{"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":"/task/language-modelling/papers/59","list_of":"/task/language-modelling","task":"Language Modelling","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":59,"pages_in_order":177,"rows_per_page":100,"rows":[5801,5900],"of":17610,"counts":{"archive_papers_tagged":17610,"with_a_code_link":7012,"where_syntology_ran_a_sample":2428,"not_listed_spam_title":0,"listed":17610,"listed_where_code_ran":2428,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2027,"every_run_a_failure_of_syntologys_instrument":401,"listed_with_a_run_with_no_instrument_failure":2027,"listed_every_run_a_failure_of_syntologys_instrument":401,"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":"/task/language-modelling","prev":"/task/language-modelling/papers/58","next":"/task/language-modelling/papers/60","papers":[{"url":"/paper/visual-semantics-allow-for-textual-reasoning-1","slug":"visual-semantics-allow-for-textual-reasoning-1","title":"Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition","date":"2021-12-24","arxiv_id":"2112.12916","repositories_listed":1,"syntology":null},{"url":"/paper/atm-an-uncertainty-aware-active-self-training","slug":"atm-an-uncertainty-aware-active-self-training","title":"AcTune: Uncertainty-aware Active Self-Training for Semi-Supervised Active Learning with Pretrained Language Models","date":"2021-12-16","arxiv_id":"2112.08787","repositories_listed":1,"syntology":null},{"url":"/paper/clin-x-pre-trained-language-models-and-a","slug":"clin-x-pre-trained-language-models-and-a","title":"CLIN-X: pre-trained language models and a study on cross-task transfer for concept extraction in the clinical domain","date":"2021-12-16","arxiv_id":"2112.08754","repositories_listed":1,"syntology":null},{"url":"/paper/commonsense-knowledge-augmented-pretrained-1","slug":"commonsense-knowledge-augmented-pretrained-1","title":"Knowledge-Augmented Language Models for Cause-Effect Relation Classification","date":"2021-12-16","arxiv_id":"2112.08615","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/commonsense-knowledge-augmented-pretrained-1#ran","syntology_url":"https://syntology.ai/paper/2112.08615","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.08615"}},"official":{"repos":["phosseini/causal-reasoning"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/efficient-hierarchical-domain-adaptation-for","slug":"efficient-hierarchical-domain-adaptation-for","title":"Efficient Hierarchical Domain Adaptation for Pretrained Language Models","date":"2021-12-16","arxiv_id":"2112.08786","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-learning-for-speech-1","slug":"self-supervised-learning-for-speech-1","title":"Self-Supervised Learning for speech recognition with Intermediate layer supervision","date":"2021-12-16","arxiv_id":"2112.08778","repositories_listed":1,"syntology":null},{"url":"/paper/unirex-a-unified-learning-framework-for","slug":"unirex-a-unified-learning-framework-for","title":"UNIREX: A Unified Learning Framework for Language Model Rationale Extraction","date":"2021-12-16","arxiv_id":"2112.08802","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 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; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unirex-a-unified-learning-framework-for#ran","syntology_url":"https://syntology.ai/paper/2112.08802","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.08802"}},"official":{"repos":["facebookresearch/unirex"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-conversational-recommendation-1","slug":"improving-conversational-recommendation-1","title":"Improving Conversational Recommendation Systems' Quality with Context-Aware Item Meta Information","date":"2021-12-15","arxiv_id":"2112.08140","repositories_listed":1,"syntology":null},{"url":"/paper/oracle-linguistic-graphs-complement-a","slug":"oracle-linguistic-graphs-complement-a","title":"Linguistic Frameworks Go Toe-to-Toe at Neuro-Symbolic Language Modeling","date":"2021-12-15","arxiv_id":"2112.07874","repositories_listed":1,"syntology":null},{"url":"/paper/spts-single-point-text-spotting","slug":"spts-single-point-text-spotting","title":"SPTS: Single-Point Text Spotting","date":"2021-12-15","arxiv_id":"2112.07917","repositories_listed":1,"syntology":null},{"url":"/paper/value-retrieval-with-arbitrary-queries-for","slug":"value-retrieval-with-arbitrary-queries-for","title":"Value Retrieval with Arbitrary Queries for Form-like Documents","date":"2021-12-15","arxiv_id":"2112.07820","repositories_listed":1,"syntology":null},{"url":"/paper/deciphering-antibody-affinity-maturation-with","slug":"deciphering-antibody-affinity-maturation-with","title":"Deciphering antibody affinity maturation with language models and weakly supervised learning","date":"2021-12-14","arxiv_id":"2112.07782","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":1,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 1 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","sample_list":"/paper/deciphering-antibody-affinity-maturation-with#ran","syntology_url":"https://syntology.ai/paper/2112.07782","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.07782"}},"official":null}},{"url":"/paper/step-unrolled-denoising-autoencoders-for-text-1","slug":"step-unrolled-denoising-autoencoders-for-text-1","title":"Step-unrolled Denoising Autoencoders for Text Generation","date":"2021-12-13","arxiv_id":"2112.06749","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/step-unrolled-denoising-autoencoders-for-text-1#ran","syntology_url":"https://syntology.ai/paper/2112.06749","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.06749"}},"official":null}},{"url":"/paper/magma-multimodal-augmentation-of-generative","slug":"magma-multimodal-augmentation-of-generative","title":"MAGMA -- Multimodal Augmentation of Generative Models through Adapter-based Finetuning","date":"2021-12-09","arxiv_id":"2112.05253","repositories_listed":1,"syntology":{"n":15,"n_ran":10,"n_constructed":0,"n_ran_checked":6,"n_instrument":4,"n_unverified":5,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/magma-multimodal-augmentation-of-generative#ran","syntology_url":"https://syntology.ai/paper/2112.05253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.05253"}},"official":{"repos":["Aleph-Alpha/magma"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/jaber-junior-arabic-bert","slug":"jaber-junior-arabic-bert","title":"JABER and SABER: Junior and Senior Arabic BERt","date":"2021-12-08","arxiv_id":"2112.04329","repositories_listed":1,"syntology":null},{"url":"/paper/mlp-architectures-for-vision-and-language","slug":"mlp-architectures-for-vision-and-language","title":"MLP Architectures for Vision-and-Language Modeling: An Empirical Study","date":"2021-12-08","arxiv_id":"2112.04453","repositories_listed":1,"syntology":null},{"url":"/paper/prompting-visual-language-models-for","slug":"prompting-visual-language-models-for","title":"Prompting Visual-Language Models for Efficient Video Understanding","date":"2021-12-08","arxiv_id":"2112.04478","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"5 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; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/prompting-visual-language-models-for#ran","syntology_url":"https://syntology.ai/paper/2112.04478","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.04478"}},"official":{"repos":["ju-chen/Efficient-Prompt"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/zero-shot-recommendation-as-language-modeling","slug":"zero-shot-recommendation-as-language-modeling","title":"Zero-Shot Recommendation as Language Modeling","date":"2021-12-08","arxiv_id":"2112.04184","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-adaptive-distributed-training-on","slug":"end-to-end-adaptive-distributed-training-on","title":"End-to-end Adaptive Distributed Training on PaddlePaddle","date":"2021-12-06","arxiv_id":"2112.02752","repositories_listed":1,"syntology":null},{"url":"/paper/fleetx","slug":"fleetx","title":"FleetX","date":"2021-12-06","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/keeping-it-simple-language-models-can-learn","slug":"keeping-it-simple-language-models-can-learn","title":"Keeping it Simple: Language Models can learn Complex Molecular Distributions","date":"2021-12-06","arxiv_id":"2112.03041","repositories_listed":1,"syntology":null},{"url":"/paper/achieving-forgetting-prevention-and-knowledge-1","slug":"achieving-forgetting-prevention-and-knowledge-1","title":"Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning","date":"2021-12-05","arxiv_id":"2112.02706","repositories_listed":1,"syntology":null},{"url":"/paper/causal-distillation-for-language-models","slug":"causal-distillation-for-language-models","title":"Causal Distillation for Language Models","date":"2021-12-05","arxiv_id":"2112.02505","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_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) · 1 unverified","sample_list":"/paper/causal-distillation-for-language-models#ran","syntology_url":"https://syntology.ai/paper/2112.02505","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.02505"}},"official":{"repos":["frankaging/Causal-Distill"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/dibert-dependency-injected-bidirectional","slug":"dibert-dependency-injected-bidirectional","title":"DIBERT: Dependency Injected Bidirectional Encoder Representations from Transformers","date":"2021-12-05","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/probing-linguistic-information-for-logical","slug":"probing-linguistic-information-for-logical","title":"Probing Linguistic Information For Logical Inference In Pre-trained Language Models","date":"2021-12-03","arxiv_id":"2112.01753","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/probing-linguistic-information-for-logical#ran","syntology_url":"https://syntology.ai/paper/2112.01753","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.01753"}},"official":{"repos":["eric11eca/inference-information-probing"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/denseclip-language-guided-dense-prediction","slug":"denseclip-language-guided-dense-prediction","title":"DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting","date":"2021-12-02","arxiv_id":"2112.01518","repositories_listed":1,"syntology":null},{"url":"/paper/dkplm-decomposable-knowledge-enhanced-pre","slug":"dkplm-decomposable-knowledge-enhanced-pre","title":"DKPLM: Decomposable Knowledge-enhanced Pre-trained Language Model for Natural Language Understanding","date":"2021-12-02","arxiv_id":"2112.01047","repositories_listed":1,"syntology":null},{"url":"/paper/infolm-a-new-metric-to-evaluate-summarization","slug":"infolm-a-new-metric-to-evaluate-summarization","title":"InfoLM: A New Metric to Evaluate Summarization & Data2Text Generation","date":"2021-12-02","arxiv_id":"2112.01589","repositories_listed":1,"syntology":null},{"url":"/paper/pixelated-butterfly-simple-and-efficient-1","slug":"pixelated-butterfly-simple-and-efficient-1","title":"Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models","date":"2021-11-30","arxiv_id":"2112.00029","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"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","sample_list":"/paper/pixelated-butterfly-simple-and-efficient-1#ran","syntology_url":"https://syntology.ai/paper/2112.00029","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.00029"}},"official":{"repos":["HazyResearch/pixelfly"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/a-simple-long-tailed-recognition-baseline-via","slug":"a-simple-long-tailed-recognition-baseline-via","title":"A Simple Long-Tailed Recognition Baseline via Vision-Language Model","date":"2021-11-29","arxiv_id":"2111.14745","repositories_listed":1,"syntology":null},{"url":"/paper/linguistic-knowledge-in-data-augmentation-for","slug":"linguistic-knowledge-in-data-augmentation-for","title":"Linguistic Knowledge in Data Augmentation for Natural Language Processing: An Example on Chinese Question Matching","date":"2021-11-29","arxiv_id":"2111.14709","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-image-to-text-generation-for-visual","slug":"zero-shot-image-to-text-generation-for-visual","title":"ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic","date":"2021-11-29","arxiv_id":"2111.14447","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"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) · 0 unverified","sample_list":"/paper/zero-shot-image-to-text-generation-for-visual#ran","syntology_url":"https://syntology.ai/paper/2111.14447","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.14447"}},"official":{"repos":["yoadtew/zero-shot-image-to-text"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/fasttrees-parallel-latent-tree-induction-for","slug":"fasttrees-parallel-latent-tree-induction-for","title":"FastTrees: Parallel Latent Tree-Induction for Faster Sequence Encoding","date":"2021-11-28","arxiv_id":"2111.14031","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-cross-lingual-transfer-in-legal","slug":"zero-shot-cross-lingual-transfer-in-legal","title":"Zero-Shot Cross-Lingual Transfer in Legal Domain Using Transformer Models","date":"2021-11-28","arxiv_id":"2111.14192","repositories_listed":1,"syntology":null},{"url":"/paper/predict-prevent-and-evaluate-disentangled","slug":"predict-prevent-and-evaluate-disentangled","title":"Predict, Prevent, and Evaluate: Disentangled Text-Driven Image Manipulation Empowered by Pre-Trained Vision-Language Model","date":"2021-11-26","arxiv_id":"2111.13333","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-the-robustness-of-retrieval","slug":"evaluating-the-robustness-of-retrieval","title":"Evaluating the Robustness of Retrieval Pipelines with Query Variation Generators","date":"2021-11-25","arxiv_id":"2111.13057","repositories_listed":1,"syntology":null},{"url":"/paper/crossing-the-format-boundary-of-text-and","slug":"crossing-the-format-boundary-of-text-and","title":"UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modeling","date":"2021-11-23","arxiv_id":"2111.12085","repositories_listed":1,"syntology":{"n":15,"n_ran":14,"n_constructed":0,"n_ran_checked":9,"n_instrument":5,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":5,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/crossing-the-format-boundary-of-text-and#ran","syntology_url":"https://syntology.ai/paper/2111.12085","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.12085"}},"official":{"repos":["microsoft/UniTAB"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/romanian-speech-recognition-experiments-from","slug":"romanian-speech-recognition-experiments-from","title":"Romanian Speech Recognition Experiments from the ROBIN Project","date":"2021-11-23","arxiv_id":"2111.12028","repositories_listed":1,"syntology":null},{"url":"/paper/using-language-model-to-bootstrap-human","slug":"using-language-model-to-bootstrap-human","title":"Using Language Model to Bootstrap Human Activity Recognition Ambient Sensors Based in Smart Homes","date":"2021-11-23","arxiv_id":"2111.12158","repositories_listed":1,"syntology":null},{"url":"/paper/knowledge-based-multilingual-language-model-1","slug":"knowledge-based-multilingual-language-model-1","title":"Enhancing Multilingual Language Model with Massive Multilingual Knowledge Triples","date":"2021-11-22","arxiv_id":"2111.10962","repositories_listed":1,"syntology":null},{"url":"/paper/robertuito-a-pre-trained-language-model-for","slug":"robertuito-a-pre-trained-language-model-for","title":"RoBERTuito: a pre-trained language model for social media text in Spanish","date":"2021-11-18","arxiv_id":"2111.09453","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_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) · 3 unverified","sample_list":"/paper/robertuito-a-pre-trained-language-model-for#ran","syntology_url":"https://syntology.ai/paper/2111.09453","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.09453"}},"official":{"repos":["pysentimiento/robertuito"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/emscore-evaluating-video-captioning-via","slug":"emscore-evaluating-video-captioning-via","title":"EMScore: Evaluating Video Captioning via Coarse-Grained and Fine-Grained Embedding Matching","date":"2021-11-17","arxiv_id":"2111.08919","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/emscore-evaluating-video-captioning-via#ran","syntology_url":"https://syntology.ai/paper/2111.08919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.08919"}},"official":{"repos":["shiyaya/emscore"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/integrated-semantic-and-phonetic-post-1","slug":"integrated-semantic-and-phonetic-post-1","title":"Integrated Semantic and Phonetic Post-correction for Chinese Speech Recognition","date":"2021-11-16","arxiv_id":"2111.08400","repositories_listed":1,"syntology":null},{"url":"/paper/interpreting-language-models-through","slug":"interpreting-language-models-through","title":"Interpreting Language Models Through Knowledge Graph Extraction","date":"2021-11-16","arxiv_id":"2111.08546","repositories_listed":1,"syntology":null},{"url":"/paper/meeting-summarization-with-pre-training-and","slug":"meeting-summarization-with-pre-training-and","title":"Meeting Summarization with Pre-training and Clustering Methods","date":"2021-11-16","arxiv_id":"2111.08210","repositories_listed":1,"syntology":null},{"url":"/paper/xlm-e-cross-lingual-language-model-pre-1","slug":"xlm-e-cross-lingual-language-model-pre-1","title":"XLM-E: Cross-lingual Language Model Pre-training via ELECTRA","date":"2021-11-16","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/automated-audio-captioning-by-fine-tuning","slug":"automated-audio-captioning-by-fine-tuning","title":"AUTOMATED AUDIO CAPTIONING BY FINE-TUNING BART WITH AUDIOSET TAGS","date":"2021-11-15","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/semantically-grounded-object-matching-for","slug":"semantically-grounded-object-matching-for","title":"Semantically Grounded Object Matching for Robust Robotic Scene Rearrangement","date":"2021-11-15","arxiv_id":"2111.07975","repositories_listed":1,"syntology":null},{"url":"/paper/machine-in-the-loop-rewriting-for-creative","slug":"machine-in-the-loop-rewriting-for-creative","title":"Machine-in-the-Loop Rewriting for Creative Image Captioning","date":"2021-11-07","arxiv_id":"2111.04193","repositories_listed":1,"syntology":null},{"url":"/paper/nlp-from-scratch-without-large-scale","slug":"nlp-from-scratch-without-large-scale","title":"NLP From Scratch Without Large-Scale Pretraining: A Simple and Efficient Framework","date":"2021-11-07","arxiv_id":"2111.04130","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_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) · 1 unverified","sample_list":"/paper/nlp-from-scratch-without-large-scale#ran","syntology_url":"https://syntology.ai/paper/2111.04130","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.04130"}},"official":{"repos":["yaoxingcheng/TLM"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/tip-adapter-training-free-clip-adapter-for","slug":"tip-adapter-training-free-clip-adapter-for","title":"Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling","date":"2021-11-06","arxiv_id":"2111.03930","repositories_listed":1,"syntology":null},{"url":"/paper/lexically-aware-semi-supervised-learning-for","slug":"lexically-aware-semi-supervised-learning-for","title":"Lexically Aware Semi-Supervised Learning for OCR Post-Correction","date":"2021-11-04","arxiv_id":"2111.02622","repositories_listed":1,"syntology":null},{"url":"/paper/the-neural-architecture-of-language","slug":"the-neural-architecture-of-language","title":"The neural architecture of language: Integrative modeling converges on predictive processing","date":"2021-11-04","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/an-explanation-of-in-context-learning-as-1","slug":"an-explanation-of-in-context-learning-as-1","title":"An Explanation of In-context Learning as Implicit Bayesian Inference","date":"2021-11-03","arxiv_id":"2111.02080","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/an-explanation-of-in-context-learning-as-1#ran","syntology_url":"https://syntology.ai/paper/2111.02080","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.02080"}},"official":{"repos":["p-lambda/incontext-learning"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/the-klarna-product-page-dataset-a","slug":"the-klarna-product-page-dataset-a","title":"The Klarna Product Page Dataset: Web Element Nomination with Graph Neural Networks and Large Language Models","date":"2021-11-03","arxiv_id":"2111.02168","repositories_listed":1,"syntology":null},{"url":"/paper/a-model-of-cross-lingual-knowledge-grounded","slug":"a-model-of-cross-lingual-knowledge-grounded","title":"A Model of Cross-Lingual Knowledge-Grounded Response Generation for Open-Domain Dialogue Systems","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-pilot-study-for-bert-language-modelling-and","slug":"a-pilot-study-for-bert-language-modelling-and","title":"A Pilot Study for BERT Language Modelling and Morphological Analysis for Ancient and Medieval Greek","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/aesop-paraphrase-generation-with-adaptive","slug":"aesop-paraphrase-generation-with-adaptive","title":"AESOP: Paraphrase Generation with Adaptive Syntactic Control","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/arabictransformer-efficient-large-arabic","slug":"arabictransformer-efficient-large-arabic","title":"ArabicTransformer: Efficient Large Arabic Language Model with Funnel Transformer and ELECTRA Objective","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/attentionrank-unsupervised-keyphrase","slug":"attentionrank-unsupervised-keyphrase","title":"AttentionRank: Unsupervised Keyphrase Extraction using Self and Cross Attentions","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/casting-the-same-sentiment-classification","slug":"casting-the-same-sentiment-classification","title":"Casting the Same Sentiment Classification Problem","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/dilbert-customized-pre-training-for-domain-1","slug":"dilbert-customized-pre-training-for-domain-1","title":"DILBERT: Customized Pre-Training for Domain Adaptation with Category Shift, with an Application to Aspect Extraction","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/distilling-relation-embeddings-from","slug":"distilling-relation-embeddings-from","title":"Distilling Relation Embeddings from Pretrained Language Models","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/distilling-word-meaning-in-context-from-pre","slug":"distilling-word-meaning-in-context-from-pre","title":"Distilling Word Meaning in Context from Pre-trained Language Models","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/effective-use-of-graph-convolution-network-1","slug":"effective-use-of-graph-convolution-network-1","title":"Effective Use of Graph Convolution Network and Contextual Sub-Tree for Commodity News Event Extraction","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/exploring-multitask-learning-for-low-resource-1","slug":"exploring-multitask-learning-for-low-resource-1","title":"Exploring Multitask Learning for Low-Resource Abstractive Summarization","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/hotter-hierarchical-optimal-topic-transport","slug":"hotter-hierarchical-optimal-topic-transport","title":"HOTTER: Hierarchical Optimal Topic Transport with Explanatory Context Representations","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/hyperparameter-power-impact-in-transformer","slug":"hyperparameter-power-impact-in-transformer","title":"Hyperparameter Power Impact in Transformer Language Model Training","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/intrinsic-evaluation-of-language-models-for","slug":"intrinsic-evaluation-of-language-models-for","title":"Intrinsic evaluation of language models for code-switching","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/it-doesnt-look-good-for-a-date-transforming","slug":"it-doesnt-look-good-for-a-date-transforming","title":"“It doesn’t look good for a date”: Transforming Critiques into Preferences for Conversational Recommendation Systems","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/klmo-knowledge-graph-enhanced-pretrained","slug":"klmo-knowledge-graph-enhanced-pretrained","title":"KLMo: Knowledge Graph Enhanced Pretrained Language Model with Fine-Grained Relationships","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/less-is-more-pretrain-a-strong-siamese","slug":"less-is-more-pretrain-a-strong-siamese","title":"Less is More: Pretrain a Strong Siamese Encoder for Dense Text Retrieval Using a Weak Decoder","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/openframing-open-sourced-tool-for","slug":"openframing-open-sourced-tool-for","title":"OpenFraming: Open-sourced Tool for Computational Framing Analysis of Multilingual Data","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/perspeechnorm-a-persian-toolkit-for-speech","slug":"perspeechnorm-a-persian-toolkit-for-speech","title":"ParsiNorm: A Persian Toolkit for Speech Processing Normalization","date":"2021-11-01","arxiv_id":"2111.03470","repositories_listed":1,"syntology":null},{"url":"/paper/prosper-probing-human-and-neural-network","slug":"prosper-probing-human-and-neural-network","title":"ProSPer: Probing Human and Neural Network Language Model Understanding of Spatial Perspective","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/scaffolded-input-promotes-atomic-organization","slug":"scaffolded-input-promotes-atomic-organization","title":"Scaffolded input promotes atomic organization in the recurrent neural network language model","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/small-data-no-problem-exploring-the-viability","slug":"small-data-no-problem-exploring-the-viability","title":"Small Data? No Problem! Exploring the Viability of Pretrained Multilingual Language Models for Low-resourced Languages","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/stacked-amr-parsing-with-silver-data","slug":"stacked-amr-parsing-with-silver-data","title":"Stacked AMR Parsing with Silver Data","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/the-world-of-an-octopus-how-reporting-bias-1","slug":"the-world-of-an-octopus-how-reporting-bias-1","title":"The World of an Octopus: How Reporting Bias Influences a Language Model’s Perception of Color","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/transfer-learning-with-shallow-decoders-bsc","slug":"transfer-learning-with-shallow-decoders-bsc","title":"Transfer Learning with Shallow Decoders: BSC at WMT2021’s Multilingual Low-Resource Translation for Indo-European Languages Shared Task","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/tsdae-using-transformer-based-sequential-1","slug":"tsdae-using-transformer-based-sequential-1","title":"TSDAE: Using Transformer-based Sequential Denoising Auto-Encoderfor Unsupervised Sentence Embedding Learning","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/whos-on-first-probing-the-learning-and","slug":"whos-on-first-probing-the-learning-and","title":"Who’s on First?: Probing the Learning and Representation Capabilities of Language Models on Deterministic Closed Domains","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/with-a-little-help-from-my-temporal-context","slug":"with-a-little-help-from-my-temporal-context","title":"With a Little Help from my Temporal Context: Multimodal Egocentric Action Recognition","date":"2021-11-01","arxiv_id":"2111.01024","repositories_listed":1,"syntology":null},{"url":"/paper/top1-solution-of-qq-browser-2021-ai-algorithm","slug":"top1-solution-of-qq-browser-2021-ai-algorithm","title":"Top1 Solution of QQ Browser 2021 Ai Algorithm Competition Track 1 : Multimodal Video Similarity","date":"2021-10-30","arxiv_id":"2111.01677","repositories_listed":1,"syntology":null},{"url":"/paper/bridge-the-gap-between-cv-and-nlp-a-gradient","slug":"bridge-the-gap-between-cv-and-nlp-a-gradient","title":"Bridge the Gap Between CV and NLP! A Gradient-based Textual Adversarial Attack Framework","date":"2021-10-28","arxiv_id":"2110.15317","repositories_listed":1,"syntology":null},{"url":"/paper/scatterbrain-unifying-sparse-and-low-rank","slug":"scatterbrain-unifying-sparse-and-low-rank","title":"Scatterbrain: Unifying Sparse and Low-rank Attention Approximation","date":"2021-10-28","arxiv_id":"2110.15343","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/scatterbrain-unifying-sparse-and-low-rank#ran","syntology_url":"https://syntology.ai/paper/2110.15343","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.15343"}},"official":{"repos":["hazyresearch/scatterbrain"],"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"]}}},{"url":"/paper/semi-siamese-bi-encoder-neural-ranking-model","slug":"semi-siamese-bi-encoder-neural-ranking-model","title":"Semi-Siamese Bi-encoder Neural Ranking Model Using Lightweight Fine-Tuning","date":"2021-10-28","arxiv_id":"2110.14943","repositories_listed":1,"syntology":null},{"url":"/paper/ufal-at-multilexnorm-2021-improving","slug":"ufal-at-multilexnorm-2021-improving","title":"ÚFAL at MultiLexNorm 2021: Improving Multilingual Lexical Normalization by Fine-tuning ByT5","date":"2021-10-28","arxiv_id":"2110.15248","repositories_listed":1,"syntology":null},{"url":"/paper/discovering-non-monotonic-autoregressive","slug":"discovering-non-monotonic-autoregressive","title":"Discovering Non-monotonic Autoregressive Orderings with Variational Inference","date":"2021-10-27","arxiv_id":"2110.15797","repositories_listed":1,"syntology":{"n":7,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/discovering-non-monotonic-autoregressive#ran","syntology_url":"https://syntology.ai/paper/2110.15797","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.15797"}},"official":{"repos":["xuanlinli17/autoregressive_inference"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/mutformer-a-context-dependent-transformer","slug":"mutformer-a-context-dependent-transformer","title":"Deciphering the Language of Nature: A transformer-based language model for deleterious mutations in proteins","date":"2021-10-27","arxiv_id":"2110.14746","repositories_listed":1,"syntology":null},{"url":"/paper/avocado-strategy-for-adapting-vocabulary-to","slug":"avocado-strategy-for-adapting-vocabulary-to","title":"AVocaDo: Strategy for Adapting Vocabulary to Downstream Domain","date":"2021-10-26","arxiv_id":"2110.13434","repositories_listed":1,"syntology":null},{"url":"/paper/spanish-legalese-language-model-and-corpora","slug":"spanish-legalese-language-model-and-corpora","title":"Spanish Legalese Language Model and Corpora","date":"2021-10-23","arxiv_id":"2110.12201","repositories_listed":1,"syntology":null},{"url":"/paper/climatebert-a-pretrained-language-model-for","slug":"climatebert-a-pretrained-language-model-for","title":"ClimateBert: A Pretrained Language Model for Climate-Related Text","date":"2021-10-22","arxiv_id":"2110.12010","repositories_listed":1,"syntology":null},{"url":"/paper/text-counterfactuals-via-latent-optimization","slug":"text-counterfactuals-via-latent-optimization","title":"Text Counterfactuals via Latent Optimization and Shapley-Guided Search","date":"2021-10-22","arxiv_id":"2110.11589","repositories_listed":1,"syntology":null},{"url":"/paper/improved-multilingual-language-model","slug":"improved-multilingual-language-model","title":"Improved Multilingual Language Model Pretraining for Social Media Text via Translation Pair Prediction","date":"2021-10-20","arxiv_id":"2110.10318","repositories_listed":1,"syntology":null},{"url":"/paper/javabert-training-a-transformer-based-model","slug":"javabert-training-a-transformer-based-model","title":"JavaBERT: Training a transformer-based model for the Java programming language","date":"2021-10-20","arxiv_id":"2110.10404","repositories_listed":1,"syntology":null},{"url":"/paper/lmsoc-an-approach-for-socially-sensitive","slug":"lmsoc-an-approach-for-socially-sensitive","title":"LMSOC: An Approach for Socially Sensitive Pretraining","date":"2021-10-20","arxiv_id":"2110.10319","repositories_listed":1,"syntology":null},{"url":"/paper/normformer-improved-transformer-pretraining-1","slug":"normformer-improved-transformer-pretraining-1","title":"NormFormer: Improved Transformer Pretraining with Extra Normalization","date":"2021-10-18","arxiv_id":"2110.09456","repositories_listed":1,"syntology":null},{"url":"/paper/training-deep-neural-networks-with-adaptive","slug":"training-deep-neural-networks-with-adaptive","title":"Training Deep Neural Networks with Adaptive Momentum Inspired by the Quadratic Optimization","date":"2021-10-18","arxiv_id":"2110.09057","repositories_listed":1,"syntology":{"n":17,"n_ran":13,"n_constructed":0,"n_ran_checked":7,"n_instrument":6,"n_unverified":4,"n_honours":1,"n_violates":3,"n_no_contract":3,"n_pointer_only":5,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 3 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/training-deep-neural-networks-with-adaptive#ran","syntology_url":"https://syntology.ai/paper/2110.09057","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.09057"}},"official":{"repos":["kentaroy47/vision-transformers-cifar10"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/gnn-lm-language-modeling-based-on-global-1","slug":"gnn-lm-language-modeling-based-on-global-1","title":"GNN-LM: Language Modeling based on Global Contexts via GNN","date":"2021-10-17","arxiv_id":"2110.08743","repositories_listed":1,"syntology":null}],"record_sha256":"b76f8b70fe97cff889eb9befa89f5932d7becb12867d16a75efb37b63f383c23","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}