{"total":151,"rows":[{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075,"area":null},{"id":"2101.08231","title":"Word Alignment by Fine-tuning Embeddings on Parallel Corpora","created":"2021-01-20","cited_by_count":186,"area":null},{"id":"2109.09784","title":"Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarization","created":"2021-08-30","cited_by_count":129,"area":null},{"id":"2305.12182","title":"Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages","created":"2023-05-20","cited_by_count":116,"area":null},{"id":"2302.07856","title":"Dictionary-based Phrase-level Prompting of Large Language Models for Machine Translation","created":"2023-02-15","cited_by_count":74,"area":null},{"id":"2106.16138","title":"XLM-E: Cross-lingual Language Model Pre-training via ELECTRA","created":"2021-06-30","cited_by_count":72,"area":null},{"id":"2108.11357","title":"ProoFVer: Natural Logic Theorem Proving for Fact Verification","created":"2021-08-25","cited_by_count":53,"area":null},{"id":"2107.00676","title":"A Primer on Pretrained Multilingual Language Models","created":"2021-07-01","cited_by_count":49,"area":null},{"id":"2104.08692","title":"MT6: Multilingual Pretrained Text-to-Text Transformer with Translation Pairs","created":"2021-04-18","cited_by_count":41,"area":null},{"id":"2106.06381","title":"Improving Pretrained Cross-Lingual Language Models via Self-Labeled Word Alignment","created":"2021-06-11","cited_by_count":41,"area":null},{"id":"2311.08849","title":"OFA: A Framework of Initializing Unseen Subword Embeddings for Efficient Large-scale Multilingual Continued Pretraining","created":"2023-11-15","cited_by_count":37,"area":null},{"id":"2402.04636","title":"TransLLaMa: LLM-based Simultaneous Translation System","created":"2024-02-07","cited_by_count":34,"area":null},{"id":"2211.15613","title":"Frustratingly Easy Label Projection for Cross-lingual Transfer","created":"2022-11-28","cited_by_count":33,"area":null},{"id":"2205.11758","title":"Analyzing the Mono- and Cross-Lingual Pretraining Dynamics of Multilingual Language Models","created":"2022-05-24","cited_by_count":32,"area":null},{"id":"2212.07850","title":"Attention as a Guide for Simultaneous Speech Translation","created":"2022-12-15","cited_by_count":32,"area":null},{"id":"2107.06483","title":"From Machine Translation to Code-Switching: Generating High-Quality Code-Switched Text","created":"2021-07-14","cited_by_count":29,"area":null},{"id":"2209.09900","title":"LINGUIST: Language Model Instruction Tuning to Generate Annotated Utterances for Intent Classification and Slot Tagging","created":"2022-09-20","cited_by_count":29,"area":null},{"id":"2401.13303","title":"MaLA-500: Massive Language Adaptation of Large Language Models","created":"2024-01-24","cited_by_count":28,"area":null},{"id":"2203.05227","title":"Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methods","created":"2022-03-10","cited_by_count":27,"area":null},{"id":"2202.11451","title":"Zero-shot Cross-lingual Transfer of Prompt-based Tuning with a Unified Multilingual Prompt","created":"2022-02-23","cited_by_count":25,"area":null},{"id":"2402.01512","title":"Distractor Generation in Multiple-Choice Tasks: A Survey of Methods, Datasets, and Evaluation","created":"2024-02-02","cited_by_count":25,"area":null},{"id":"2103.09593","title":"Code-Mixing on Sesame Street: Dawn of the Adversarial Polyglots","created":"2021-03-17","cited_by_count":23,"area":null},{"id":"2105.04840","title":"Investigating the Reordering Capability in CTC-based Non-Autoregressive End-to-End Speech Translation","created":"2021-05-11","cited_by_count":23,"area":null},{"id":"2312.14069","title":"EmphAssess : a Prosodic Benchmark on Assessing Emphasis Transfer in Speech-to-Speech Models","created":"2023-12-21","cited_by_count":22,"area":null},{"id":"2210.07074","title":"CLASP: Few-Shot Cross-Lingual Data Augmentation for Semantic Parsing","created":"2022-10-13","cited_by_count":21,"area":null},{"id":"2210.12623","title":"Model and Data Transfer for Cross-Lingual Sequence Labelling in Zero-Resource Settings","created":"2022-10-23","cited_by_count":21,"area":null},{"id":"2101.00148","title":"Bilingual Lexicon Induction via Unsupervised Bitext Construction and Word Alignment","created":"2021-01-01","cited_by_count":19,"area":null},{"id":"2104.07554","title":"Zero-Shot Cross-lingual Semantic Parsing","created":"2021-04-15","cited_by_count":19,"area":null},{"id":"2305.06586","title":"SemEval-2023 Task 2: Fine-grained Multilingual Named Entity Recognition (MultiCoNER 2)","created":"2023-05-11","cited_by_count":17,"area":null},{"id":"2109.06798","title":"Everything Is All It Takes: A Multipronged Strategy for Zero-Shot Cross-Lingual Information Extraction","created":"2021-09-14","cited_by_count":16,"area":null},{"id":"2401.16092","title":"Multilingual Text-to-Image Generation Magnifies Gender Stereotypes and Prompt Engineering May Not Help You","created":"2024-01-29","cited_by_count":15,"area":null},{"id":"2212.10548","title":"T-Projection: High Quality Annotation Projection for Sequence Labeling Tasks","created":"2022-12-20","cited_by_count":14,"area":null},{"id":"2311.02321","title":"Identifying Context-Dependent Translations for Evaluation Set Production","created":"2023-11-04","cited_by_count":14,"area":null},{"id":"2404.02490","title":"Enhancing Cross-lingual Sentence Embedding for Low-resource Languages with Word Alignment","created":"2024-04-03","cited_by_count":13,"area":null},{"id":"2109.04556","title":"Subword Mapping and Anchoring across Languages","created":"2021-09-09","cited_by_count":12,"area":null},{"id":"2405.10443","title":"Simultaneous Masking, Not Prompting Optimization: A Paradigm Shift in Fine-tuning LLMs for Simultaneous Translation","created":"2024-05-16","cited_by_count":11,"area":null},{"id":"2306.05644","title":"WSPAlign: Word Alignment Pre-training via Large-Scale Weakly Supervised Span Prediction","created":"2023-06-09","cited_by_count":10,"area":null},{"id":"2502.02173","title":"Mass-Editing Memory with Attention in Transformers: A cross-lingual exploration of knowledge","created":"2025-02-04","cited_by_count":10,"area":null},{"id":"2303.13310","title":"SwissBERT: The Multilingual Language Model for Switzerland","created":"2023-03-23","cited_by_count":9,"area":null},{"id":"2405.09913","title":"TransMI: A Framework to Create Strong Baselines from Multilingual Pretrained Language Models for Transliterated Data","created":"2024-05-16","cited_by_count":9,"area":null},{"id":"2110.05151","title":"WeTS: A Benchmark for Translation Suggestion","created":"2021-10-11","cited_by_count":8,"area":null},{"id":"2201.12219","title":"Towards a Broad Coverage Named Entity Resource: A Data-Efficient Approach for Many Diverse Languages","created":"2022-01-28","cited_by_count":8,"area":null},{"id":"2301.12140","title":"Multilingual Sentence Transformer as A Multilingual Word Aligner","created":"2023-01-28","cited_by_count":8,"area":null},{"id":"2312.01582","title":"Explaining with Contrastive Phrasal Highlighting: A Case Study in Assisting Humans to Detect Translation Differences","created":"2023-12-04","cited_by_count":8,"area":null},{"id":"2503.02969","title":"InfiniSST: Simultaneous Translation of Unbounded Speech with Large Language Model","created":"2025-03-04","cited_by_count":8,"area":null},{"id":"2506.13044","title":"Just Go Parallel: Improving the Multilingual Capabilities of Large Language Models","created":"2025-06-16","cited_by_count":8,"area":null},{"id":"2209.13192","title":"Direct Speech Translation for Automatic Subtitling","created":"2022-09-27","cited_by_count":7,"area":null},{"id":"2311.09404","title":"To Translate or Not to Translate: A Systematic Investigation of Translation-Based Cross-Lingual Transfer to Low-Resource Languages","created":"2023-11-15","cited_by_count":7,"area":null},{"id":"2312.01308","title":"Bridging Background Knowledge Gaps in Translation with Automatic Explicitation","created":"2023-12-03","cited_by_count":7,"area":null},{"id":"2306.04116","title":"Unbalanced Optimal Transport for Unbalanced Word Alignment","created":"2023-06-07","cited_by_count":6,"area":null},{"id":"2306.04384","title":"Multilingual Clinical NER: Translation or Cross-lingual Transfer?","created":"2023-06-07","cited_by_count":6,"area":null},{"id":"2406.17377","title":"A Three-Pronged Approach to Cross-Lingual Adaptation with Multilingual LLMs","created":"2024-06-25","cited_by_count":6,"area":null},{"id":"2406.18776","title":"Implicit Discourse Relation Classification For Nigerian Pidgin","created":"2024-06-26","cited_by_count":6,"area":null},{"id":"2504.02122","title":"Overcoming Vocabulary Constraints with Pixel-level Fallback","created":"2025-04-02","cited_by_count":6,"area":null},{"id":"2510.13796","title":"The Mechanistic Emergence of Symbol Grounding in Language Models","created":"2025-10-15","cited_by_count":6,"area":null},{"id":"2109.06515","title":"Netmarble AI Center's WMT21 Automatic Post-Editing Shared Task Submission","created":"2021-09-14","cited_by_count":5,"area":null},{"id":"2110.08538","title":"Substructure Distribution Projection for Zero-Shot Cross-Lingual Dependency Parsing","created":"2021-10-16","cited_by_count":5,"area":null},{"id":"2209.02962","title":"Adam Mickiewicz University at WMT 2022: NER-Assisted and Quality-Aware Neural Machine Translation","created":"2022-09-07","cited_by_count":5,"area":null},{"id":"2305.10561","title":"Massively Multi-Lingual Event Understanding: Extraction, Visualization, and Search","created":"2023-05-17","cited_by_count":5,"area":null},{"id":"2305.13303","title":"Towards Unsupervised Recognition of Token-level Semantic Differences in Related Documents","created":"2023-05-22","cited_by_count":5,"area":null},{"id":"2406.04914","title":"Submodular Framework for Structured-Sparse Optimal Transport","created":"2024-06-07","cited_by_count":5,"area":null},{"id":"2406.11085","title":"Multiple Sources are Better Than One: Incorporating External Knowledge in Low-Resource Glossing","created":"2024-06-16","cited_by_count":5,"area":null},{"id":"2109.06283","title":"Graph Algorithms for Multiparallel Word Alignment","created":"2021-09-13","cited_by_count":4,"area":null},{"id":"2203.08654","title":"Graph Neural Networks for Multiparallel Word Alignment","created":"2022-03-16","cited_by_count":4,"area":null},{"id":"2301.10527","title":"Cross-lingual Argument Mining in the Medical Domain","created":"2023-01-25","cited_by_count":4,"area":null},{"id":"2302.07912","title":"Meeting the Needs of Low-Resource Languages: The Value of Automatic Alignments via Pretrained Models","created":"2023-02-15","cited_by_count":4,"area":null},{"id":"2411.04530","title":"Tomato, Tomahto, Tomate: Do Multilingual Language Models Understand Based on Subword-Level Semantic Concepts?","created":"2024-11-07","cited_by_count":4,"area":null},{"id":"2502.11308","title":"ALGEN: Few-shot Inversion Attacks on Textual Embeddings using Alignment and Generation","created":"2025-02-16","cited_by_count":4,"area":null},{"id":"2107.06632","title":"ParCourE: A Parallel Corpus Explorer for a Massively Multilingual Corpus","created":"2021-07-14","cited_by_count":3,"area":null},{"id":"2203.01644","title":"UDAAN: Machine Learning based Post-Editing tool for Document Translation","created":"2022-03-03","cited_by_count":3,"area":null},{"id":"2203.10010","title":"CaMEL: Case Marker Extraction without Labels","created":"2022-03-18","cited_by_count":3,"area":null},{"id":"2206.14504","title":"GERNERMED++: Transfer Learning in German Medical NLP","created":"2022-06-29","cited_by_count":3,"area":null},{"id":"2212.00138","title":"Word Alignment in the Era of Deep Learning: A Tutorial","created":"2022-11-30","cited_by_count":3,"area":null},{"id":"2306.08702","title":"Does mBERT understand Romansh? Evaluating word embeddings using word alignment","created":"2023-06-14","cited_by_count":3,"area":null},{"id":"2308.07489","title":"SOTASTREAM: A Streaming Approach to Machine Translation Training","created":"2023-08-14","cited_by_count":3,"area":null},{"id":"2309.08873","title":"X-PARADE: Cross-Lingual Textual Entailment and Information Divergence across Paragraphs","created":"2023-09-16","cited_by_count":3,"area":null},{"id":"2309.12998","title":"Audience-specific Explanations for Machine Translation","created":"2023-09-22","cited_by_count":3,"area":null},{"id":"2401.06620","title":"TransliCo: A Contrastive Learning Framework to Address the Script Barrier in Multilingual Pretrained Language Models","created":"2024-01-12","cited_by_count":3,"area":null},{"id":"2404.11532","title":"Select and Reorder: A Novel Approach for Neural Sign Language Production","created":"2024-04-17","cited_by_count":3,"area":null},{"id":"2407.12881","title":"BinaryAlign: Word Alignment as Binary Sequence Labeling","created":"2024-07-16","cited_by_count":3,"area":null},{"id":"2503.20007","title":"Low-resource Machine Translation for Code-switched Kazakh-Russian Language Pair","created":"2025-03-25","cited_by_count":3,"area":null},{"id":"2511.03295","title":"How to Evaluate Speech Translation with Source-Aware Neural MT Metrics","created":"2025-11-05","cited_by_count":3,"area":null},{"id":"2206.08709","title":"Statistical and Neural Methods for Cross-lingual Entity Label Mapping in Knowledge Graphs","created":"2022-06-17","cited_by_count":2,"area":null},{"id":"2210.04141","title":"Cross-Align: Modeling Deep Cross-lingual Interactions for Word Alignment","created":"2022-10-09","cited_by_count":2,"area":null},{"id":"2304.11766","title":"NAIST-SIC-Aligned: an Aligned English-Japanese Simultaneous Interpretation Corpus","created":"2023-04-23","cited_by_count":2,"area":null},{"id":"2307.04096","title":"Optimal Transport Posterior Alignment for Cross-lingual Semantic Parsing","created":"2023-07-09","cited_by_count":2,"area":null},{"id":"2401.05727","title":"Zero Resource Cross-Lingual Part Of Speech Tagging","created":"2024-01-11","cited_by_count":2,"area":null},{"id":"2402.13571","title":"Multilingual Coreference Resolution in Low-resource South Asian Languages","created":"2024-02-21","cited_by_count":2,"area":null},{"id":"2403.08189","title":"Embedded Translations for Low-resource Automated Glossing","created":"2024-03-13","cited_by_count":2,"area":null},{"id":"2409.18199","title":"LangSAMP: Language-Script Aware Multilingual Pretraining","created":"2024-09-26","cited_by_count":2,"area":null},{"id":"2502.12959","title":"AlignFreeze: Navigating the Impact of Realignment on the Layers of Multilingual Models Across Diverse Languages","created":"2025-02-18","cited_by_count":2,"area":null},{"id":"2504.21677","title":"20min-XD: A Comparable Corpus of Swiss News Articles","created":"2025-04-30","cited_by_count":2,"area":null},{"id":"2505.10507","title":"The Devil Is in the Word Alignment Details: On Translation-Based Cross-Lingual Transfer for Token Classification Tasks","created":"2025-05-15","cited_by_count":2,"area":null},{"id":"2505.14393","title":"Editing Across Languages: A Survey of Multilingual Knowledge Editing","created":"2025-05-20","cited_by_count":2,"area":null},{"id":"2506.13143","title":"CMU's IWSLT 2025 Simultaneous Speech Translation System","created":"2025-06-16","cited_by_count":2,"area":null},{"id":"2508.07781","title":"SASST: Leveraging Syntax-Aware Chunking and LLMs for Simultaneous Speech Translation","created":"2025-08-11","cited_by_count":2,"area":null},{"id":"2111.11815","title":"CL-NERIL: A Cross-Lingual Model for NER in Indian Languages","created":"2021-11-23","cited_by_count":1,"area":null},{"id":"2201.13429","title":"Constrained Density Matching and Modeling for Cross-lingual Alignment of Contextualized Representations","created":"2022-01-31","cited_by_count":1,"area":null},{"id":"2203.07643","title":"Can Synthetic Translations Improve Bitext Quality?","created":"2022-03-15","cited_by_count":1,"area":null},{"id":"2204.00871","title":"Accurate Online Posterior Alignments for Principled Lexically-Constrained Decoding","created":"2022-04-02","cited_by_count":1,"area":null}],"next_cursor":"100"}