Publikationer för datorlingvistik

  • Humanistiska teatern, Thunbergsvägen 3H, Uppsala 2019-03-09 kl 10:15

    Tang, Marc

    A typology of classifiers and gender: From description to computation

    Open access
  • Dahllöf, Mats

    Clustering writing components from medieval manuscripts

    Ingår i Proceedings of the Workshop on Computational Methods in the Humanities 2018, s. 23-32, 2019.

    Open access
  • Marie, Dubremetz; Nivre, Joakim

    Rhetorical Figure Detection: Chiasmus, Epanaphora, Epiphora

    Ingår i Frontiers in Digital Humanities, 2018.

  • Dahllöf, Mats

    Automatic Scribe Attribution for Medieval Manuscripts

    Ingår i Digital Medievalist, s. 1-26, 2018.

    Open access
  • Smith, Aaron; Bohnet, Bernd; de Lhoneux, Miryam; Nivre, Joakim et al.

    82 Treebanks, 34 Models: Universal Dependency Parsing with Multi-Treebank Models

    Ingår i Proceedings of the CoNLL 2018 Shared Task, s. 113-123, 2018.

  • Smith, Aaron; de Lhoneux, Miryam; Stymne, Sara; Nivre, Joakim et al.

    An Investigation of the Interactions Between Pre-Trained Word Embeddings, Character Models and POS Tags in Dependency Parsing

    Ingår i Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, s. 2711-2720, 2018.

  • Nivre, Joakim; Marongiu, Paola; Ginter, Filip; Kanerva, Jenna et al.

    Enhancing Universal Dependency Treebanks: A Case Study

    Ingår i Proceedings of the Second Workshop on Universal Dependencies (UDW 2018), s. 102-107, 2018.

  • Schuster, Sebastian; Nivre, Joakim; Manning, Christopher D.

    Sentences with Gapping: Parsing and Reconstructing Elided Predicates

    Ingår i Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics, s. 1156-1168, 2018.

  • Bouma, Gosse; Hajič, Jan; Haug, Dag; Nivre, Joakim et al.

    Expletives in Universal Dependency Treebanks

    Ingår i Proceedings of the Second Workshop on Universal Dependencies (UDW 2018), s. 18-26, 2018.

  • Tang, Gongbo; Müller, Mathias; Rios, Annette; Sennrich, Rico et al.

    Why Self-Attention? A Targeted Evaluation of Neural Machine Translation Architectures

    Ingår i Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, s. 4263-4272, 2018.

  • Tang, Gongbo; Cap, Fabienne; Pettersson, Eva; Nivre, Joakim et al.

    An evaluation of neural machine translation models on historical spelling normalization

    Ingår i Proceedings of the 27th International Conference on Computational Linguistics, s. 1320-1331, 2018.

  • Tang, Gongbo; Sennrich, Rico; Nivre, Joakim

    An analysis of Attention Mechanism: The Case of Word Sense Disambiguation in Neural Machine Translation

    Ingår i Proceedings of the Third Conference on Machine Translation, s. 26-35, 2018.

  • Megyesi, Beáta; Granstedt, Lena; Johansson, Sofia; Prentice, Julia et al.

    Learner Corpus Anonymization in the Age of GDPR: Insights from the Creation of a Learner Corpus of Swedish

    Ingår i Proceedings of the 7th NLP4CALL, 2018.

    Open access
  • Her, One-Soon; Tang, Marc

    A Statistical Explanation of the Distribution of Sortal Classifiers in Languages of the World via Computational Classifiers

    Ingår i Journal of Quantitative Linguistics, 2018.

    Open access
  • Søgaard, Anders; de Lhoneux, Miryam; Augenstein, Isabelle

    Nightmare at test time: How punctuation prevents parsers from generalizing

    Ingår i Proceedings of the 2018 EMNLP Workshop BlackboxNLP, s. 25-29, 2018.

    Open access
  • de Lhoneux, Miryam; Bjerva, Johannes; Augenstein, Isabelle; Søgaard, Anders et al.

    Parameter sharing between dependency parsers for related languages

    Ingår i Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, s. 4992-4997, 2018.

    Open access
  • Dahllöf, Mats

    Clustering Writing Components from Medieval Manuscripts

    Ingår i COMHUM 2018: Book of Abstracts for the Workshop on Computational Methods in the Humanities 2018, s. 11-13, 2018.

    Open access
  • Stymne, Sara; de Lhoneux, Miryam; Smith, Aaron; Nivre, Joakim et al.

    Parser Training with Heterogeneous Treebanks

    Ingår i Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), s. 619-625, 2018.

    Open access
  • Megyesi, Beáta

    Proceedings of the 1st International Conference on Historical Cryptology: HistoCrypt 2018

    2018.

    Open access
  • Room 22-0008, Humanistiska teatern, 752 38, Uppsala 2018-09-08 kl 09:00

    Basirat, Ali

    Principal Word Vectors

    Open access
  • Shao, Yan; Hardmeier, Christian; Nivre, Joakim

    Universal Word Segmentation: Implementation and Interpretation

    Ingår i Transactions of the Association for Computational Linguistics, s. 421-435, 2018.

    Open access
  • Pettersson, Eva; Megyesi, Beata

    The HistCorp Collection of Historical Corpora and Resources

    Ingår i DHN 2018, s. 306-320, 2018.

    Open access
  • Humanistiska teatern, Thunbergsvägen 3, Uppsala 2018-06-09 kl 10:15

    Shao, Yan

    Segmenting and Tagging Text with Neural Networks

    Open access
  • Virk, Shafqat Mumtaz; Borin, Lars; Saxena, Anju; Hammarström, Harald et al.

    Automatic extraction of typological linguistic features from descriptive grammars

    Ingår i Text, Speech, and Dialogue, s. 111-119, 2017.

  • Hammarström, Harald; Virk, Shafqat Mumtaz; Forsberg, Markus

    Poor Man’s OCR Post-Correction: Unsupervised Recognition of Variant Spelling Applied to a Multilingual Document Collection

    Ingår i Proceedings of the Digital Access to Textual Cultural Heritage (DATeCH) conference, s. 71-75, 2017.

  • Shao, Yan; Hardmeier, Christian; Tiedemann, Jörg; Nivre, Joakim et al.

    Character-based Joint Segmentation and POS Tagging for Chinese using Bidirectional RNN-CRF

    Ingår i Proceedings of the The 8th International Joint Conference on Natural Language Processing, s. 173-183, 2017.

    Open access
  • Shao, Yan; Hardmeier, Christian; Nivre, Joakim

    Recall is the Proper Evaluation Metric for Word Segmentation

    Ingår i Proceedings of the The 8th International Joint Conference on Natural Language Processing, s. 86-90, 2017.

    Open access
  • de Lhoneux, Miryam; Yan, Shao; Basirat, Ali; Kiperwasser, Eliyahu et al.

    From raw text to Universal Dependencies: look, no tags!

    Ingår i Proceedings of the CoNLL 2017 Shared Task, s. 207-217, 2017.

    Open access
  • Shao, Yan

    Cross-lingual Word Segmentation and Morpheme Segmentation as Sequence Labelling

    Ingår i Proceedings of MLP 2017, s. 75-80, 2017.

    Open access
  • Parks, Magdalena; Karlgren, Jussi; Stymne, Sara

    Plausibility Testing for Lexical Resources

    Ingår i Proceedings of CLEF 2017, s. 132-137, 2017.

  • Adams, Allison; Stymne, Sara

    Learning with learner corpora: Using the TLE for native language identification

    Ingår i Proceedings of the joint workshop on NLP for Computer Assisted Language Learning and NLP for Language Acquisition, s. 1-7, 2017.

    Open access
  • Stymne, Sara

    The Effect of Translationese on Tuning for Statistical Machine Translation

    Ingår i Proceedings of the 21st Nordic Conference on Computational Linguistics, s. 241-246, 2017.

    Open access
  • Loáiciga, Sharid; Stymne, Sara; Nakov, Preslav; Hardmeier, Christian et al.

    Findings of the 2017 DiscoMT Shared Task on Cross-lingual Pronoun Prediction

    Ingår i Proceedings of the Third Workshop on Discourse in Machine Translation, 2017.

    Open access
  • Stymne, Sara; Loàiciga, Sharid; Cap, Fabienne

    A BiLSTM-based System for Cross-lingual Pronoun Prediction

    2017.

  • Padilla López, Rebeca; Cap, Fabienne

    Did you ever read about Frogs drinking Coffee?: Investigating the Compositionality of Multi-Emoji Expressions

    Ingår i Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, s. 113-117, 2017.

    Open access
  • Savary, Agata; Ramisch, Carlos; Cordeiro, Silvio Ricardo; Sangati, Federico et al.

    The PARSEME Shared Task on Automatic Identification of Verbal Multiword Expressions

    Ingår i Proceedings of the 13th Workshop on Multiword Expressions (MWE 2017), s. 31-47, 2017.

    Open access
  • Cap, Fabienne

    Show me your variance and I tell you who you are: Deriving compound compositionality from word alignments

    Ingår i Proceedings of the 13th Workshop on Multiword Expressions, s. 102-107, 2017.

    Open access
  • Cap, Fabienne

    Approximating Compound Compositionality based on Word Alignments

    2017.

  • Stymne, Sara; Pettersson, Eva; Megyesi, Beáta; Palmér, Anne et al.

    Annotating Errors in Student Texts: First Experiences and Experiments

    Ingår i Proceedings of Joint 6th NLP4CALL and 2nd NLP4LA Nodalida workshop, s. 47-60, 2017.

    Open access
  • Näsman, Jesper; Megyesi, Beáta; Palmér, Anne

    SWEGRAM: A Web-Based Tool for Automatic Annotation and Analysis of Swedish Texts

    Ingår i Proceedings of the 21st Nordic Conference on Computational Linguistics, Nodalida 2017., s. 132-141, 2017.

    Open access
  • Fornes, Alicia; Megyesi, Beáta; Mas, Joan

    Transcription of Encoded Manuscripts with Image Processing Techniques

    Ingår i Proceedings of Digital Humanities 2017., 2017.

    Open access
  • Basirat, Ali; Tang, Marc

    Neural network and human cognition: A case study of grammatical gender in Swedish

    Ingår i Proceedings of the 13th Swedish Cognitive Science Society (SweCog) national conference, s. 28-30, 2017.

    Open access
  • Zeman, Daniel; Popel, Martin; Straka, Milan; Hajic, Jan et al.

    CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies

    Ingår i Proceedings of the CoNLL 2017 Shared Task, s. 1-19, 2017.

  • Ide, Nancy; Calzolari, Nicoletta; Eckle-Kohler, Judith; Gibbon, Dafydd et al.

    Community Standards for Linguistically-Annotated Resources

    Ingår i Handbook of Linguistic Annotation, s. 113-165, 2017.

  • Nivre, Joakim; Fang, Chiao-Ting

    Universal Dependency Evaluation

    Ingår i Proceedings of the NoDaLiDa 2017 Workshop on Universal Dependencies (UDW 2017), s. 86-95, 2017.

  • Basirat, Ali; Nivre, Joakim

    Real-valued Syntactic Word Vectors (RSV) for Greedy Neural Dependency Parsing

    s. 21-28 2017.

    Open access
  • Humanistiska teatern, Thunbergsvägen 3H, Uppsala 2018-01-20 kl 10:15

    Dubremetz, Marie

    Detecting Rhetorical Figures Based on Repetition of Words: Chiasmus, Epanaphora, Epiphora

    Open access
  • Marie, Dubremetz; Joakim, Nivre

    Machine Learning for Rhetorical Figure Detection: More Chiasmus with Less Annotation

    Ingår i Proceedings of the 21st Nordic Conference of Computational Linguistics, s. 37-45, 2017.

  • de Lhoneux, Miryam; Stymne, Sara; Nivre, Joakim

    Arc-Hybrid Non-Projective Dependency Parsing with a Static-Dynamic Oracle

    Ingår i IWPT 2017 15th International Conference on Parsing Technologies, s. 99-104, 2017.

    Open access
  • Shao, Yan; Nivre, Joakim

    Applying Neural Networks to English-Chinese Named Entity Transliteration

    Ingår i Proceedings of the Sixth Named Entity Workshop, joint with 54th ACL, 2016.

    Open access
  • Cap, Fabienne; Adesam, Yvonne; Ahrenberg, Lars; Borin, Lars et al.

    SWORD: Towards Cutting-Edge Swedish Word Processing

    2016.

  • Borin, Lars; Tahmasebi, Nina; Volodina, Elena; Ekman, Stefan et al.

    Swe-Clarin: Language Resources and Technology for Digital Humanities

    Ingår i Extended Papers of the International Symposium on Digital Humanities, s. 29-51, 2016.

    Open access
  • Volodina, Elena; Megyesi, Beáta; Wirén, Mats; Granstedt, Lena et al.

    A Friend in Need?: Research agenda for electronic Second Language infrastructure

    Ingår i Proceedings of SLTC 2016, 2016.

    Open access
  • Cap, Fabienne; Stymne, Sara

    Using Word Alignments to Determine the Compositionality of Swedish Compound Nouns

    2016.

  • Constant, Matthieu; Nivre, Joakim

    A Transition-Based System for Joint Lexical and Syntactic Analysis

    Ingår i Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, s. 161-171, 2016.

  • Shao, Yan; Hardmeier, Christian; Nivre, Joakim

    Multilingual Named Entity Recognition using Hybrid Neural Networks

    2016.

    Open access
  • Guillou, Liane; Hardmeier, Christian; Nakov, Preslav; Stymne, Sara et al.

    Findings of the 2016 WMT Shared Taskon Cross-lingual Pronoun Prediction

    Ingår i Proceedings of the First Conference on Machine Translation, s. 525-542, 2016.

    Open access
  • Tiedemann, Jörg; Cap, Fabienne; Kanerva, Jenna; Ginter, Filip et al.

    Phrase-Based SMT for Finnish with More Data, Better Models and Alternative Alignment and Translation Tools

    Ingår i Proceedings of the First Conference on Machine Translation, s. 391-398, 2016.

    Open access
  • Sagemo, Oscar; Stymne, Sara

    The UU Submission to the Machine Translation Quality Estimation Task

    Ingår i Proceedings of the First Conference on Machine Translation, s. 825-830, 2016.

    Open access
  • Stymne, Sara

    Feature Exploration for Cross-Lingual Pronoun Prediction

    Ingår i Proceedings of the First Conference on Machine Translation, s. 609-615, 2016.

    Open access
  • Stymne, Sara

    The Effect of Translationese on SMT Tuning

    2016.

    Open access
  • Marie, Dubremetz; Joakim, Nivre

    Syntax Matters for Rhetorical Structure: The Case of Chiasmus

    Ingår i Proceedings of the Fifth Workshop on Computational Linguistics for Literature, s. 47-53, 2016.

  • Nivre, Joakim; de Marneffe, Marie-Catherine; Ginter, Filip; Goldberg, Yoav et al.

    Universal Dependencies v1: A Multilingual Treebank Collection

    Ingår i Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016), 2016.

  • Dobrovoljc, Kaja; Nivre, Joakim

    The Universal Dependencies Treebank of Spoken Slovenian

    Ingår i Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016), 2016.

  • Seraji, Mojgan; Ginter, Filip; Nivre, Joakim

    Universal Dependencies for Persian

    Ingår i Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016), 2016.

  • Basirat, Ali; Faili, Heshaam; Nivre, Joakim

    A statistical model for grammar mapping

    Ingår i Natural Language Engineering, s. 215-255, 2016.

  • Smith, Aaron; Hardmeier, Christian; Tiedemann, Jorg

    Climbing Mount BLEU: The Strange World of Reachable High-BLEU Translations

    Ingår i Baltic Journal of Modern Computing, s. 269-281, 2016.

  • Hardmeier, Christian; Guillou, Liane

    A Graphical Pronoun Analysis Tool for the PROTEST Pronoun Evaluation Test Suite

    Ingår i Baltic Journal of Modern Computing, s. 318-330, 2016.

  • Megyesi, Beata; Näsman, Jesper; Palmér, Anne

    The Uppsala Corpus of Student Writings: Corpus Creation, Annotation, and Analysis

    Ingår i Language Resources and Evaluation, 2016.

  • Ballesteros, Miguel; Nivre, Joakim

    MaltOptimizer: Fast and Effective Parser Optimization

    Ingår i Natural Language Engineering, s. 187-213, 2016.

  • Shao, Yan; Tiedemann, Jörg; Nivre, Joakim

    Boosting English-Chinese Machine Transliteration via High Quality Alignment and Multilingual Resources

    Ingår i Proceedings of the Fifth Named Entity Workshop, s. 56-60, 2015.

  • Pettersson, Eva; Megyesi, Beata; Nivre, Joakim

    Ranking Relevant Verb Phrases Extracted from Historical Text

    Ingår i Proceedings of the 9th SIGHUM Workshop on Language Technology for Cultural Heritage, Social Sciences, and Humanities, 2015.

  • Megyesi, Beata

    Proceedings of the 20th Nordic Conference of Computational Linguistics

    2015.

  • Webber, Bonnie; Carpuat, Marine; Popescu-Belis, Andrei; Hardmeier, Christian et al.

    Proceedings of the Second Workshop on Discourse in Machine Translation

    2015.

  • Hardmeier, Christian; Nakov, Preslav; Stymne, Sara; Tiedemann, Jörg et al.

    Pronoun-Focused MT and Cross-Lingual Pronoun Prediction: Findings of the 2015 DiscoMT Shared Task on Pronoun Translation

    Ingår i Proceedings of the Second Workshop on Discourse in Machine Translation (DiscoMT), s. 1-16, 2015.

    Open access
  • Callin, Jimmy; Hardmeier, Christian; Tiedemann, Jörg

    Part-of-Speech Driven Cross-Lingual Pronoun Prediction with Feed-Forward Neural Networks

    Ingår i Proceedings of the Second Workshop on Discourse in Machine Translation (DiscoMT), s. 59-64, 2015.

    Open access
  • Hardmeier, Christian

    On Statistical Machine Translation and Translation Theory

    Ingår i Proceedings of the Second Workshop on Discourse in Machine Translation (DiscoMT), s. 168-172, 2015.

    Open access
  • Hardmeier, Christian

    A Document-Level SMT System with Integrated Pronoun Prediction

    Ingår i Proceedings of the Second Workshop on Discourse in Machine Translation (DiscoMT), s. 72-77, 2015.

    Open access
  • Universitetshuset / IX, Uppsala 2015-05-27 kl 10:15

    Seraji, Mojgan

    Morphosyntactic Corpora and Tools for Persian

    Open access
  • Xiong, Deyi; Duh, Kevin; Hardmeier, Christian; Navigli, Roberto et al.

    Proceedings of the 1st Workshop on Semantics-Driven Statistical Machine Translation (S2MT 2015)

    2015.

    Open access
  • Beck, Daniel; Cohn, Trevor; Hardmeier, Christian; Specia, Lucia et al.

    Learning Structural Kernels for Natural Language Processing

    Ingår i Transactions of the Association for Computational Linguistics, s. 461-473, 2015.

    Open access
  • Kavathatzopoulos, Iordanis; Björk, Ingrid

    How ethical robots process information, communicate and act

    Ingår i 1st TRANSOR Workshop, 2015.

  • Nivre, Joakim

    Om datorer och språkförståelse

    Ingår i Ņrsbok 2015, s. 75-82, 2015.

  • Pettersson, Eva; Nivre, Joakim

    Improving Verb Phrase Extraction from Historical Text by Use of Verb Valency Frames

    Ingår i Proceedings of the 20th Nordic Conference of Computational Linguistics, s. 153-161, 2015.

  • Marie, Dubremetz; Joakim, Nivre

    Rhetorical Figure Detection: the Case of Chiasmus

    Ingår i Proceedings of the Fourth Workshop on Computational Linguistics for Literature, s. 23-31, 2015.

  • Seraji, Mojgan; Bernd, Bohnet; Nivre, Joakim

    ParsPer: A Dependency Parser for Persian

    Ingår i Depling 2015, s. 300-309, 2015.

    Open access
  • Farahmand, Meghdad; Smith, Aaron; Nivre, Joakim

    A Multiword Expression Data Set: Annotating Non-Compositionality and Conventionalization for English Noun Compounds

    Ingår i Proceedings of the 11th Workshop on Multiword Expressions, s. 29-33, 2015.

  • Björkelund, Anders; Nivre, Joakim

    Non-Deterministic Oracles for Unrestricted Non-Projective Transition-Based Dependency Parsing

    Ingår i Proceedings of the 14th International Conference on Parsing Technologies, s. 76-86, 2015.

  • Farahmand, Meghdad; Nivre, Joakim

    Modeling the Statistical Idiosyncrasy of Multiword Expressions

    Ingår i Proceedings of the 11th Workshop on Multiword Expressions, s. 34-38, 2015.

  • Pettersson, Eva; Megyesi, Beata; Nivre, Joakim

    A Multilingual Evaluation of Three Spelling Normalization Methods for Historical Text.

    Ingår i Workshop on Language Technology for Cultural Heritage, Social Sciences and Humanities, LaTeCH 2014, 2014.

  • Tengstrand, Lisa; Megyesi, Beata; Henriksson, Aron; Duneld, Martin et al.

    EACL - Expansion of Abbreviations in CLinical text

    Ingår i Workshop on Predicting and Improving Text Readability for Target Reader Populations, PITR 2014, 2014.

  • Tan, Liling; Zampieri, Marcos; Ljubesic, Nikola; Tiedemann, Jorg et al.

    Merging Comparable Data Sources for the Discrimination of Similar Languages: The DSL Corpus Collection

    Ingår i LREC 2014 - Ninth International Conference On Language Resources And Evaluation, 2014.

  • Hardmeier, Christian; Tiedemann, Jörg; Nivre, Joakim

    Translating Pronouns with Latent Anaphora Resolution

    2014.

    Open access
  • Hardmeier, Christian

    A Dependency Projection Model for Phrase-Based SMT

    2014.

    Open access
  • Dahllöf, Mats

    Scribe attribution for early medieval handwriting by means of letter extraction and classification and a voting procedure for larger pieces

    Ingår i 22nd International Conference on Pattern Recognition (ICPR), s. 1910-1915, 2014.

    Open access
  • Dahllöf, Mats

    Predicting the Scribe Behind a Page of Medieval Handwriting

    2014.

    Open access
  • Skadinš, Raivis; Tiedemann, Jörg; Rozis, Roberts; Deksne, Daiga et al.

    Billions of Parallel Words for Free: Building and Using the EU Bookshop Corpus

    Ingår i Proceedings of the 9th International Conference on Language Resources and Evaluation (LREC-2014), s. 1850-1855, 2014.

  • Agić, Zeljko; Tiedemann, Jörg; Merkler, Danijela; Krek, Simon et al.

    Cross-lingual Dependency Parsing of Related Languages with Rich Morphosyntactic Tagsets

    Ingår i Proceedings of the EMNLP’2014 Workshop on Language Technology for Closely Related Languages and Language Variants, s. 13-24, 2014.

  • Martinez Garcia, Eva; Tiedemann, Jörg; España-Bonet, Cristina; Màrquez, Lluís et al.

    Word’s Vector Representations meet Machine Translation

    Ingår i Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation, s. 132-134, 2014.

  • Tiedemann, Jörg

    Rediscovering Annotation Projection for Cross-Lingual Parser Induction

    Ingår i Proceedings of COLING 2014, 2014.