-mediqa-chat-2023> on doctor-patient conversations, which focuses on the following tasks: 1. Dialogue2Note Summarization: Given a conversation between a doctor and patient, participants are tasked with producing a clinical note summarizing the conversation with one or multiple note sections (e.g. Assessment, Past Medical History, Past Surgical History). 2. Note2Dialogue Generation: Given a clinical note, participants are tasked with generating a synthetic doctor-patient conversation related to the information described in the clinical note section(s). Please visit the shared task website <https://sites.google.com/view/mediqa2023/clinicalnlp-mediqa-chat-2023> to register to participate and for additional information about the shared tasks. Submissions Submissions may have a maximum length of eight (8) pages for long papers and four (4) pages for short papers and shared task participant papers, with unlimited pages for references and appendices. All submissions must be made through OpenReview <https://openreview.net/> and follow ACL formatting guidelines <https://acl-org.github.io/ACLPUB/formatting.html>. The OpenReview submission site can be found here: OpenReview-ClinicalNLP <https://openreview.net/group?id=aclweb.org/ACL/2023/Workshop/Clinical_NLP> We encourage submissions of papers submitted to but not accepted by EACL 2023 <https://2023.eacl.org/>, ACL 2023 <https://2023.aclweb.org/>, or ACL Rolling Review <https://aclrollingreview.org/>, as long as the topics are relevant to Clinical NLP. Important Dates All deadlines are 11:59PM UTC-12:00 (anywhere on Earth <https://www.timeanddate.com/time/zones/aoe>) EventDate Shared task registration opens Tuesday, January 10, 2023 Shared task release of training and validation sets Friday, February 10, 2023 Shared task release of the test sets Wednesday, March 15, 2023 Shared task run submission deadline Friday, March 17, 2023 Shared task release of official results Friday, March 31, 2023 Submission deadline (both general and shared task) Tuesday, May 2, 2023 Notification of acceptance Monday, May 22, 2023 Final versions of papers due Tuesday, June 6, 2023 Pre-recorded video due Monday, June 12, 2023 Workshop Thursday or Friday, July 13 or 14, 2023Workshop Organizers - Anna Rumshisky (UMass Lowell) - Asma Ben Abacha (Microsoft) - Kirk Roberts (University of Texas Health Science Center at Houston) - Steven Bethard (University of Arizona) - Tristan Naumann (Microsoft Research) For inquiries, please contact: clinical-nlp-workshop-organizers(a)googlegroups.com.

1 0

PhD position in NLP for climate change at CIS/LMU
by Barbara Plank 12 Feb '23

12 Feb '23

There is an opening for a funded PhD position at CIS LMU Munich to work on NLP for climate change within the KLIMA-MEMES project at the MaiNLP lab, with ample opportunities for collaboration. The deadline is today, the position remains open until filled. Interested? Check out the details and apply as soon as possible: https://mainlp.github.io/jobs/

1 0

Fwd: Fwd: Deadline extension: 19th Workshop on Multiword Expressions (MWE 2023)
by Kilian Evang 11 Feb '23

11 Feb '23

Forwarded message from Archna below ---------- Forwarded message --------- Von: Archna Bhatia <abhatia(a)ihmc.org> Date: Sa., 11. Feb. 2023 um 01:57 Uhr Subject: Re: [Corpora-List] Fwd: Deadline extension: 19th Workshop on Multiword Expressions (MWE 2023) To: Ada Wan <adawan919(a)gmail.com> Cc: Kilian Evang <kilian.evang(a)gmail.com>, corpora(a)list.elra.info < corpora(a)list.elra.info> Thanks, Ada. My point was not that the term “multiword expressions” predates the term “idioms/idiomatic expressions” but that the category of items, of which idioms is a subset, has been referred to as multiwords for a long time. It may not be the perfect terminology but there’s some shared understanding what kinds of expressions or constructions constitute this category labeled as multiwords/multiword expressions/multiword units. I would like to see strong evidence of better suitability of a new term to refer to this category before I adopt it. BTW, I’m curious do you have examples in mind which belong to this category but show that wordhood might be a problematic notion? How frequent is this phenomenon? Also regarding emojis etc, I’m curious: are there combinations of emojis that show some sort of idiosyncrasy when they cooccur? Or even combinations of emojis and textual words or other utterances which show such idiosyncratic behavior as we generally associate with “MWEs”? (It’s possible but I had not thought of it until now and it would be interesting to see that.) BTW, are you planning on attending the MWE 2023 workshop? There would be a lot of opportunity to discuss this with researchers currently working on multiword expressions. Thanks, Archna On Feb 11, 2023, at 4:02 AM, Ada Wan <adawan919(a)gmail.com> wrote: Hi Archna "Idioms"/"Idiomatic expressions" are established terms in the study of language [1], with a longer history than MWE [2]. "Fixed", e.g. in "fixed phrases", is mentioned in, inter alia, [3], which was the earliest cite from the earliest work on MWEs in the ACL Anthology [4]. If I understand correctly, "MWEs" was a term so coined in order to establish a practice based on "words" (if anyone should view this differently, please do correct me here). You're right, the task I suggested can be seen as orthogonal to distinguishing between lexical expressions or non-lexical expressions. I think it's important to document also the contexts surrounding expressions, instead of just picking expressions out and studying them in an isolated manner. It was just a suggestion for those who might be interested in building a multilingual parallel lexical database as well as those who might want to get a more holistic understanding of language while weaning oneself of "words" --- now that it's become even more obvious how superfluous the term/concept is. [1] See e.g. https://en.wikipedia.org/wiki/Phraseme <https://nam02.safelinks.protection.outlook.com/?url=https%3A%2F%2Fen.wikipe…> [2] "Idiomatic expression" is just another formulation of "idiom" (see https://www.thefreedictionary.com/idiomatic+expression <https://nam02.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.thefr…>). According to Collins English Dictionary (accessed via https://www.thefreedictionary.com/idiom <https://nam02.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.thefr…>), "idiom" stems from the 16th century Latin idiōma, denoting "pecularity of language". [3] Nunberg, Geoffrey, Ivan A. Sag, and Thomas Wasow. 1994. Idioms. Language, 70:491–538. https://doi.org/10.2307/416483 <https://nam02.safelinks.protection.outlook.com/?url=https%3A%2F%2Fdoi.org%2…> (Many older references on "idioms" by linguists can be found therein.) [4] Ann Copestake, Fabre Lambeau, Aline Villavicencio, Francis Bond, Timothy Baldwin, Ivan A. Sag, and Dan Flickinger. 2002. Multiword expressions: linguistic precision and reusability. In Proceedings of the Third International Conference on Language Resources and Evaluation (LREC’02), Las Palmas, Canary Islands - Spain. European Language Resources Association (ELRA). ------------------------------ Hi Kilian Sorry about my oversight on "item". I do think "item" could be better than "term" in this case, but it does carry a sense of "a single element", a more discrete "singleton". It's ok to combine it with "complex" to mitigate the sense of "singleton", but then "complex" as you suggested is dependent on morphology, which can be problematic. Re "lexical": sure. (I think there have been so many different views/traditions/conventions among linguists and computational linguists in the past, we don't necessarily have to agree on how we or our definitions/methods might differ or might have differed, as long as we have the same goal now?) One argument for "expressions" would be that they could include a sign (e.g. hand sign in motion). So how about updating "MWEs" to: i. "lexical expressions", or ii. "lexical expressions (of one character or more when written)*", or iii. [i] or [ii] without "lexical", or iv. others? * I'm trying to incorporate how expressions with emojis would/should be treated too. ------------------------------ What do you all think? Thanks and best Ada On Fri, Feb 10, 2023 at 10:58 AM Kilian Evang via Corpora < corpora(a)list.elra.info> wrote: > Forwarded message from Archna below > > ---------- Forwarded message --------- > Von: Archna Bhatia <abhatia(a)ihmc.org> > Date: Do., 9. Feb. 2023 um 19:58 Uhr > Subject: Re: [Corpora-List] Deadline extension: 19th Workshop on Multiword > Expressions (MWE 2023) > To: Ada Wan <adawan919(a)gmail.com>, kilian Evang <kilian.evang(a)gmail.com> > Cc: Mike Scott <mike(a)lexically.net>, mweworkshop2023(a)googlegroups.com < > mweworkshop2023(a)googlegroups.com>, corpora(a)list.elra.info < > corpora(a)list.elra.info> > > > Thanks, Ada. I think using the terms “fixed” and “idiomatic” make the > category appear more restrictive, and would need qualifications such as > “fixed” is a relative term here, etc. With “multiwords/multiword > expressions” also, there are stipulations (the notion of wordhood may not > be applicable to every single language and in the same way) but since the > term has been used for a long while, there is a bit of a shared > understanding of this term, including about these stipulations. I am open > to better terminology. Using just “expressions”, however, seems too vague > and loses some generalizations about the idiosyncrasies that "multiword > expressions” demonstrate. Every expression in not the same, “multiword > expressions” show characteristics different from other expressions. I > understand there is some fluidity also there when trying to distinguish > between multiwords and non multiword expressions. > > There are so many angles that one could look at language from. I don’t see > anything wrong with the view that studies expressions covering all aspects > as you suggest without distinguishing between expressions based on notions > of wordhood. The task you suggest will help in developing understanding > about language and how languages are similar or different and how they are > used. I don’t think it disqualifies efforts that distinguish between > “multiword expressions” and non-multiword expressions though, and the > idiosyncrasies are not limited to morphology/syntax, idiosyncrasies are > found in other linguistic aspects too when characterizing "multiword > expressions”. > > ~ Archna > > On Feb 9, 2023, at 11:17 AM, Ada Wan <adawan919(a)gmail.com> wrote: > > Hi Archna, hi Kilian, hi all > > Thanks for your replies. > > TLDR on my part: I'd be fine going with "expressions" (instead of > "fixed/idiomatic expressions"). Neither "word" nor "morphology/syntax" > (apart from the ordering of elements and/or sequential patterns) is > necessary in the analyses of such. > > ----- > > More specifically: > > [@Archna] Re "fixed/idiomatic expressions": I don't think it matters much > whether they are "fixed" or "idiomatic". A "fixed expression" is one that > is usually more impervious to (lexical) change. One can measure this > quality in a longitudinal study, e.g. in relation to other aspects of > language change etc.. Re how "fixed" is "fixed": it's relative, much like > many other aspects of language studies. By "idiomatic", one could mean that > there is an element of idiosyncrasy (as "idiom"/"idioma"). > > The message that I am trying to get across is that "word" is a superflous > category in the study of language. Would you mind please justifying why you > need "words"? > > The same goes for morphology, actually. In essence, morphological analyses > involve selective decomposition, not decomposition of all decomposable > units. Hence if one is only accounting for variations within an expression > as a ((sub-)character) sequence involving "morphemes" (assuming definable > rigorously) and discounting the changes in other parts of the sequence, > that would be an incomplete analysis of the expression. Instead, one can > just refer to expressions as "expressions", as e.g. sequences/strings of > various lengths/vocabs in (sub-)characters --- such an account is also more > flexible and accommodating to diverse languages/registers/modalities. > > A study of "expressions" can cover all other aspects --- not just lexical > but also functional ones. One doesn't need to incorporate/impose any ad hoc > notions of "wordhood" in these studies. > > Suggestion: I believe there are many more interesting tasks in this area, > instead of trying to find/define "words" within expressions, or to "parse" > them according to some structuralist assumptions (i.e. > morphologically/syntactically). For example, the community could start > (some multi-year project) building an international multilingual parallel > (note: not everything would be parallelizable) database of all expressions > and terminologies ever existed with contextual (historical/cultural/social) > information and start verifying their sources and status of current use. > (Just be aware, though, that one is not reinforcing values that shouldn't > be further emphasized / transfered to posterity --- as an ethical > consideration. So if something is in the grey area now, document clearly > what the current attitudes towards a certain value are, so posterity can > look back and evaluate with respect to their point of view.) > > Counter questions to Archna: > What are the motivations behind your suggestion to access/interpret > language using "words"? How do you define "words" and justify the > sufficiency/necessity of morphology/syntax in relation to the study of > these expressions, esp. when the morphological decomposition of these > expressions is arbitrary and helps little (or not at all) with explanation > or prediction? > > Re "complex lexical terms", @Kilian: I'm just wondering what kind of terms > that would be considered "terms" that wouldn't be considered lexical (I was > tempted to add "lexical" to "expressions" as well, but thought that might > be a bit redundant)? It depends on how one defines "terms", of course. And > how "complex" are expressions really? They are just more calcified units > after all, aren't they? (Why do we/some always seem to want to add the term > "complex" to everything? Things that aren't "complex" are also worthy of > studying!) > > Curious what you think... > > Thanks and best > Ada > > Why I'm advocating #noWords: > Fairness in Representation for Multilingual NLP: Insights from Controlled > Experiments on Conditional Language Modeling > https://openreview.net/forum?id=-llS6TiOew > > <https://nam02.safelinks.protection.outlook.com/?url=https%3A%2F%2Fopenrevie…> > https://drive.google.com/file/d/1eKbhdZkPJ0HgU1RsGXGFBPGameWIVdt9/view > > <https://nam02.safelinks.protection.outlook.com/?url=https%3A%2F%2Fdrive.goo…> > (It took me a while for everything to sink in.) > > > On Thu, Feb 9, 2023 at 3:27 PM Mike Scott via Corpora < > corpora(a)list.elra.info> wrote: > >> I must say I'm perfectly happy with "multi-word expression", or >> "multi-word unit". >> >> I feel sympathy with Archna's post (and incidentally wish Archna didn't >> have to go through a friend!) >> Cheers -- Mike >> >> -- >> >> Mike Scottlexically.net <https://nam02.safelinks.protection.outlook.com/?url=http%3A%2F%2Flexically.…> >> Lexical Analysis Software and Aston University >> >> _______________________________________________ >> Corpora mailing list -- corpora(a)list.elra.info >> https://list.elra.info/mailman3/postorius/lists/corpora.list.elra.info/ >> <https://nam02.safelinks.protection.outlook.com/?url=https%3A%2F%2Flist.elra…> >> To unsubscribe send an email to corpora-leave(a)list.elra.info >> > > -- > You received this message because you are subscribed to the Google Groups > "MWE Workshop 2023 Organizers" group. > To unsubscribe from this group and stop receiving emails from it, send an > email to mweworkshop2023+unsubscribe(a)googlegroups.com. > To view this discussion on the web visit > https://groups.google.com/d/msgid/mweworkshop2023/CAB7Mis_GSyFjZOVw_XWp431V… > <https://nam02.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgroups.go…> > . > For more options, visit https://groups.google.com/d/optout > <https://nam02.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgroups.go…> > . > > > > > > > -- > Archna Bhatia, Ph.D. > Research Scientist, Institute for Human & Machine Cognition > 15 SE Osceola Ave, Ocala, FL 34471 > (352) 387-3061 > > _______________________________________________ > Corpora mailing list -- corpora(a)list.elra.info > https://list.elra.info/mailman3/postorius/lists/corpora.list.elra.info/ > <https://nam02.safelinks.protection.outlook.com/?url=https%3A%2F%2Flist.elra…> > To unsubscribe send an email to corpora-leave(a)list.elra.info >

1 0

PhD Student position: Limitations of Large Language Models (LLMs)
by steffen.eger＠uni-bielefeld.de 11 Feb '23

11 Feb '23

The Natural Language Learning Group (NLLG) at Bielefeld University, Germany, is looking for a PhD student in NLP for understanding limitations of large language models (such as BERT, ChatGPT, etc.) in social/political science contexts. The position is jointly supervised by the NLLG group and the Semantic Computing Group at Bielefeld. More information and application details are here: https://nl2g.github.io/positions The application deadline is 23.02.2023. For any questions, please contact steffen.eger(a)uni-bielefeld.de

1 0

2024

2023

2022