{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/bert/papers/29","list_of":"/method/bert","method":"BERT","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":29,"pages_in_order":70,"rows_per_page":100,"rows":[2801,2900],"of":6938,"counts":{"archive_papers_tagged":6938,"with_a_code_link":2862,"where_syntology_ran_a_sample":640,"not_listed_spam_title":0,"listed":6938,"listed_where_code_ran":640,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":520,"every_run_a_failure_of_syntologys_instrument":120,"listed_with_a_run_with_no_instrument_failure":520,"listed_every_run_a_failure_of_syntologys_instrument":120,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/bert","prev":"/method/bert/papers/28","next":"/method/bert/papers/30","papers":[{"paper":null,"slug":"logion-machine-learning-for-greek-philology","title":"Logion: Machine Learning for Greek Philology","date":"2023-05-01","arxiv_id":"2305.01099","n_code_links":0,"syntology":null},{"paper":null,"slug":"retrieving-comparative-arguments-using","title":"Retrieving Comparative Arguments using Ensemble Methods and Neural Information Retrieval","date":"2023-05-01","arxiv_id":"2305.01513","n_code_links":0,"syntology":null},{"paper":"/paper/safewebuh-at-semeval-2023-task-11-learning","slug":"safewebuh-at-semeval-2023-task-11-learning","title":"SafeWebUH at SemEval-2023 Task 11: Learning Annotator Disagreement in Derogatory Text: Comparison of Direct Training vs Aggregation","date":"2023-05-01","arxiv_id":"2305.01050","n_code_links":1,"syntology":null},{"paper":"/paper/are-the-best-multilingual-document-embeddings","slug":"are-the-best-multilingual-document-embeddings","title":"Are the Best Multilingual Document Embeddings simply Based on Sentence Embeddings?","date":"2023-04-28","arxiv_id":"2304.14796","n_code_links":1,"syntology":null},{"paper":"/paper/flowtransformer-a-transformer-framework-for","slug":"flowtransformer-a-transformer-framework-for","title":"FlowTransformer: A Transformer Framework for Flow-based Network Intrusion Detection Systems","date":"2023-04-28","arxiv_id":"2304.14746","n_code_links":1,"syntology":null},{"paper":"/paper/towards-better-domain-adaptation-for-self","slug":"towards-better-domain-adaptation-for-self","title":"Towards Better Domain Adaptation for Self-supervised Models: A Case Study of Child ASR","date":"2023-04-28","arxiv_id":"2305.00115","n_code_links":1,"syntology":null},{"paper":null,"slug":"assessing-text-mining-and-technical-analyses","title":"Assessing Text Mining and Technical Analyses on Forecasting Financial Time Series","date":"2023-04-27","arxiv_id":"2304.14544","n_code_links":0,"syntology":null},{"paper":"/paper/pybibx-a-python-library-for-bibliometric-and","slug":"pybibx-a-python-library-for-bibliometric-and","title":"pyBibX -- A Python Library for Bibliometric and Scientometric Analysis Powered with Artificial Intelligence Tools","date":"2023-04-27","arxiv_id":"2304.14516","n_code_links":1,"syntology":null},{"paper":"/paper/hausanlp-at-semeval-2023-task-12-leveraging","slug":"hausanlp-at-semeval-2023-task-12-leveraging","title":"HausaNLP at SemEval-2023 Task 12: Leveraging African Low Resource TweetData for Sentiment Analysis","date":"2023-04-26","arxiv_id":"2304.13634","n_code_links":1,"syntology":null},{"paper":"/paper/impact-of-position-bias-on-language-models-in","slug":"impact-of-position-bias-on-language-models-in","title":"Technical Report: Impact of Position Bias on Language Models in Token Classification","date":"2023-04-26","arxiv_id":"2304.13567","n_code_links":2,"syntology":null},{"paper":null,"slug":"nlp-ltu-at-semeval-2023-task-10-the-impact-of","title":"NLP-LTU at SemEval-2023 Task 10: The Impact of Data Augmentation and Semi-Supervised Learning Techniques on Text Classification Performance on an Imbalanced Dataset","date":"2023-04-25","arxiv_id":"2304.12847","n_code_links":0,"syntology":null},{"paper":null,"slug":"what-does-bert-learn-about-prosody","title":"What does BERT learn about prosody?","date":"2023-04-25","arxiv_id":"2304.12706","n_code_links":0,"syntology":null},{"paper":"/paper/paragraph2graph-a-gnn-based-framework-for","slug":"paragraph2graph-a-gnn-based-framework-for","title":"PARAGRAPH2GRAPH: A GNN-based framework for layout paragraph analysis","date":"2023-04-24","arxiv_id":"2304.11810","n_code_links":1,"syntology":null},{"paper":"/paper/pre-trained-embeddings-for-entity-resolution","slug":"pre-trained-embeddings-for-entity-resolution","title":"Pre-trained Embeddings for Entity Resolution: An Experimental Analysis [Experiment, Analysis & Benchmark]","date":"2023-04-24","arxiv_id":"2304.12329","n_code_links":1,"syntology":null},{"paper":"/paper/socialdial-a-benchmark-for-socially-aware","slug":"socialdial-a-benchmark-for-socially-aware","title":"SocialDial: A Benchmark for Socially-Aware Dialogue Systems","date":"2023-04-24","arxiv_id":"2304.12026","n_code_links":1,"syntology":null},{"paper":"/paper/exploring-challenges-of-deploying-bert-based","slug":"exploring-challenges-of-deploying-bert-based","title":"Processing Natural Language on Embedded Devices: How Well Do Transformer Models Perform?","date":"2023-04-23","arxiv_id":"2304.11520","n_code_links":2,"syntology":null},{"paper":null,"slug":"l3cube-indicsbert-a-simple-approach-for","title":"L3Cube-IndicSBERT: A simple approach for learning cross-lingual sentence representations using multilingual BERT","date":"2023-04-22","arxiv_id":"2304.11434","n_code_links":0,"syntology":null},{"paper":"/paper/a-group-specific-approach-to-nlp-for-hate","slug":"a-group-specific-approach-to-nlp-for-hate","title":"A Group-Specific Approach to NLP for Hate Speech Detection","date":"2023-04-21","arxiv_id":"2304.11223","n_code_links":1,"syntology":null},{"paper":null,"slug":"bert-based-clinical-knowledge-extraction-for","title":"BERT Based Clinical Knowledge Extraction for Biomedical Knowledge Graph Construction and Analysis","date":"2023-04-21","arxiv_id":"2304.10996","n_code_links":0,"syntology":null},{"paper":"/paper/building-multimodal-ai-chatbots","slug":"building-multimodal-ai-chatbots","title":"Building Multimodal AI Chatbots","date":"2023-04-21","arxiv_id":"2305.03512","n_code_links":1,"syntology":null},{"paper":"/paper/multi-modal-deep-learning-for-credit-rating","slug":"multi-modal-deep-learning-for-credit-rating","title":"Multi-Modal Deep Learning for Credit Rating Prediction Using Text and Numerical Data Streams","date":"2023-04-21","arxiv_id":"2304.10740","n_code_links":1,"syntology":null},{"paper":null,"slug":"text2time-transformer-based-article-time","title":"Text2Time: Transformer-based Article Time Period Prediction","date":"2023-04-21","arxiv_id":"2304.10859","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-cross-modal-information-retrieval-possible","title":"Is Cross-modal Information Retrieval Possible without Training?","date":"2023-04-20","arxiv_id":"2304.11095","n_code_links":0,"syntology":null},{"paper":null,"slug":"movie-box-office-prediction-with-self","title":"Movie Box Office Prediction With Self-Supervised and Visually Grounded Pretraining","date":"2023-04-20","arxiv_id":"2304.10311","n_code_links":0,"syntology":null},{"paper":null,"slug":"word-sense-induction-with-knowledge-1","title":"Word Sense Induction with Knowledge Distillation from BERT","date":"2023-04-20","arxiv_id":"2304.10642","n_code_links":0,"syntology":null},{"paper":"/paper/scaling-transformer-to-1m-tokens-and-beyond","slug":"scaling-transformer-to-1m-tokens-and-beyond","title":"Scaling Transformer to 1M tokens and beyond with RMT","date":"2023-04-19","arxiv_id":"2304.11062","n_code_links":3,"syntology":{"ran":5,"of":8,"n_ran_checked":4,"n_instrument":1,"unverified":3,"pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["booydar/t5-experiments"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/tiefake-title-text-similarity-and-emotion","slug":"tiefake-title-text-similarity-and-emotion","title":"TieFake: Title-Text Similarity and Emotion-Aware Fake News Detection","date":"2023-04-19","arxiv_id":"2304.09421","n_code_links":2,"syntology":null},{"paper":"/paper/outlier-suppression-accurate-quantization-of","slug":"outlier-suppression-accurate-quantization-of","title":"Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling","date":"2023-04-18","arxiv_id":"2304.09145","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":2,"n_instrument":3,"unverified":2,"pointer_only":0,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["modeltc/outlier_suppression_plus"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/context-dependent-embedding-utterance","slug":"context-dependent-embedding-utterance","title":"Context-Dependent Embedding Utterance Representations for Emotion Recognition in Conversations","date":"2023-04-17","arxiv_id":"2304.08216","n_code_links":1,"syntology":null},{"paper":"/paper/instructuie-multi-task-instruction-tuning-for","slug":"instructuie-multi-task-instruction-tuning-for","title":"InstructUIE: Multi-task Instruction Tuning for Unified Information Extraction","date":"2023-04-17","arxiv_id":"2304.08085","n_code_links":1,"syntology":null},{"paper":null,"slug":"multimodal-short-video-rumor-detection-system","title":"Multimodal Short Video Rumor Detection System Based on Contrastive Learning","date":"2023-04-17","arxiv_id":"2304.08401","n_code_links":0,"syntology":null},{"paper":null,"slug":"new-product-development-npd-through-social","title":"New Product Development (NPD) through Social Media-based Analysis by Comparing Word2Vec and BERT Word Embeddings","date":"2023-04-17","arxiv_id":"2304.08369","n_code_links":0,"syntology":null},{"paper":"/paper/the-minipile-challenge-for-data-efficient","slug":"the-minipile-challenge-for-data-efficient","title":"The MiniPile Challenge for Data-Efficient Language Models","date":"2023-04-17","arxiv_id":"2304.08442","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-virtual-simulation-pilot-agent-for-training","title":"A Virtual Simulation-Pilot Agent for Training of Air Traffic Controllers","date":"2023-04-16","arxiv_id":"2304.07842","n_code_links":0,"syntology":null},{"paper":"/paper/argugpt-evaluating-understanding-and","slug":"argugpt-evaluating-understanding-and","title":"ArguGPT: evaluating, understanding and identifying argumentative essays generated by GPT models","date":"2023-04-16","arxiv_id":"2304.07666","n_code_links":2,"syntology":null},{"paper":null,"slug":"can-chatgpt-forecast-stock-price-movements","title":"Can ChatGPT Forecast Stock Price Movements? Return Predictability and Large Language Models","date":"2023-04-15","arxiv_id":"2304.07619","n_code_links":0,"syntology":null},{"paper":"/paper/simplex-a-lexical-text-simplification","slug":"simplex-a-lexical-text-simplification","title":"SimpLex: a lexical text simplification architecture","date":"2023-04-14","arxiv_id":"2304.07002","n_code_links":1,"syntology":null},{"paper":null,"slug":"automated-mapping-of-cve-vulnerability","title":"Automated Mapping of CVE Vulnerability Records to MITRE CWE Weaknesses","date":"2023-04-13","arxiv_id":"2304.11130","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluation-of-social-biases-in-recent-large","title":"Evaluation of Social Biases in Recent Large Pre-Trained Models","date":"2023-04-13","arxiv_id":"2304.06861","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-use-of-foundation-models-for","title":"Exploring the Use of Foundation Models for Named Entity Recognition and Lemmatization Tasks in Slavic Languages","date":"2023-04-11","arxiv_id":"2304.05336","n_code_links":0,"syntology":null},{"paper":"/paper/towards-preserving-word-order-importance","slug":"towards-preserving-word-order-importance","title":"Towards preserving word order importance through Forced Invalidation","date":"2023-04-11","arxiv_id":"2304.05221","n_code_links":1,"syntology":null},{"paper":null,"slug":"incorporating-structured-sentences-with-time","title":"Incorporating Structured Sentences with Time-enhanced BERT for Fully-inductive Temporal Relation Prediction","date":"2023-04-10","arxiv_id":"2304.04717","n_code_links":0,"syntology":null},{"paper":"/paper/is-chatgpt-a-good-sentiment-analyzer-a","slug":"is-chatgpt-a-good-sentiment-analyzer-a","title":"Is ChatGPT a Good Sentiment Analyzer? A Preliminary Study","date":"2023-04-10","arxiv_id":"2304.04339","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["nustm/chatgpt-sentiment-evaluation"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/learning-to-tokenize-for-generative-retrieval","slug":"learning-to-tokenize-for-generative-retrieval","title":"Learning to Tokenize for Generative Retrieval","date":"2023-04-09","arxiv_id":"2304.04171","n_code_links":1,"syntology":null},{"paper":"/paper/factify-2-a-multimodal-fake-news-and-satire","slug":"factify-2-a-multimodal-fake-news-and-satire","title":"Factify 2: A Multimodal Fake News and Satire News Dataset","date":"2023-04-08","arxiv_id":"2304.03897","n_code_links":1,"syntology":null},{"paper":null,"slug":"flexmoe-scaling-large-scale-sparse-pre","title":"FlexMoE: Scaling Large-scale Sparse Pre-trained Model Training via Dynamic Device Placement","date":"2023-04-08","arxiv_id":"2304.03946","n_code_links":0,"syntology":null},{"paper":"/paper/interpretable-multi-labeled-bengali-toxic","slug":"interpretable-multi-labeled-bengali-toxic","title":"Interpretable Multi Labeled Bengali Toxic Comments Classification using Deep Learning","date":"2023-04-08","arxiv_id":"2304.04087","n_code_links":1,"syntology":null},{"paper":"/paper/tmn-at-semeval-2023-task-9-multilingual-tweet","slug":"tmn-at-semeval-2023-task-9-multilingual-tweet","title":"tmn at SemEval-2023 Task 9: Multilingual Tweet Intimacy Detection using XLM-T, Google Translate, and Ensemble Learning","date":"2023-04-08","arxiv_id":"2304.04054","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-the-logical-reasoning-ability-of","slug":"evaluating-the-logical-reasoning-ability-of","title":"Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4","date":"2023-04-07","arxiv_id":"2304.03439","n_code_links":1,"syntology":null},{"paper":null,"slug":"chatgpt-crawler-find-out-if-chatgpt-really","title":"ChatGPT-Crawler: Find out if ChatGPT really knows what it's talking about","date":"2023-04-06","arxiv_id":"2304.03325","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-for-opinion-mining-and-topic","title":"Deep Learning for Opinion Mining and Topic Classification of Course Reviews","date":"2023-04-06","arxiv_id":"2304.03394","n_code_links":0,"syntology":null},{"paper":"/paper/micron-bert-bert-based-facial-micro","slug":"micron-bert-bert-based-facial-micro","title":"Micron-BERT: BERT-based Facial Micro-Expression Recognition","date":"2023-04-06","arxiv_id":"2304.03195","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["uark-cviu/micron-bert"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"multi-label-classification-of-open-ended","title":"Multi-label classification of open-ended questions with BERT","date":"2023-04-06","arxiv_id":"2304.02945","n_code_links":0,"syntology":null},{"paper":null,"slug":"bengali-fake-review-detection-using-semi","title":"Bengali Fake Review Detection using Semi-supervised Generative Adversarial Networks","date":"2023-04-05","arxiv_id":"2304.02739","n_code_links":0,"syntology":null},{"paper":null,"slug":"context-aware-classification-of-legal","title":"Context-Aware Classification of Legal Document Pages","date":"2023-04-05","arxiv_id":"2304.02787","n_code_links":0,"syntology":null},{"paper":"/paper/improved-visual-fine-tuning-with-natural","slug":"improved-visual-fine-tuning-with-natural","title":"Improved Visual Fine-tuning with Natural Language Supervision","date":"2023-04-04","arxiv_id":"2304.01489","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["idstcv/tes"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"san-bert-extractive-summarization-for","title":"San-BERT: Extractive Summarization for Sanskrit Documents using BERT and it's variants","date":"2023-04-04","arxiv_id":"2304.01894","n_code_links":0,"syntology":null},{"paper":null,"slug":"detection-of-homophobia-transphobia-in","title":"Detection of Homophobia & Transphobia in Dravidian Languages: Exploring Deep Learning Methods","date":"2023-04-03","arxiv_id":"2304.01241","n_code_links":0,"syntology":null},{"paper":"/paper/greekbart-the-first-pretrained-greek-sequence","slug":"greekbart-the-first-pretrained-greek-sequence","title":"GreekBART: The First Pretrained Greek Sequence-to-Sequence Model","date":"2023-04-03","arxiv_id":"2304.00869","n_code_links":2,"syntology":null},{"paper":"/paper/hate-speech-targets-detection-in-parler-using","slug":"hate-speech-targets-detection-in-parler-using","title":"Hate Speech Targets Detection in Parler using BERT","date":"2023-04-03","arxiv_id":"2304.01179","n_code_links":1,"syntology":null},{"paper":"/paper/minirbt-a-two-stage-distilled-small-chinese","slug":"minirbt-a-two-stage-distilled-small-chinese","title":"MiniRBT: A Two-stage Distilled Small Chinese Pre-trained Model","date":"2023-04-03","arxiv_id":"2304.00717","n_code_links":1,"syntology":null},{"paper":"/paper/safety-analysis-in-the-era-of-large-language","slug":"safety-analysis-in-the-era-of-large-language","title":"Safety Analysis in the Era of Large Language Models: A Case Study of STPA using ChatGPT","date":"2023-04-03","arxiv_id":"2304.01246","n_code_links":2,"syntology":null},{"paper":null,"slug":"classifying-covid-19-related-tweets-for-fake","title":"Classifying COVID-19 Related Tweets for Fake News Detection and Sentiment Analysis with BERT-based Models","date":"2023-04-02","arxiv_id":"2304.00636","n_code_links":0,"syntology":null},{"paper":"/paper/the-other-side-of-compression-measuring-bias","slug":"the-other-side-of-compression-measuring-bias","title":"The Other Side of Compression: Measuring Bias in Pruned Transformers","date":"2023-04-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/bertino-an-italian-distilbert-model","slug":"bertino-an-italian-distilbert-model","title":"BERTino: an Italian DistilBERT model","date":"2023-03-31","arxiv_id":"2303.18121","n_code_links":1,"syntology":null},{"paper":null,"slug":"extracting-thyroid-nodules-characteristics","title":"Extracting Thyroid Nodules Characteristics from Ultrasound Reports Using Transformer-based Natural Language Processing Methods","date":"2023-03-31","arxiv_id":"2304.00115","n_code_links":0,"syntology":null},{"paper":null,"slug":"jobham-place-with-smart-recommend-job-options","title":"JobHam-place with smart recommend job options and candidate filtering options","date":"2023-03-31","arxiv_id":"2303.17930","n_code_links":0,"syntology":null},{"paper":null,"slug":"quick-dense-retrievers-consume-kale-post","title":"Quick Dense Retrievers Consume KALE: Post Training Kullback Leibler Alignment of Embeddings for Asymmetrical dual encoders","date":"2023-03-31","arxiv_id":"2304.01016","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluation-of-gpt-and-bert-based-models-on","title":"Evaluation of GPT and BERT-based models on identifying protein-protein interactions in biomedical text","date":"2023-03-30","arxiv_id":"2303.17728","n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-tuning-bert-with-character-level-noise","title":"Fine-Tuning BERT with Character-Level Noise for Zero-Shot Transfer to Dialects and Closely-Related Languages","date":"2023-03-30","arxiv_id":"2303.17683","n_code_links":0,"syntology":null},{"paper":null,"slug":"oberta-improving-sparse-transfer-learning-via","title":"oBERTa: Improving Sparse Transfer Learning via improved initialization, distillation, and pruning regimes","date":"2023-03-30","arxiv_id":"2303.17612","n_code_links":0,"syntology":null},{"paper":"/paper/bert4eth-a-pre-trained-transformer-for","slug":"bert4eth-a-pre-trained-transformer-for","title":"BERT4ETH: A Pre-trained Transformer for Ethereum Fraud Detection","date":"2023-03-29","arxiv_id":"2303.18138","n_code_links":1,"syntology":null},{"paper":"/paper/larger-probes-tell-a-different-story","slug":"larger-probes-tell-a-different-story","title":"Larger Probes Tell a Different Story: Extending Psycholinguistic Datasets Via In-Context Learning","date":"2023-03-29","arxiv_id":"2303.16445","n_code_links":1,"syntology":null},{"paper":null,"slug":"textmi-textualize-multimodal-information-for","title":"TextMI: Textualize Multimodal Information for Integrating Non-verbal Cues in Pre-trained Language Models","date":"2023-03-27","arxiv_id":"2303.15430","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-multimodal-sentiment-analysis-via","title":"Exploring Multimodal Sentiment Analysis via CBAM Attention and Double-layer BiLSTM Architecture","date":"2023-03-26","arxiv_id":"2303.14708","n_code_links":0,"syntology":null},{"paper":"/paper/indonesian-text-to-image-synthesis-with","slug":"indonesian-text-to-image-synthesis-with","title":"Indonesian Text-to-Image Synthesis with Sentence-BERT and FastGAN","date":"2023-03-25","arxiv_id":"2303.14517","n_code_links":1,"syntology":null},{"paper":null,"slug":"spatio-temporal-driven-attention-graph-neural","title":"Spatio-Temporal driven Attention Graph Neural Network with Block Adjacency matrix (STAG-NN-BA)","date":"2023-03-25","arxiv_id":"2303.14322","n_code_links":0,"syntology":null},{"paper":null,"slug":"depression-detection-in-social-media-posts","title":"Depression detection in social media posts using affective and social norm features","date":"2023-03-24","arxiv_id":"2303.14279","n_code_links":0,"syntology":null},{"paper":"/paper/sigmorphon-2023-shared-task-of-interlinear","slug":"sigmorphon-2023-shared-task-of-interlinear","title":"SIGMORPHON 2023 Shared Task of Interlinear Glossing: Baseline Model","date":"2023-03-24","arxiv_id":"2303.14234","n_code_links":1,"syntology":null},{"paper":null,"slug":"toward-open-domain-slot-filling-via-self","title":"Toward Open-domain Slot Filling via Self-supervised Co-training","date":"2023-03-24","arxiv_id":"2303.13801","n_code_links":0,"syntology":null},{"paper":"/paper/where-to-go-next-for-recommender-systems-id","slug":"where-to-go-next-for-recommender-systems-id","title":"Where to Go Next for Recommender Systems? ID- vs. Modality-based Recommender Models Revisited","date":"2023-03-24","arxiv_id":"2303.13835","n_code_links":1,"syntology":null},{"paper":"/paper/a-novel-patent-similarity-measurement","slug":"a-novel-patent-similarity-measurement","title":"A Novel Patent Similarity Measurement Methodology: Semantic Distance and Technological Distance","date":"2023-03-23","arxiv_id":"2303.16767","n_code_links":1,"syntology":null},{"paper":"/paper/retrieval-augmented-classification-with","slug":"retrieval-augmented-classification-with","title":"Retrieval-Augmented Classification with Decoupled Representation","date":"2023-03-23","arxiv_id":"2303.13065","n_code_links":1,"syntology":null},{"paper":null,"slug":"analyzing-the-generalizability-of-deep","title":"Analyzing the Generalizability of Deep Contextualized Language Representations For Text Classification","date":"2023-03-22","arxiv_id":"2303.12936","n_code_links":0,"syntology":null},{"paper":null,"slug":"generate-labeled-training-data-using-prompt","title":"Generate labeled training data using Prompt Programming and GPT-3. An example of Big Five Personality Classification","date":"2023-03-22","arxiv_id":"2303.12279","n_code_links":0,"syntology":null},{"paper":null,"slug":"tron-transformer-neural-network-acceleration","title":"TRON: Transformer Neural Network Acceleration with Non-Coherent Silicon Photonics","date":"2023-03-22","arxiv_id":"2303.12914","n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-tuning-climatebert-transformer-with","title":"Fine-tuning ClimateBert transformer with ClimaText for the disclosure analysis of climate-related financial risks","date":"2023-03-21","arxiv_id":"2303.13373","n_code_links":0,"syntology":null},{"paper":"/paper/is-bert-blind-exploring-the-effect-of-vision","slug":"is-bert-blind-exploring-the-effect-of-vision","title":"Is BERT Blind? Exploring the Effect of Vision-and-Language Pretraining on Visual Language Understanding","date":"2023-03-21","arxiv_id":"2303.12513","n_code_links":1,"syntology":null},{"paper":null,"slug":"multimodal-pre-training-framework-for","title":"Multimodal Pre-training Framework for Sequential Recommendation via Contrastive Learning","date":"2023-03-21","arxiv_id":"2303.11879","n_code_links":0,"syntology":null},{"paper":"/paper/character-word-or-both-revisiting-the","slug":"character-word-or-both-revisiting-the","title":"Character, Word, or Both? Revisiting the Segmentation Granularity for Chinese Pre-trained Language Models","date":"2023-03-20","arxiv_id":"2303.10893","n_code_links":1,"syntology":null},{"paper":"/paper/ctran-cnn-transformer-based-network-for","slug":"ctran-cnn-transformer-based-network-for","title":"CTRAN: CNN-Transformer-based Network for Natural Language Understanding","date":"2023-03-19","arxiv_id":"2303.10606","n_code_links":1,"syntology":null},{"paper":null,"slug":"paco-provocation-involving-action-culture-and","title":"PACO: Provocation Involving Action, Culture, and Oppression","date":"2023-03-19","arxiv_id":"2303.12808","n_code_links":0,"syntology":null},{"paper":"/paper/an-empirical-study-of-pre-trained-language","slug":"an-empirical-study-of-pre-trained-language","title":"An Empirical Study of Pre-trained Language Models in Simple Knowledge Graph Question Answering","date":"2023-03-18","arxiv_id":"2303.10368","n_code_links":1,"syntology":null},{"paper":null,"slug":"noisyhate-benchmarking-content-moderation","title":"NoisyHate: Mining Online Human-Written Perturbations for Realistic Robustness Benchmarking of Content Moderation Models","date":"2023-03-18","arxiv_id":"2303.10430","n_code_links":0,"syntology":null},{"paper":"/paper/gadformer-an-attention-based-model-for-group","slug":"gadformer-an-attention-based-model-for-group","title":"GADformer: A Transparent Transformer Model for Group Anomaly Detection on Trajectories","date":"2023-03-17","arxiv_id":"2303.09841","n_code_links":1,"syntology":null},{"paper":"/paper/trained-on-100-million-words-and-still-in","slug":"trained-on-100-million-words-and-still-in","title":"Trained on 100 million words and still in shape: BERT meets British National Corpus","date":"2023-03-17","arxiv_id":"2303.09859","n_code_links":2,"syntology":{"ran":3,"of":7,"n_ran_checked":3,"n_instrument":0,"unverified":4,"pointer_only":7,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","official":{"repos":["ltgoslo/ltg-bert"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"block-wise-bit-compression-of-transformer","title":"Block-wise Bit-Compression of Transformer-based Models","date":"2023-03-16","arxiv_id":"2303.09184","n_code_links":0,"syntology":null},{"paper":"/paper/jump-to-conclusions-short-cutting","slug":"jump-to-conclusions-short-cutting","title":"Jump to Conclusions: Short-Cutting Transformers With Linear Transformations","date":"2023-03-16","arxiv_id":"2303.09435","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sashayd/mat"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"measuring-improvement-of-f-1-scores-in","title":"Measuring Improvement of F$_1$-Scores in Detection of Self-Admitted Technical Debt","date":"2023-03-16","arxiv_id":"2303.09617","n_code_links":0,"syntology":null},{"paper":"/paper/smartbert-a-promotion-of-dynamic-early","slug":"smartbert-a-promotion-of-dynamic-early","title":"SmartBERT: A Promotion of Dynamic Early Exiting Mechanism for Accelerating BERT Inference","date":"2023-03-16","arxiv_id":"2303.09266","n_code_links":0,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","official":null}}],"record_sha256":"1cc50d230630df420e150e8b997942e751c18f1fb4d234a42f617daca9558ca0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}