Alexander Fraser

Optical Character Recognition for the International Phonetic Alphabet EACL 2026 NLP for Social Good: A Survey and Outlook of Challenges, Opportunities and Responsible Deployment EACL 2026 LLM Sensitivity Challenges in Abusive Language Detection: Instruction-Tuned vs. Human Feedback COLING 2025 Mask and You Shall Receive: Optimizing Masked Language Modeling For Pretraining BabyLMs EMNLP 2025 EmoBench-UA: A Benchmark Dataset for Emotion Detection in Ukrainian EMNLP 2025 Data-Efficient Hate Speech Detection via Cross-Lingual Nearest Neighbor Retrieval with Limited Labeled Data EMNLP 2025 Extracting Linguistic Information from Large Language Models: Syntactic Relations and Derivational Knowledge EMNLP 2025 From Unaligned to Aligned: Scaling Multilingual LLMs with Multi-Way Parallel Corpora EMNLP 2025 QiMP at SemEval-2025 Task 11: Optimizing Text-based Emotion Classification in English Beyond Traditional Methods SEMEVAL 2025 Positional Overload: Positional Debiasing and Context Window Extension for Large Language Models using Set Encoding ACL 2025 Multilingual Text-to-Image Generation Magnifies Gender Stereotypes ACL 2025 Improving Parallel Sentence Mining for Low-Resource and Endangered Languages ACL 2025 EXECUTE: A Multilingual Benchmark for LLM Token Understanding ACL 2025 A Practical Tool to Help Automate Interlinear Glossing: a Study on Mukrī Kurdish ACL 2025 QiMP at SemEval-2025 Task 11: Optimizing Text-based Emotion Classification in English Beyond Traditional Methods ACL 2025 Can Prompting LLMs Unlock Hate Speech Detection across Languages? A Zero-shot and Few-shot Study ACL 2025 Beyond Literal Token Overlap: Token Alignability for Multilinguality NAACL 2025 Fine-Grained Transfer Learning for Harmful Content Detection through Label-Specific Soft Prompt Tuning NAACL 2025 Joint Localization and Activation Editing for Low-Resource Fine-Tuning ICML 2025 Findings of the WMT 2025 Shared Task LLMs with Limited Resources for Slavic Languages: MT and QA EMNLP 2025 Analyzing the Understanding of Morphologically Complex Words in Large Language Models COLING 2024 Style-Specific Neurons for Steering LLMs in Text Style Transfer EMNLP 2024 Subword Segmentation in LLMs: Looking at Inflection and Consistency EMNLP 2024 A Study of the Class Imbalance Problem in Abusive Language Detection NAACL 2024 VOLIMET: A Parallel Corpus of Literal and Metaphorical Verb-Object Pairs for English–German and English–French NAACL 2024 CUTE: Measuring LLMs’ Understanding of Their Tokens EMNLP 2024 Are BabyLMs Second Language Learners? CONLL 2024 How to Solve Few-Shot Abusive Content Detection Using the Data We Actually Have COLING 2024 Reconstruction of Cuneiform Literary Texts as Text Matching COLING 2024 Informing climate risk analysis using textual information - A research agenda ACL 2024 LLMs Beyond English: Scaling the Multilingual Capability of LLMs with Cross-Lingual Feedback ACL 2024 Understanding Cross-Lingual Alignment—A Survey ACL 2024 Hate Personified: Investigating the role of LLMs in content moderation EMNLP 2024 Multilingual Word Embeddings for Low-Resource Languages using Anchors and a Chain of Related Languages EMNLP 2023 Speaking Multiple Languages Affects the Moral Bias of Language Models ACL 2023 Exploring Anisotropy and Outliers in Multilingual Language Models for Cross-Lingual Semantic Sentence Similarity ACL 2023 On the Copying Problem of Unsupervised NMT: A Training Schedule with a Language Discriminator Loss ACL 2023 A Survey of Methods for Addressing Class Imbalance in Deep-Learning Based Natural Language Processing EACL 2023 AdapterSoup: Weight Averaging to Improve Generalization of Pretrained Language Models EACL 2023 Language-Family Adapters for Low-Resource Multilingual Neural Machine Translation EACL 2023 A Study on Accessing Linguistic Information in Pre-Trained Language Models by Using Prompts EMNLP 2023 Mitigating Data Imbalance and Representation Degeneration in Multilingual Machine Translation EMNLP 2023 Why don’t people use character-level machine translation? ACL 2022 m4 Adapter: Multilingual Multi-Domain Adaptation for Machine Translation with a Meta-Adapter EMNLP 2022 Comparative Analysis of Cross-lingual Contextualized Word Embeddings EMNLP 2022 Combining Static and Contextualised Multilingual Embeddings ACL 2022 Test Suite Evaluation: Morphological Challenges and Pronoun Translation EMNLP 2022 Findings of the WMT 2022 Shared Tasks in Unsupervised MT and Very Low Resource Supervised MT EMNLP 2022 Neural String Edit Distance ACL 2022 Improving Low-Resource Languages in Pre-Trained Multilingual Language Models EMNLP 2022 Improving Both Domain Robustness and Domain Adaptability in Machine Translation COLING 2022 Findings of the WMT 2021 Shared Tasks in Unsupervised MT and Very Low Resource Supervised MT EMNLP 2021 Anchor-based Bilingual Word Embeddings for Low-Resource Languages IJCNLP 2021 Addressing Zero-Resource Domains Using Document-Level Context in Neural Machine Translation EACL 2021 Cross-Lingual Transfer Learning for Hate Speech Detection EACL 2021 Anchor-based Bilingual Word Embeddings for Low-Resource Languages ACL 2021 Improving the Lexical Ability of Pretrained Language Models for Unsupervised Neural Machine Translation NAACL 2021 Adapting Entities across Languages and Cultures EMNLP 2021 Do not neglect related languages: The case of low-resource Occitan cross-lingual word embeddings EMNLP 2021 The LMU Munich System for the WMT 2021 Large-Scale Multilingual Machine Translation Shared Task EMNLP 2021 Improving Machine Translation of Rare and Unseen Word Senses EMNLP 2021 The LMU Munich Systems for the WMT21 Unsupervised and Very Low-Resource Translation Task EMNLP 2021 The LMU Munich System for the WMT 2020 Unsupervised Machine Translation Shared Task EMNLP 2020 The LMU Munich System for the WMT20 Very Low Resource Supervised MT Task EMNLP 2020 Towards Reasonably-Sized Character-Level Transformer NMT by Finetuning Subword Systems EMNLP 2020 ContraCAT: Contrastive Coreference Analytical Templates for Machine Translation COLING 2020 Reusing a Pretrained Language Model on Languages with Limited Corpora for Unsupervised NMT EMNLP 2020 On the Language Neutrality of Pre-trained Multilingual Representations EMNLP 2020 Findings of the WMT 2020 Shared Tasks in Unsupervised MT and Very Low Resource Supervised MT EMNLP 2020 Combining Word Embeddings with Bilingual Orthography Embeddings for Bilingual Dictionary Induction COLING 2020 Modeling Word Formation in English–German Neural Machine Translation ACL 2020 Unsupervised Parallel Sentence Extraction with Parallel Segment Detection Helps Machine Translation ACL 2019 Combining Local and Document-Level Context: The LMU Munich Neural Machine Translation System at WMT19 ACL 2019 The LMU Munich Unsupervised Machine Translation System for WMT19 ACL 2019 Better OOV Translation with Bilingual Terminology Mining ACL 2019 Cross-lingual Annotation Projection Is Effective for Neural Part-of-Speech Tagging NAACL 2019 Two Methods for Domain Adaptation of Bilingual Tasks: Delightfully Simple and Broadly Applicable ACL 2018 Unsupervised Parallel Sentence Extraction from Comparable Corpora EMNLP 2018 Coreference and Coherence in Neural Machine Translation: A Study Using Oracle Experiments EMNLP 2018 The LMU Munich Unsupervised Machine Translation Systems EMNLP 2018 LMU Munich’s Neural Machine Translation Systems at WMT 2018 EMNLP 2018 An Unsupervised System for Parallel Corpus Filtering EMNLP 2018 Embedding Learning Through Multilingual Concept Induction ACL 2018 Evaluating bilingual word embeddings on the long tail NAACL 2018 Annotating tense, mood and voice for English, French and German ACL 2017 Producing Unseen Morphological Variants in Statistical Machine Translation EACL 2017 Addressing Problems across Linguistic Levels in SMT: Combining Approaches to Model Morphology, Syntax and Lexical Choice EACL 2017 Target-Side Context for Discriminative Models in Statistical Machine Translation ACL 2016 Joint Lemmatization and Morphological Tagging with Lemming EMNLP 2015 Rule Selection with Soft Syntactic Features for String-to-Tree Statistical Machine Translation EMNLP 2015 Labeled Morphological Segmentation with Semi-Markov Models CONLL 2015 Investigating the Usefulness of Generalized Word Representations in SMT COLING 2014 How to Produce Unseen Teddy Bears: Improved Morphological Processing of Compounds in SMT EACL 2014 Model With Minimal Translation Units, But Decode With Phrases NAACL 2013 Using subcategorization knowledge to improve case prediction for translation to German ACL 2013 Can Markov Models Over Minimal Translation Units Help Phrase-Based SMT? ACL 2013 Modeling Inflection and Word-Formation in SMT EACL 2012 A Statistical Model for Unsupervised and Semi-supervised Transliteration Mining ACL 2012 Determining the placement of German verbs in English–to–German SMT EACL 2012 An Algorithm for Unsupervised Transliteration Mining with an Application to Word Alignment ACL 2011 Comparing Two Techniques for Learning Transliteration Models Using a Parallel Corpus IJCNLP 2011 A Joint Sequence Translation Model with Integrated Reordering ACL 2011 Hindi-to-Urdu Machine Translation through Transliteration ACL 2010 Bitext-Based Resolution of German Subject-Object Ambiguities NAACL 2010 Improved Unsupervised Sentence Alignment for Symmetrical and Asymmetrical Parallel Corpora COLING 2010 Rich Bitext Projection Features for Parse Reranking EACL 2009 Getting the Structure Right for Word Alignment: LEAF CONLL 2007 Getting the Structure Right for Word Alignment: LEAF EMNLP 2007 Semi-Supervised Training for Statistical Word Alignment COLING 2006 Semi-Supervised Training for Statistical Word Alignment ACL 2006 Improved Machine Translation Performance via Parallel Sentence Extraction from Comparable Corpora NAACL 2004