Publikationer för datorlingvistik
-
LingFN: A Framenet for the Linguistic Domain
Ingår i Computational Linguistics and Intelligent Text Processing, s. 367-379, 2023.
-
Schrödinger's tree: On syntax and neural language models
Ingår i Frontiers in Artificial Intelligence, 2022.
DOI för Schrödinger's tree: On syntax and neural language models Ladda ner fulltext (pdf) av Schrödinger's tree: On syntax and neural language models
-
A Few Thousand Translations Go A Long Way! Leveraging Pre-trained Models for African News Translation
Ingår i NAACL 2022, s. 3053-3070, 2022.
-
To the Most Gracious Highness, from Your Humble Servant: Analysing Swedish 18th Century Petitions Using Text Classification
Ingår i Proceedings of the 6th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature, s. 53-64, 2022.
-
A Tale of Four Parsers: Methodological Reflections on Diagnostic Evaluation and In-Depth Error Analysis for Meaning Representation Parsing
Ingår i Language Resources and Evaluation, s. 1075-1102, 2022.
DOI för A Tale of Four Parsers: Methodological Reflections on Diagnostic Evaluation and In-Depth Error Analysis for Meaning Representation Parsing Ladda ner fulltext (pdf) av A Tale of Four Parsers: Methodological Reflections on Diagnostic Evaluation and In-Depth Error Analysis for Meaning Representation Parsing
-
Tha sound system of Kanashi
Ingår i Synchronic and diachronic aspects of Kanashi, s. 13-51, 2022.
-
A linguistic sketch of Kanashi
Ingår i Synchronic and diachronic aspects of Kanashi, s. 53-127, 2022.
-
Linguistic variation: A challenge for describing the phonology of Kanashi
Ingår i Synchronic and diachronic aspects of Kanashi, s. 131-144, 2022.
DOI för Linguistic variation: A challenge for describing the phonology of Kanashi
-
And then there was one: Kanashi numerals from borrowed superdiversity to borrowed uniformity
Ingår i Synchronic and diachronic aspects of Kanashi, s. 145-170, 2022.
DOI för And then there was one: Kanashi numerals from borrowed superdiversity to borrowed uniformity
-
Clues to Kanashi prehistory 1: Loanword adaptation in nouns and adjectives
Ingår i Synchronic and diachronic aspects of Kanashi, s. 173-213, 2022.
DOI för Clues to Kanashi prehistory 1: Loanword adaptation in nouns and adjectives
-
Clues to Kanashi prehistory 2: Loanword adaptation in verbs
Ingår i Synchronic and diachronic aspects of Kanashi, s. 215-233, 2022.
DOI för Clues to Kanashi prehistory 2: Loanword adaptation in verbs
-
Kanashi and West Himalayish: Genealogy, language contact, prehistoric migrations
Ingår i Synchronic and diachronic aspects of Kanashi, s. 237-254, 2022.
DOI för Kanashi and West Himalayish: Genealogy, language contact, prehistoric migrations
-
Introduction: Kanashi, its speakers, its linguistic and extralinguistic context
Ingår i Synchronic and diachronic aspects of Kanashi, s. 3-11, 2022.
DOI för Introduction: Kanashi, its speakers, its linguistic and extralinguistic context
-
The linguistic landscape of the Indian Himalayas
Brill Academic Publishers, 2022.
-
Cause and Effect in Governmental Reports: Two Data Sets for Causality Detection in Swedish
Ingår i Proceedings of the LREC 2022 Workshop on Natural Language Processing for Political Sciences, s. 46-55, 2022.
-
Fine-Grained Controllable Text Generation Using Non-Residual Prompting
Ingår i Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1 Long Papers), s. 6837-6857, 2022.
DOI för Fine-Grained Controllable Text Generation Using Non-Residual Prompting
-
Nucleus Composition in Transition-Based Dependency Parsing
Ingår i Computational Linguistics, s. 849-886, 2022.
-
Processing of Condition Monitoring Annotations with BERT and Technical Language Processing
Ingår i PHM Society European Conference, s. 306-314, 2022.
-
Exploring Cross-Lingual Transfer to Counteract Data Scarcity for Causality Detection
Ingår i WWW '22, s. 501-508, 2022.
DOI för Exploring Cross-Lingual Transfer to Counteract Data Scarcity for Causality Detection Ladda ner fulltext (pdf) av Exploring Cross-Lingual Transfer to Counteract Data Scarcity for Causality Detection
-
Overview of Touché 2022: Argument Retrieval
Ingår i Experimental IR Meets Multilinguality, Multimodality, and Interaction (CLEF 2022), s. 311-336, 2022.
-
The DECODE Database of Historical Ciphers and Keys: Version 2
Ingår i Proceedings of the 5th International Conference on Historical Cryptology. HistoCrypt 2022., s. 111-114, 2022.
DOI för The DECODE Database of Historical Ciphers and Keys: Version 2
-
Identifying Cleartext in Historical Ciphers
Ingår i Proceedings of the Workshop on Language Technologies for Historical and Ancient Languages. LT4HALA 2022., 2022.
-
Lost in Transcription of Graphic Signs in Ciphers
Ingår i Proceedings of the 5th International Conference on Historical Cryptology. HistoCrypt 2022, s. 153-158, 2022.
-
What Was Encoded in Historical Cipher Keys in the Early Modern Era?
Ingår i Proceedings of the 5th International Conference on Historical Cryptology. HistoCrypt 2022., 2022.
DOI för What Was Encoded in Historical Cipher Keys in the Early Modern Era?
-
Quotation and Narration in Contemporary Popular Fiction in Swedish – Stylometric Explorations
Ingår i Proceedings of the 6th Digital Humanities in the Nordic and Baltic Countries Conference (DHNB 2022), s. 203-211, 2022.
-
Zero-Shot Dependency Parsing with Worst-Case Aware Automated Curriculum Learning
Ingår i Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Acl 2022), s. 578-587, 2022.
DOI för Zero-Shot Dependency Parsing with Worst-Case Aware Automated Curriculum Learning
-
Word Order Does Matter (And Shuffled Language Models Know It)
Ingår i PROCEEDINGS OF THE 60TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2022), VOL 1, s. 6907-6919, 2022.
-
Challenges and Strategies in Cross-Cultural NLP
Ingår i PROCEEDINGS OF THE 60TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2022), VOL 1, s. 6997-7013, 2022.
-
SLäNDa Version 2.0: Improved and Extended Annotation of Narrative and Dialogue in Swedish Literature
Ingår i Proceedings of the 13th International Conference on Language Resources and Evaluation (LREC 2022), s. 5324-5333, 2022.
-
Uppsala University at SemEval-2022 Task 1: Can Foreign Entries Enhance an English Reverse Dictionary?
Ingår i Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), s. 88-93, 2022.
-
Cause and Effect in Governmental Reports: Two Data Sets for Causality Detection in Swedish
Ingår i Proceedings of the First Workshop on Natural Language Processing for Political Sciences (PoliticalNLP), s. 46-55, 2022.
-
Few shots are all you need: A progressive learning approach for low resource handwritten text recognition
Ingår i Pattern Recognition Letters, s. 43-49, 2022.
DOI för Few shots are all you need: A progressive learning approach for low resource handwritten text recognition Ladda ner fulltext (pdf) av Few shots are all you need: A progressive learning approach for low resource handwritten text recognition
-
Probing Pre-trained Language Models for Semantic Attributes and their Values
Ingår i Findings of the Association for Computational Linguistics: EMNLP 2021, Virtual Event / Punta Cana, Dominican Republic, 16-20 November, 2021, s. 2554-2559, 2021.
-
A bird’s-eye view on South Asian languages through LSI
Ingår i Journal of South Asian languages and linguistics, s. 203-237, 2021.
DOI för A bird’s-eye view on South Asian languages through LSI
-
Syntactic Nuclei in Dependency Parsing –: A Multilingual Exploration
Ingår i Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics, s. 1376-1387, 2021.
DOI för Syntactic Nuclei in Dependency Parsing –: A Multilingual Exploration Ladda ner fulltext (pdf) av Syntactic Nuclei in Dependency Parsing –: A Multilingual Exploration
-
Attention Can Reflect Syntactic Structure (If You Let It)
Ingår i Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics, s. 3031-3045, 2021.
DOI för Attention Can Reflect Syntactic Structure (If You Let It)
-
Audiobook stylistics: Comparing print and audio in the bestselling segment
Ingår i Journal of Cultural Analytics, s. 1-30, 2021.
DOI för Audiobook stylistics: Comparing print and audio in the bestselling segment Ladda ner fulltext (pdf) av Audiobook stylistics: Comparing print and audio in the bestselling segment
-
Have Attention Heads in BERT Learned Constituency Grammar?
Ingår i Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics, s. 8-15, 2021.
DOI för Have Attention Heads in BERT Learned Constituency Grammar? Ladda ner fulltext (pdf) av Have Attention Heads in BERT Learned Constituency Grammar?
-
Whit’s the Richt Pairt o Speech: PoS tagging for Scots
Ingår i Proceedings of the Eighth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial), s. 39-48, 2021.
Ladda ner fulltext (pdf) av Whit’s the Richt Pairt o Speech: PoS tagging for Scots
-
Investigation of Transfer Languages for Parsing Latin: Italic Branch vs. Hellenic Branch
Ingår i Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa), s. 315-320, 2021.
-
Survey and reproduction of computational approaches to dating of historical texts
Ingår i Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa), s. 145-156, 2021.
-
Uppsala NLP at SemEval-2021 Task 2: Multilingual Language Models for Fine-tuning and Feature Extraction in Word-in-Context Disambiguation
Ingår i Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021), s. 150-156, 2021.
-
Swedish FrameNet++ and comparative linguistics
Ingår i The Swedish FrameNet++, s. 139-166, 2021.
-
Universal Dependencies
Ingår i Computational Linguistics, s. 255-308, 2021.
DOI för Universal Dependencies Ladda ner fulltext (pdf) av Universal Dependencies
-
Universals of Linguistic Idiosyncrasy in Multilingual Computational Linguistics
Ingår i Dagstuhl Reports, s. 89-138, 2021.
DOI för Universals of Linguistic Idiosyncrasy in Multilingual Computational Linguistics
-
Revisiting Negation in Neural Machine Translation
Ingår i Transactions of the Association for Computational Linguistics, s. 740-755, 2021.
-
Bidirectional Domain Adaptation Using Weighted Multi-Task Learning
Ingår i IWPT 2021, s. 93-105, 2021.
DOI för Bidirectional Domain Adaptation Using Weighted Multi-Task Learning
-
Unsupervised Alphabet Matching in Historical Encrypted Manuscript Images
Ingår i Proceedings of the 4th International Conference on Historical Cryptology HistoCrypt 2021, 2021.
DOI för Unsupervised Alphabet Matching in Historical Encrypted Manuscript Images Ladda ner fulltext (pdf) av Unsupervised Alphabet Matching in Historical Encrypted Manuscript Images
-
Key Design in the Early Modern Era in Europe
Ingår i Proceedings of the 4th International Conference on Historical Cryptology (HistoCrypt 2021), 2021.
DOI för Key Design in the Early Modern Era in Europe Ladda ner fulltext (pdf) av Key Design in the Early Modern Era in Europe
-
Tang, Gongbo
Understanding Neural Machine Translation: An investigation into linguistic phenomena and attention mechanisms
2020.
-
Czech Historical Named Entity Corpus v 1.0
Ingår i Proceedings of the 12th International Conference on Language Resources and Evaluation (LREC 2020), s. 4458-4465, 2020.
Ladda ner fulltext (pdf) av Czech Historical Named Entity Corpus v 1.0
-
What Should/Do/Can LSTMs Learn When Parsing Auxiliary Verb Constructions?
Ingår i Computational linguistics - Association for Computational Linguistics (Print), s. 763-784, 2020.
DOI för What Should/Do/Can LSTMs Learn When Parsing Auxiliary Verb Constructions? Ladda ner fulltext (pdf) av What Should/Do/Can LSTMs Learn When Parsing Auxiliary Verb Constructions?
-
The DReaM Corpus: A Multilingual Annotated Corpus of Grammars for the World's Languages
Ingår i Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), s. 878-884, 2020.
-
Czech Historical Named Entity Corpus v 1.0
Ingår i 12th Conference on Language Resources and Evaluation (LREC 2020), s. 4458-4465, 2020.
Ladda ner fulltext (pdf) av Czech Historical Named Entity Corpus v 1.0
-
Exploiting Cross-lingual Hints to Discover Event Pronouns
Ingår i Proceedings of the 12th Conference on Linguistic Resources and Evaluation (LREC), s. 99-103, 2020.
Ladda ner fulltext (pdf) av Exploiting Cross-lingual Hints to Discover Event Pronouns
-
A Tale of Three Parsers: Towards Diagnostic Evaluation for Meaning Representation Parsing
Ingår i Proceedings of the 12th International Conference on Language Resources and Evaluation (LREC 2020), s. 1902-1909, 2020.
-
SLäNDa: An Annotated Corpus of Narrative and Dialogue in Swedish Literary Fiction
Ingår i Proceedings of the 12th Language Resources and Evaluation Conference, s. 826-834, 2020.
-
A bird’s-eye view on South Asian languages through LSI
Ingår i Journal of South Asian languages and linguistics, s. 203-237, 2020.
DOI för A bird’s-eye view on South Asian languages through LSI Ladda ner fulltext (pdf) av A bird’s-eye view on South Asian languages through LSI
-
Understanding Pure Character-Based Neural Machine Translation: The Case of Translating Finnish into English
Ingår i Proceedings of the 28th International Conference on Computational Linguistics, s. 4251-4262, 2020.
-
Real-valued syntactic word vectors
Ingår i Journal of experimental and theoretical artificial intelligence (Print), s. 557-579, 2020.
DOI för Real-valued syntactic word vectors Ladda ner fulltext (pdf) av Real-valued syntactic word vectors
-
Multilingual Dependency Parsing from Universal Dependencies to Sesame Street
Ingår i Text, Speech, and Dialogue (TSD 2020), s. 11-29, 2020.
DOI för Multilingual Dependency Parsing from Universal Dependencies to Sesame Street
-
Cross-Lingual Domain Adaptation for Dependency Parsing
Ingår i Proceedings of the 19th International Workshop on Treebanks and Linguistic Theories (TLT), s. 62-69, 2020.
DOI för Cross-Lingual Domain Adaptation for Dependency Parsing Ladda ner fulltext (pdf) av Cross-Lingual Domain Adaptation for Dependency Parsing
-
Cross-lingual Embeddings Reveal Universal and Lineage-Specific Patterns in Grammatical Gender Assignment
Ingår i Proceedings of the the 24th Conference on Computational Natural Language Learning, s. 265-275, 2020.
DOI för Cross-lingual Embeddings Reveal Universal and Lineage-Specific Patterns in Grammatical Gender Assignment Ladda ner fulltext (pdf) av Cross-lingual Embeddings Reveal Universal and Lineage-Specific Patterns in Grammatical Gender Assignment
-
Evaluating Word Embeddings for Indonesian–English Code-Mixed Text Based on Synthetic Data
Ingår i Proceedings of the 4th Workshop on Computational Approaches to Code Switching, s. 26-35, 2020.
-
Edition 1.2 of the PARSEME Shared Task on Semi-supervised Identification of Verbal Multiword Expressions
Ingår i Proceedings of the Joint Workshop on Multiword Expressions and Electronic Lexicons, s. 107-118, 2020.
-
The University of Edinburgh-Uppsala University's Submission to the WMT 2020 Chat Translation Task
Ingår i Proceedings of the 5th Conference on Machine Translation (WMT), s. 473-478, 2020.
-
Coreference Strategies in English-German Translation
Ingår i Proceedings of the 3rd Workshop on Computational Models of Reference, Anaphora and Coreference, s. 139-153, 2020.
Ladda ner fulltext (pdf) av Coreference Strategies in English-German Translation
-
IESTAC: English-Italian Parallel Corpus for End-to-End Speech-to-Text Machine Translation
Ingår i Proceedings of the First International Workshop on Natural Language Processing Beyond Text, s. 41-50, 2020.
DOI för IESTAC: English-Italian Parallel Corpus for End-to-End Speech-to-Text Machine Translation
-
Text Processing Procedures for Analysing a Corpus with Medieval Marian Miracle Tales in Old Swedish
Ingår i Proceedings of the 12th International Conference on Agents and Artificial Intelligence, s. 452-458, 2020.
-
Marian Miracles in Old Swedish Texts
Ingår i Les miracles de Notre-Dame du Moyen Âge à nos jours, s. 179-190, 2020.
-
Towards Privacy by Design in Learner Corpora Research: A Case of On-the-fly Pseudonymization of Swedish Learner Essays
Ingår i Proceedings of the 28th International Conference on Computational Linguistics. COLING 2020, s. 357-369, 2020.
-
Kopsala: Transition-Based Graph Parsing via Efficient Training and Effective Encoding
Ingår i 16th International Conference on Parsing Technologies and IWPT 2020 Shared Task on Parsing Into Enhanced Universal Dependencies, s. 236-244, 2020.
DOI för Kopsala: Transition-Based Graph Parsing via Efficient Training and Effective Encoding
-
Transcription of Historical Ciphers and Keys
Ingår i Proceedings of the 3rd International Conference on Historical Cryptology, s. 106-115, 2020.
Ladda ner fulltext (pdf) av Transcription of Historical Ciphers and Keys
-
Automatic Key Structure Extraction
Ingår i Proceedings of the 3rd International Conference on Historical Cryptology, s. 146-152, 2020.
Ladda ner fulltext (pdf) av Automatic Key Structure Extraction
-
Rubenson on the Move: A Biographical Journey
Ingår i Wisdom on the Move, s. 247-250, 2020.
-
Classification of Medieval Documents: Determining the Issuer, Place of Issue, and Decade for Old Swedish Charters
Ingår i DHN 2020 Digital Humanities in the Nordic Countries, s. 12-23, 2020.
-
A Web-based Interactive Transcription Tool for Encrypted Manuscripts
Ingår i Proceedings of the 3rd International Conference on Historical Cryptology HistoCrypt 2020, 2020.
DOI för A Web-based Interactive Transcription Tool for Encrypted Manuscripts Ladda ner fulltext (pdf) av A Web-based Interactive Transcription Tool for Encrypted Manuscripts
-
A Statistical Explanation of the Distribution of Sortal Classifiers in Languages of the World via Computational Classifiers
Ingår i Journal of Quantitative Linguistics, s. 93-113, 2020.
DOI för A Statistical Explanation of the Distribution of Sortal Classifiers in Languages of the World via Computational Classifiers Ladda ner fulltext (pdf) av A Statistical Explanation of the Distribution of Sortal Classifiers in Languages of the World via Computational Classifiers
-
Encoders Help You Disambiguate Word Senses in Neural Machine Translation
Ingår i Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), s. 1429-1435, 2019.
DOI för Encoders Help You Disambiguate Word Senses in Neural Machine Translation
-
Deep Contextualized Word Embeddings in Transition-Based and Graph-Based Dependency Parsing – A Tale of Two Parsers Revisited
Ingår i Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), s. 2755-2768, 2019.
-
Towards a Generic Unsupervised Method for Transcription of Encoded Manuscripts
Ingår i Proceedings of the 3rd International Conference on Digital Access to Textual Cultural Heritage, 2019.
DOI för Towards a Generic Unsupervised Method for Transcription of Encoded Manuscripts