{"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/attention-dropout/papers/67","list_of":"/method/attention-dropout","method":"Attention Dropout","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":67,"pages_in_order":109,"rows_per_page":100,"rows":[6601,6700],"of":10892,"counts":{"archive_papers_tagged":10892,"with_a_code_link":4634,"where_syntology_ran_a_sample":1270,"not_listed_spam_title":0,"listed":10892,"listed_where_code_ran":1270,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1043,"every_run_a_failure_of_syntologys_instrument":227,"listed_with_a_run_with_no_instrument_failure":1043,"listed_every_run_a_failure_of_syntologys_instrument":227,"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/attention-dropout","prev":"/method/attention-dropout/papers/66","next":"/method/attention-dropout/papers/68","papers":[{"paper":null,"slug":"the-role-of-complex-nlp-in-transformers-for","title":"The Role of Complex NLP in Transformers for Text Ranking?","date":"2022-07-06","arxiv_id":"2207.02522","n_code_links":0,"syntology":null},{"paper":"/paper/betti-numbers-of-attention-graphs-is-all-you-1","slug":"betti-numbers-of-attention-graphs-is-all-you-1","title":"Betti numbers of attention graphs is all you really need","date":"2022-07-05","arxiv_id":"2207.01903","n_code_links":1,"syntology":null},{"paper":"/paper/coderl-mastering-code-generation-through","slug":"coderl-mastering-code-generation-through","title":"CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning","date":"2022-07-05","arxiv_id":"2207.01780","n_code_links":2,"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":["salesforce/coderl"],"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":"machine-learning-model-sizes-and-the","title":"Machine Learning Model Sizes and the Parameter Gap","date":"2022-07-05","arxiv_id":"2207.02852","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-can-he-predict-contrastive-focus","title":"BERT, can HE predict contrastive focus? Predicting and controlling prominence in neural TTS using a language model","date":"2022-07-04","arxiv_id":"2207.01718","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-contextual-sentence-analysis-models-to","title":"Using contextual sentence analysis models to recognize ESG concepts","date":"2022-07-04","arxiv_id":"2207.01402","n_code_links":0,"syntology":null},{"paper":"/paper/generating-repetitions-with-appropriate","slug":"generating-repetitions-with-appropriate","title":"Generating Repetitions with Appropriate Repeated Words","date":"2022-07-03","arxiv_id":"2207.00929","n_code_links":1,"syntology":null},{"paper":null,"slug":"guim-general-user-and-item-embedding-with","title":"GUIM -- General User and Item Embedding with Mixture of Representation in E-commerce","date":"2022-07-02","arxiv_id":"2207.00750","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-polyphone-bert-for-polyphone-disambiguation","title":"A Polyphone BERT for Polyphone Disambiguation in Mandarin Chinese","date":"2022-07-01","arxiv_id":"2207.12089","n_code_links":0,"syntology":null},{"paper":"/paper/is-neural-language-acquisition-similar-to","slug":"is-neural-language-acquisition-similar-to","title":"Is neural language acquisition similar to natural? A chronological probing study","date":"2022-07-01","arxiv_id":"2207.00560","n_code_links":1,"syntology":null},{"paper":"/paper/anoshift-a-distribution-shift-benchmark-for","slug":"anoshift-a-distribution-shift-benchmark-for","title":"AnoShift: A Distribution Shift Benchmark for Unsupervised Anomaly Detection","date":"2022-06-30","arxiv_id":"2206.15476","n_code_links":1,"syntology":{"ran":10,"of":13,"n_ran_checked":10,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["bit-ml/anoshift"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"compressing-pre-trained-transformers-via-low","title":"Compressing Pre-trained Transformers via Low-Bit NxM Sparsity for Natural Language Understanding","date":"2022-06-30","arxiv_id":"2206.15014","n_code_links":0,"syntology":null},{"paper":"/paper/deepspeed-inference-enabling-efficient","slug":"deepspeed-inference-enabling-efficient","title":"DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale","date":"2022-06-30","arxiv_id":"2207.00032","n_code_links":2,"syntology":null},{"paper":"/paper/gaitforemer-self-supervised-pre-training-of","slug":"gaitforemer-self-supervised-pre-training-of","title":"GaitForeMer: Self-Supervised Pre-Training of Transformers via Human Motion Forecasting for Few-Shot Gait Impairment Severity Estimation","date":"2022-06-30","arxiv_id":"2207.00106","n_code_links":1,"syntology":null},{"paper":null,"slug":"listbert-learning-to-rank-e-commerce-products","title":"ListBERT: Learning to Rank E-commerce products with Listwise BERT","date":"2022-06-30","arxiv_id":"2206.15198","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-topological-bert-transforming-attention","title":"The Topological BERT: Transforming Attention into Topology for Natural Language Processing","date":"2022-06-30","arxiv_id":"2206.15195","n_code_links":0,"syntology":null},{"paper":"/paper/two-stage-classifier-for-covid-19","slug":"two-stage-classifier-for-covid-19","title":"Two-Stage Classifier for COVID-19 Misinformation Detection Using BERT: a Study on Indonesian Tweets","date":"2022-06-30","arxiv_id":"2206.15359","n_code_links":2,"syntology":null},{"paper":"/paper/chinese-word-sense-embedding-with-sememewsd","slug":"chinese-word-sense-embedding-with-sememewsd","title":"Chinese Word Sense Embedding with SememeWSD and Synonym Set","date":"2022-06-29","arxiv_id":"2206.14388","n_code_links":2,"syntology":null},{"paper":null,"slug":"salo-an-efficient-spatial-accelerator","title":"SALO: An Efficient Spatial Accelerator Enabling Hybrid Sparse Attention Mechanisms for Long Sequences","date":"2022-06-29","arxiv_id":"2206.14550","n_code_links":0,"syntology":null},{"paper":null,"slug":"simple-and-effective-multi-sentence-tts-with","title":"Simple and Effective Multi-sentence TTS with Expressive and Coherent Prosody","date":"2022-06-29","arxiv_id":"2206.14643","n_code_links":0,"syntology":null},{"paper":null,"slug":"two-stage-covid19-classification-using-bert","title":"Two-Stage COVID19 Classification Using BERT Features","date":"2022-06-29","arxiv_id":"2206.14861","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-linguistic-feature-and-model","title":"Exploring linguistic feature and model combination for speech recognition based automatic AD detection","date":"2022-06-28","arxiv_id":"2206.13758","n_code_links":0,"syntology":null},{"paper":"/paper/robustifying-vision-transformer-without","slug":"robustifying-vision-transformer-without","title":"Robustifying Vision Transformer without Retraining from Scratch by Test-Time Class-Conditional Feature Alignment","date":"2022-06-28","arxiv_id":"2206.13951","n_code_links":1,"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":["kojima-takeshi188/cfa"],"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":"/paper/materials-transformers-language-models-for","slug":"materials-transformers-language-models-for","title":"Materials Transformers Language Models for Generative Materials Design: a benchmark study","date":"2022-06-27","arxiv_id":"2206.13578","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-multi-model-based-deep-learning-framework","title":"A multi-model-based deep learning framework for short text multiclass classification with the imbalanced and extremely small data set","date":"2022-06-24","arxiv_id":"2206.12027","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-test-for-evaluating-performance-in-human","title":"A Test for Evaluating Performance in Human-Computer Systems","date":"2022-06-24","arxiv_id":"2206.12390","n_code_links":0,"syntology":null},{"paper":null,"slug":"text-and-author-level-political-inference","title":"Text and author-level political inference using heterogeneous knowledge representations","date":"2022-06-24","arxiv_id":"2206.12293","n_code_links":0,"syntology":null},{"paper":null,"slug":"unified-bert-for-few-shot-natural-language","title":"Unified BERT for Few-shot Natural Language Understanding","date":"2022-06-24","arxiv_id":"2206.12094","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-bert-embeddings-to-model-word-1","title":"Using BERT Embeddings to Model Word Importance in Conversational Transcripts for Deaf and Hard of Hearing Users","date":"2022-06-24","arxiv_id":"2206.12368","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-disability-lens-towards-biases-in-gpt-3","title":"A Disability Lens towards Biases in GPT-3 Generated Open-Ended Languages","date":"2022-06-23","arxiv_id":"2206.11993","n_code_links":0,"syntology":null},{"paper":"/paper/bert-rankers-are-brittle-a-study-using","slug":"bert-rankers-are-brittle-a-study-using","title":"BERT Rankers are Brittle: a Study using Adversarial Document Perturbations","date":"2022-06-23","arxiv_id":"2206.11724","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-winoqueer-developing-a-benchmark-for","title":"Towards WinoQueer: Developing a Benchmark for Anti-Queer Bias in Large Language Models","date":"2022-06-23","arxiv_id":"2206.11484","n_code_links":0,"syntology":null},{"paper":null,"slug":"answer-fast-accelerating-bert-on-the-tensor","title":"Answer Fast: Accelerating BERT on the Tensor Streaming Processor","date":"2022-06-22","arxiv_id":"2206.11062","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-and-effective-training-of-language","title":"Efficient and effective training of language and graph neural network models","date":"2022-06-22","arxiv_id":"2206.10781","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-automatic-and-efficient-bert-pruning-for","title":"An Automatic and Efficient BERT Pruning for Edge AI Systems","date":"2022-06-21","arxiv_id":"2206.10461","n_code_links":0,"syntology":null},{"paper":null,"slug":"cocopie-xgen-a-full-stack-ai-oriented","title":"CoCoPIE XGen: A Full-Stack AI-Oriented Optimizing Framework","date":"2022-06-21","arxiv_id":"2206.10620","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-graph-fusion-for-language-model","title":"Knowledge Graph Fusion for Language Model Fine-tuning","date":"2022-06-21","arxiv_id":"2206.14574","n_code_links":0,"syntology":null},{"paper":null,"slug":"taphsir-towards-anaphoric-ambiguity-detection","title":"TAPHSIR: Towards AnaPHoric Ambiguity Detection and ReSolution In Requirements","date":"2022-06-21","arxiv_id":"2206.10227","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-cognitive-psychology-to-understand-gpt","title":"Using cognitive psychology to understand GPT-3","date":"2022-06-21","arxiv_id":"2206.14576","n_code_links":0,"syntology":null},{"paper":"/paper/domain-adaptive-text-classification-with","slug":"domain-adaptive-text-classification-with","title":"Domain-Adaptive Text Classification with Structured Knowledge from Unlabeled Data","date":"2022-06-20","arxiv_id":"2206.09591","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"pointer_only":6,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","official":{"repos":["hikaru-nara/dask"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/nuqmm-quantized-matmul-for-efficient","slug":"nuqmm-quantized-matmul-for-efficient","title":"LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models","date":"2022-06-20","arxiv_id":"2206.09557","n_code_links":2,"syntology":null},{"paper":"/paper/argumentative-text-generation-in-economic","slug":"argumentative-text-generation-in-economic","title":"Argumentative Text Generation in Economic Domain","date":"2022-06-18","arxiv_id":"2206.09251","n_code_links":1,"syntology":null},{"paper":null,"slug":"automatic-summarization-of-russian-texts","title":"Automatic Summarization of Russian Texts: Comparison of Extractive and Abstractive Methods","date":"2022-06-18","arxiv_id":"2206.09253","n_code_links":0,"syntology":null},{"paper":null,"slug":"ruarg-2022-argument-mining-evaluation","title":"RuArg-2022: Argument Mining Evaluation","date":"2022-06-18","arxiv_id":"2206.09249","n_code_links":0,"syntology":null},{"paper":null,"slug":"bits-pilani-at-hinglisheval-quality","title":"BITS Pilani at HinglishEval: Quality Evaluation for Code-Mixed Hinglish Text Using Transformers","date":"2022-06-17","arxiv_id":"2206.08680","n_code_links":0,"syntology":null},{"paper":"/paper/sima-simple-softmax-free-attention-for-vision","slug":"sima-simple-softmax-free-attention-for-vision","title":"SimA: Simple Softmax-free Attention for Vision Transformers","date":"2022-06-17","arxiv_id":"2206.08898","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ucdvision/sima"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/video-sparse-transformer-with-attention","slug":"video-sparse-transformer-with-attention","title":"Video Sparse Transformer With Attention-Guided Memory for Video Object Detection","date":"2022-06-17","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"an-open-domain-qa-system-for-e-governance","title":"An Open-Domain QA System for e-Governance","date":"2022-06-16","arxiv_id":"2206.08046","n_code_links":0,"syntology":null},{"paper":null,"slug":"alexa-teacher-model-pretraining-and","title":"Alexa Teacher Model: Pretraining and Distilling Multi-Billion-Parameter Encoders for Natural Language Understanding Systems","date":"2022-06-15","arxiv_id":"2206.07808","n_code_links":0,"syntology":null},{"paper":"/paper/detecting-harmful-online-conversational","slug":"detecting-harmful-online-conversational","title":"Detecting Harmful Online Conversational Content towards LGBTQIA+ Individuals","date":"2022-06-15","arxiv_id":"2207.10032","n_code_links":1,"syntology":null},{"paper":null,"slug":"estimating-confidence-of-predictions-of","title":"Estimating Confidence of Predictions of Individual Classifiers and Their Ensembles for the Genre Classification Task","date":"2022-06-15","arxiv_id":"2206.07427","n_code_links":0,"syntology":null},{"paper":"/paper/natgen-generative-pre-training-by","slug":"natgen-generative-pre-training-by","title":"NatGen: Generative pre-training by \"Naturalizing\" source code","date":"2022-06-15","arxiv_id":"2206.07585","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["saikat107/natgen"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"rdu-a-region-based-approach-to-form-style","title":"RDU: A Region-based Approach to Form-style Document Understanding","date":"2022-06-14","arxiv_id":"2206.06890","n_code_links":0,"syntology":null},{"paper":"/paper/sbert-studies-meaning-representations","slug":"sbert-studies-meaning-representations","title":"SBERT studies Meaning Representations: Decomposing Sentence Embeddings into Explainable Semantic Features","date":"2022-06-14","arxiv_id":"2206.07023","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":6,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["flipz357/S3BERT"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/lst-ladder-side-tuning-for-parameter-and","slug":"lst-ladder-side-tuning-for-parameter-and","title":"LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learning","date":"2022-06-13","arxiv_id":"2206.06522","n_code_links":2,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":3,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ylsung/ladder-side-tuning"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/optimal-clipping-and-magnitude-aware","slug":"optimal-clipping-and-magnitude-aware","title":"Optimal Clipping and Magnitude-aware Differentiation for Improved Quantization-aware Training","date":"2022-06-13","arxiv_id":"2206.06501","n_code_links":1,"syntology":{"ran":9,"of":9,"n_ran_checked":9,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"transition-based-abstract-meaning","title":"Transition-based Abstract Meaning Representation Parsing with Contextual Embeddings","date":"2022-06-13","arxiv_id":"2206.06229","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-dataset-and-benchmark-for-automatically","title":"From Human Days to Machine Seconds: Automatically Answering and Generating Machine Learning Final Exams","date":"2022-06-11","arxiv_id":"2206.05442","n_code_links":0,"syntology":null},{"paper":"/paper/comparative-snippet-generation-1","slug":"comparative-snippet-generation-1","title":"Comparative Snippet Generation","date":"2022-06-11","arxiv_id":"2206.05473","n_code_links":1,"syntology":null},{"paper":"/paper/putting-gpt-3-s-creativity-to-the-alternative","slug":"putting-gpt-3-s-creativity-to-the-alternative","title":"Putting GPT-3's Creativity to the (Alternative Uses) Test","date":"2022-06-10","arxiv_id":"2206.08932","n_code_links":1,"syntology":null},{"paper":"/paper/beyond-the-imitation-game-quantifying-and","slug":"beyond-the-imitation-game-quantifying-and","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","date":"2022-06-09","arxiv_id":"2206.04615","n_code_links":6,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 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) · 0 unverified","official":{"repos":["google/BIG-bench"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"joint-encoder-decoder-self-supervised-pre","title":"Joint Encoder-Decoder Self-Supervised Pre-training for ASR","date":"2022-06-09","arxiv_id":"2206.04465","n_code_links":0,"syntology":null},{"paper":"/paper/traditional-and-context-specific-spam","slug":"traditional-and-context-specific-spam","title":"Traditional and context-specific spam detection in low resource settings","date":"2022-06-09","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/abstraction-not-memory-bert-and-the-english","slug":"abstraction-not-memory-bert-and-the-english","title":"Abstraction not Memory: BERT and the English Article System","date":"2022-06-08","arxiv_id":"2206.04184","n_code_links":1,"syntology":null},{"paper":"/paper/scideberta-learning-deberta-for-science","slug":"scideberta-learning-deberta-for-science","title":"SciDeBERTa: Learning DeBERTa for Science Technology Documents and Fine-Tuning Information Extraction Tasks","date":"2022-06-08","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/always-keep-your-target-in-mind-studying-1","slug":"always-keep-your-target-in-mind-studying-1","title":"Always Keep your Target in Mind: Studying Semantics and Improving Performance of Neural Lexical Substitution","date":"2022-06-07","arxiv_id":"2206.11815","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-empirical-study-of-iot-security-aspects-at","title":"An Empirical Study of IoT Security Aspects at Sentence-Level in Developer Textual Discussions","date":"2022-06-07","arxiv_id":"2206.03079","n_code_links":0,"syntology":null},{"paper":null,"slug":"dynamar-dynamic-prompt-with-mask-token","title":"DynaMaR: Dynamic Prompt with Mask Token Representation","date":"2022-06-07","arxiv_id":"2206.02982","n_code_links":0,"syntology":null},{"paper":null,"slug":"ochadai-at-semeval-2022-task-2-adversarial","title":"OCHADAI at SemEval-2022 Task 2: Adversarial Training for Multilingual Idiomaticity Detection","date":"2022-06-07","arxiv_id":"2206.03025","n_code_links":0,"syntology":null},{"paper":"/paper/a-computational-psycholinguistic-evaluation","slug":"a-computational-psycholinguistic-evaluation","title":"A computational psycholinguistic evaluation of the syntactic abilities of Galician BERT models at the interface of dependency resolution and training time","date":"2022-06-06","arxiv_id":"2206.02440","n_code_links":1,"syntology":null},{"paper":"/paper/on-the-advance-of-making-language-models","slug":"on-the-advance-of-making-language-models","title":"Making Large Language Models Better Reasoners with Step-Aware Verifier","date":"2022-06-06","arxiv_id":"2206.02336","n_code_links":0,"syntology":null},{"paper":null,"slug":"spam-detection-using-bert","title":"Spam Detection Using BERT","date":"2022-06-06","arxiv_id":"2206.02443","n_code_links":0,"syntology":null},{"paper":"/paper/sports-re-id-improving-re-identification-of","slug":"sports-re-id-improving-re-identification-of","title":"Sports Re-ID: Improving Re-Identification Of Players In Broadcast Videos Of Team Sports","date":"2022-06-06","arxiv_id":"2206.02373","n_code_links":1,"syntology":null},{"paper":"/paper/what-do-tokens-know-about-their-characters-1","slug":"what-do-tokens-know-about-their-characters-1","title":"What do tokens know about their characters and how do they know it?","date":"2022-06-06","arxiv_id":"2206.02608","n_code_links":1,"syntology":null},{"paper":null,"slug":"sentiment-analysis-of-online-travel-reviews","title":"Sentiment Analysis of Online Travel Reviews Based on Capsule Network and Sentiment Lexicon","date":"2022-06-05","arxiv_id":"2206.02160","n_code_links":0,"syntology":null},{"paper":null,"slug":"speech-detection-task-against-asian-hate-bert","title":"Speech Detection Task Against Asian Hate: BERT the Central, While Data-Centric Studies the Crucial","date":"2022-06-05","arxiv_id":"2206.02114","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparing-performance-of-different","title":"Comparing Performance of Different Linguistically-Backed Word Embeddings for Cyberbullying Detection","date":"2022-06-04","arxiv_id":"2206.01950","n_code_links":0,"syntology":null},{"paper":"/paper/extreme-compression-for-pre-trained","slug":"extreme-compression-for-pre-trained","title":"Extreme Compression for Pre-trained Transformers Made Simple and Efficient","date":"2022-06-04","arxiv_id":"2206.01859","n_code_links":1,"syntology":null},{"paper":"/paper/zeroquant-efficient-and-affordable-post","slug":"zeroquant-efficient-and-affordable-post","title":"ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers","date":"2022-06-04","arxiv_id":"2206.01861","n_code_links":3,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["microsoft/DeepSpeed"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"paper":null,"slug":"automatic-generation-of-programming-exercises-1","title":"Automatic Generation of Programming Exercises and Code Explanations using Large Language Models","date":"2022-06-03","arxiv_id":"2206.11861","n_code_links":0,"syntology":null},{"paper":null,"slug":"differentially-private-model-compression","title":"Differentially Private Model Compression","date":"2022-06-03","arxiv_id":"2206.01838","n_code_links":0,"syntology":null},{"paper":null,"slug":"extracting-similar-questions-from-naturally","title":"Extracting Similar Questions From Naturally-occurring Business Conversations","date":"2022-06-03","arxiv_id":"2206.01585","n_code_links":0,"syntology":null},{"paper":"/paper/tce-at-qur-an-qa-2022-arabic-language","slug":"tce-at-qur-an-qa-2022-arabic-language","title":"TCE at Qur'an QA 2022: Arabic Language Question Answering Over Holy Qur'an Using a Post-Processed Ensemble of BERT-based Models","date":"2022-06-03","arxiv_id":"2206.01550","n_code_links":1,"syntology":null},{"paper":"/paper/decentralized-training-of-foundation-models","slug":"decentralized-training-of-foundation-models","title":"Decentralized Training of Foundation Models in Heterogeneous Environments","date":"2022-06-02","arxiv_id":"2206.01288","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["DS3Lab/DT-FM"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"mmtm-multi-tasking-multi-decoder-transformer","title":"MMTM: Multi-Tasking Multi-Decoder Transformer for Math Word Problems","date":"2022-06-02","arxiv_id":"2206.01268","n_code_links":0,"syntology":null},{"paper":null,"slug":"assessing-group-level-gender-bias-in","title":"Assessing Group-level Gender Bias in Professional Evaluations: The Case of Medical Student End-of-Shift Feedback","date":"2022-06-01","arxiv_id":"2206.00234","n_code_links":0,"syntology":null},{"paper":"/paper/bert-sort-a-zero-shot-mlm-semantic-encoder-on","slug":"bert-sort-a-zero-shot-mlm-semantic-encoder-on","title":"BERT-Sort: A Zero-shot MLM Semantic Encoder on Ordinal Features for AutoML","date":"2022-06-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"order-sensitive-shapley-values-for-evaluating","title":"Order-sensitive Shapley Values for Evaluating Conceptual Soundness of NLP Models","date":"2022-06-01","arxiv_id":"2206.00192","n_code_links":0,"syntology":null},{"paper":null,"slug":"romantic-computing","title":"Romantic-Computing","date":"2022-06-01","arxiv_id":"2206.11864","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-unified-framework-for-emotion","title":"A Unified Framework for Emotion Identification and Generation in Dialogues","date":"2022-05-31","arxiv_id":"2205.15513","n_code_links":0,"syntology":null},{"paper":"/paper/codeattack-code-based-adversarial-attacks-for","slug":"codeattack-code-based-adversarial-attacks-for","title":"CodeAttack: Code-Based Adversarial Attacks for Pre-trained Programming Language Models","date":"2022-05-31","arxiv_id":"2206.00052","n_code_links":2,"syntology":null},{"paper":null,"slug":"knowledge-graph-deep-learning-a-case-study-in","title":"Knowledge Graph - Deep Learning: A Case Study in Question Answering in Aviation Safety Domain","date":"2022-05-31","arxiv_id":"2205.15952","n_code_links":0,"syntology":null},{"paper":"/paper/automatic-short-math-answer-grading-via-in","slug":"automatic-short-math-answer-grading-via-in","title":"Automatic Short Math Answer Grading via In-context Meta-learning","date":"2022-05-30","arxiv_id":"2205.15219","n_code_links":1,"syntology":null},{"paper":"/paper/billions-of-parameters-are-worth-more-than-in","slug":"billions-of-parameters-are-worth-more-than-in","title":"Billions of Parameters Are Worth More Than In-domain Training Data: A case study in the Legal Case Entailment Task","date":"2022-05-30","arxiv_id":"2205.15172","n_code_links":1,"syntology":null},{"paper":"/paper/e2s2-encoding-enhanced-sequence-to-sequence","slug":"e2s2-encoding-enhanced-sequence-to-sequence","title":"E2S2: Encoding-Enhanced Sequence-to-Sequence Pretraining for Language Understanding and Generation","date":"2022-05-30","arxiv_id":"2205.14912","n_code_links":1,"syntology":null},{"paper":"/paper/multi-agent-reinforcement-learning-is-a","slug":"multi-agent-reinforcement-learning-is-a","title":"Multi-Agent Reinforcement Learning is a Sequence Modeling Problem","date":"2022-05-30","arxiv_id":"2205.14953","n_code_links":1,"syntology":null},{"paper":"/paper/prompting-electra-few-shot-learning-with","slug":"prompting-electra-few-shot-learning-with","title":"Prompting ELECTRA: Few-Shot Learning with Discriminative Pre-Trained Models","date":"2022-05-30","arxiv_id":"2205.15223","n_code_links":1,"syntology":null},{"paper":null,"slug":"covid-19-literature-mining-and-retrieval","title":"COVID-19 Literature Mining and Retrieval using Text Mining Approaches","date":"2022-05-29","arxiv_id":"2205.14781","n_code_links":0,"syntology":null},{"paper":"/paper/cped-a-large-scale-chinese-personalized-and-1","slug":"cped-a-large-scale-chinese-personalized-and-1","title":"CPED: A Large-Scale Chinese Personalized and Emotional Dialogue Dataset for Conversational AI","date":"2022-05-29","arxiv_id":"2205.14727","n_code_links":1,"syntology":null},{"paper":null,"slug":"micro-expression-recognition-based-on","title":"Micro-Expression Recognition Based on Attribute Information Embedding and Cross-modal Contrastive Learning","date":"2022-05-29","arxiv_id":"2205.14643","n_code_links":0,"syntology":null}],"record_sha256":"c45acc2b29053b15a02f3b73eac9945377e1cc2a6a82bee3b1982b0e5c05bad3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}