{"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/linear-layer/papers/253","list_of":"/method/linear-layer","method":"Linear Layer","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":253,"pages_in_order":255,"rows_per_page":100,"rows":[25201,25300],"of":25421,"counts":{"archive_papers_tagged":25421,"with_a_code_link":11479,"where_syntology_ran_a_sample":3523,"not_listed_spam_title":0,"listed":25421,"listed_where_code_ran":3523,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2976,"every_run_a_failure_of_syntologys_instrument":547,"listed_with_a_run_with_no_instrument_failure":2976,"listed_every_run_a_failure_of_syntologys_instrument":547,"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/linear-layer","prev":"/method/linear-layer/papers/252","next":"/method/linear-layer/papers/254","papers":[{"paper":"/paper/utilizing-bert-for-aspect-based-sentiment","slug":"utilizing-bert-for-aspect-based-sentiment","title":"Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence","date":"2019-03-22","arxiv_id":"1903.09588","n_code_links":8,"syntology":{"ran":19,"of":27,"n_ran_checked":15,"n_instrument":4,"unverified":8,"pointer_only":9,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 3 honoured, 0 violated, 12 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified","official":{"repos":["HSLCY/ABSA-BERT-pair"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/deep-models-for-relational-databases","slug":"deep-models-for-relational-databases","title":"Equivariant Entity-Relationship Networks","date":"2019-03-21","arxiv_id":"1903.09033","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-multi-level-information-for-dialogue","title":"Learning Multi-Level Information for Dialogue Response Selection by Highway Recurrent Transformer","date":"2019-03-21","arxiv_id":"1903.08953","n_code_links":0,"syntology":null},{"paper":null,"slug":"linguistic-knowledge-and-transferability-of","title":"Linguistic Knowledge and Transferability of Contextual Representations","date":"2019-03-21","arxiv_id":"1903.08855","n_code_links":0,"syntology":null},{"paper":"/paper/selective-attention-for-context-aware-neural","slug":"selective-attention-for-context-aware-neural","title":"Selective Attention for Context-aware Neural Machine Translation","date":"2019-03-21","arxiv_id":"1903.08788","n_code_links":1,"syntology":null},{"paper":"/paper/cloze-driven-pretraining-of-self-attention","slug":"cloze-driven-pretraining-of-self-attention","title":"Cloze-driven Pretraining of Self-attention Networks","date":"2019-03-19","arxiv_id":"1903.07785","n_code_links":0,"syntology":null},{"paper":"/paper/neutron-an-implementation-of-the-transformer","slug":"neutron-an-implementation-of-the-transformer","title":"Neutron: An Implementation of the Transformer Translation Model and its Variants","date":"2019-03-18","arxiv_id":"1903.07402","n_code_links":2,"syntology":null},{"paper":null,"slug":"stnreid-deep-convolutional-networks-with","title":"STNReID : Deep Convolutional Networks with Pairwise Spatial Transformer Networks for Partial Person Re-identification","date":"2019-03-17","arxiv_id":"1903.07072","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-deep-patent-landscaping-model-using","title":"Deep Patent Landscaping Model Using Transformer and Graph Embedding","date":"2019-03-14","arxiv_id":"1903.05823","n_code_links":0,"syntology":null},{"paper":"/paper/episodic-memory-reader-learning-what-to","slug":"episodic-memory-reader-learning-what-to","title":"Episodic Memory Reader: Learning What to Remember for Question Answering from Streaming Data","date":"2019-03-14","arxiv_id":"1903.06164","n_code_links":1,"syntology":null},{"paper":"/paper/communication-efficient-distributed-sgd-with","slug":"communication-efficient-distributed-sgd-with","title":"Communication-efficient distributed SGD with Sketching","date":"2019-03-12","arxiv_id":"1903.04488","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":["dhroth/sketchedsgd"],"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":"hltsuda-at-semeval-2019-task-1-ucca-graph","title":"HLT@SUDA at SemEval 2019 Task 1: UCCA Graph Parsing as Constituent Tree Parsing","date":"2019-03-11","arxiv_id":"1903.04153","n_code_links":0,"syntology":null},{"paper":null,"slug":"scene-memory-transformer-for-embodied-agents","title":"Scene Memory Transformer for Embodied Agents in Long-Horizon Tasks","date":"2019-03-09","arxiv_id":"1903.03878","n_code_links":0,"syntology":null},{"paper":null,"slug":"dixit-interactive-visual-storytelling-via","title":"Dixit: Interactive Visual Storytelling via Term Manipulation","date":"2019-03-06","arxiv_id":"1903.02230","n_code_links":0,"syntology":null},{"paper":null,"slug":"gq-stn-optimizing-one-shot-grasp-detection","title":"GQ-STN: Optimizing One-Shot Grasp Detection based on Robustness Classifier","date":"2019-03-06","arxiv_id":"1903.02489","n_code_links":0,"syntology":null},{"paper":"/paper/high-fidelity-image-generation-with-fewer","slug":"high-fidelity-image-generation-with-fewer","title":"High-Fidelity Image Generation With Fewer Labels","date":"2019-03-06","arxiv_id":"1903.02271","n_code_links":1,"syntology":null},{"paper":"/paper/self-adversarial-variational-autoencoder-with","slug":"self-adversarial-variational-autoencoder-with","title":"adVAE: A self-adversarial variational autoencoder with Gaussian anomaly prior knowledge for anomaly detection","date":"2019-03-03","arxiv_id":"1903.00904","n_code_links":2,"syntology":null},{"paper":"/paper/frequency-domain-transformer-networks-for","slug":"frequency-domain-transformer-networks-for","title":"Frequency Domain Transformer Networks for Video Prediction","date":"2019-03-01","arxiv_id":"1903.00271","n_code_links":1,"syntology":null},{"paper":"/paper/bert-for-joint-intent-classification-and-slot","slug":"bert-for-joint-intent-classification-and-slot","title":"BERT for Joint Intent Classification and Slot Filling","date":"2019-02-28","arxiv_id":"1902.10909","n_code_links":16,"syntology":{"ran":26,"of":32,"n_ran_checked":19,"n_instrument":7,"unverified":6,"pointer_only":5,"phrase":"26 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 1 honoured, 0 violated, 18 with no contract checked; 7 where Syntology's instrument failed) · 6 unverified","official":null}},{"paper":"/paper/attentional-encoder-network-for-targeted","slug":"attentional-encoder-network-for-targeted","title":"Attentional Encoder Network for Targeted Sentiment Classification","date":"2019-02-25","arxiv_id":"1902.09314","n_code_links":5,"syntology":null},{"paper":"/paper/pretraining-based-natural-language-generation","slug":"pretraining-based-natural-language-generation","title":"Pretraining-Based Natural Language Generation for Text Summarization","date":"2019-02-25","arxiv_id":"1902.09243","n_code_links":4,"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":null}},{"paper":"/paper/star-transformer","slug":"star-transformer","title":"Star-Transformer","date":"2019-02-25","arxiv_id":"1902.09113","n_code_links":2,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["dmlc/dgl"],"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":"/paper/enhancing-clinical-concept-extraction-with","slug":"enhancing-clinical-concept-extraction-with","title":"Enhancing Clinical Concept Extraction with Contextual Embeddings","date":"2019-02-22","arxiv_id":"1902.08691","n_code_links":0,"syntology":null},{"paper":null,"slug":"breaking-the-softmax-bottleneck-via-learnable","title":"Breaking the Softmax Bottleneck via Learnable Monotonic Pointwise Non-linearities","date":"2019-02-21","arxiv_id":"1902.08077","n_code_links":0,"syntology":null},{"paper":null,"slug":"dynamic-layer-aggregation-for-neural-machine","title":"Dynamic Layer Aggregation for Neural Machine Translation with Routing-by-Agreement","date":"2019-02-15","arxiv_id":"1902.05770","n_code_links":0,"syntology":null},{"paper":null,"slug":"actions-generation-from-captions","title":"Actions Generation from Captions","date":"2019-02-14","arxiv_id":"1902.11109","n_code_links":0,"syntology":null},{"paper":"/paper/language-models-are-unsupervised-multitask","slug":"language-models-are-unsupervised-multitask","title":"Language Models are Unsupervised Multitask Learners","date":"2019-02-14","arxiv_id":null,"n_code_links":21,"syntology":null},{"paper":null,"slug":"machine-reading-comprehension-for-answer-re","title":"Machine Reading Comprehension for Answer Re-Ranking in Customer Support Chatbots","date":"2019-02-12","arxiv_id":"1902.04574","n_code_links":0,"syntology":null},{"paper":"/paper/bert-has-a-mouth-and-it-must-speak-bert-as-a","slug":"bert-has-a-mouth-and-it-must-speak-bert-as-a","title":"BERT has a Mouth, and It Must Speak: BERT as a Markov Random Field Language Model","date":"2019-02-11","arxiv_id":"1902.04094","n_code_links":13,"syntology":{"ran":10,"of":10,"n_ran_checked":8,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["kyunghyuncho/bert-gen","nyu-dl/bert-gen"],"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":["listed","official"]}}},{"paper":null,"slug":"improving-deep-image-clustering-with-spatial","title":"Improving Deep Image Clustering With Spatial Transformer Layers","date":"2019-02-09","arxiv_id":"1902.05401","n_code_links":0,"syntology":null},{"paper":null,"slug":"insertion-transformer-flexible-sequence","title":"Insertion Transformer: Flexible Sequence Generation via Insertion Operations","date":"2019-02-08","arxiv_id":"1902.03249","n_code_links":0,"syntology":null},{"paper":"/paper/bert-and-pals-projected-attention-layers-for","slug":"bert-and-pals-projected-attention-layers-for","title":"BERT and PALs: Projected Attention Layers for Efficient Adaptation in Multi-Task Learning","date":"2019-02-07","arxiv_id":"1902.02671","n_code_links":2,"syntology":null},{"paper":null,"slug":"alphastar-an-evolutionary-computation","title":"AlphaStar: An Evolutionary Computation Perspective","date":"2019-02-05","arxiv_id":"1902.01724","n_code_links":0,"syntology":null},{"paper":"/paper/end-to-end-open-domain-question-answering","slug":"end-to-end-open-domain-question-answering","title":"End-to-End Open-Domain Question Answering with BERTserini","date":"2019-02-05","arxiv_id":"1902.01718","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":5,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["rsvp-ai/bertserini"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-comprehensive-exploration-on-wikisql-with","slug":"a-comprehensive-exploration-on-wikisql-with","title":"A Comprehensive Exploration on WikiSQL with Table-Aware Word Contextualization","date":"2019-02-04","arxiv_id":"1902.01069","n_code_links":5,"syntology":{"ran":21,"of":36,"n_ran_checked":5,"n_instrument":16,"unverified":15,"pointer_only":33,"phrase":"21 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 2 violated, 1 with no contract checked; 16 where Syntology's instrument failed) · 15 unverified","official":{"repos":["naver/sqlova"],"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":["listed","official","unlocated"]}}},{"paper":null,"slug":"insertion-based-decoding-with-automatically","title":"Insertion-based Decoding with automatically Inferred Generation Order","date":"2019-02-04","arxiv_id":"1902.01370","n_code_links":0,"syntology":null},{"paper":"/paper/right-for-the-wrong-reasons-diagnosing","slug":"right-for-the-wrong-reasons-diagnosing","title":"Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference","date":"2019-02-04","arxiv_id":"1902.01007","n_code_links":6,"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":["tommccoy1/hans"],"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/parameter-efficient-transfer-learning-for-nlp","slug":"parameter-efficient-transfer-learning-for-nlp","title":"Parameter-Efficient Transfer Learning for NLP","date":"2019-02-02","arxiv_id":"1902.00751","n_code_links":17,"syntology":{"ran":14,"of":22,"n_ran_checked":14,"n_instrument":0,"unverified":8,"pointer_only":3,"phrase":"14 ran (of which 3 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","official":{"repos":["google-research/adapter-bert"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"paper":"/paper/adding-interpretable-attention-to-neural","slug":"adding-interpretable-attention-to-neural","title":"Adding Interpretable Attention to Neural Translation Models Improves Word Alignment","date":"2019-01-31","arxiv_id":"1901.11359","n_code_links":1,"syntology":null},{"paper":"/paper/multi-task-deep-neural-networks-for-natural","slug":"multi-task-deep-neural-networks-for-natural","title":"Multi-Task Deep Neural Networks for Natural Language Understanding","date":"2019-01-31","arxiv_id":"1901.11504","n_code_links":7,"syntology":{"ran":9,"of":13,"n_ran_checked":6,"n_instrument":3,"unverified":4,"pointer_only":4,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","official":{"repos":["namisan/mt-dnn"],"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/the-second-conversational-intelligence","slug":"the-second-conversational-intelligence","title":"The Second Conversational Intelligence Challenge (ConvAI2)","date":"2019-01-31","arxiv_id":"1902.00098","n_code_links":2,"syntology":null},{"paper":"/paper/the-evolved-transformer","slug":"the-evolved-transformer","title":"The Evolved Transformer","date":"2019-01-30","arxiv_id":"1901.11117","n_code_links":3,"syntology":null},{"paper":"/paper/pay-less-attention-with-lightweight-and","slug":"pay-less-attention-with-lightweight-and","title":"Pay Less Attention with Lightweight and Dynamic Convolutions","date":"2019-01-29","arxiv_id":"1901.10430","n_code_links":3,"syntology":null},{"paper":"/paper/biobert-a-pre-trained-biomedical-language","slug":"biobert-a-pre-trained-biomedical-language","title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","date":"2019-01-25","arxiv_id":"1901.08746","n_code_links":19,"syntology":{"ran":15,"of":25,"n_ran_checked":12,"n_instrument":3,"unverified":10,"pointer_only":3,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified","official":{"repos":["dmis-lab/biobert","naver/biobert-pretrained"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"paper":"/paper/a-bert-baseline-for-the-natural-questions","slug":"a-bert-baseline-for-the-natural-questions","title":"A BERT Baseline for the Natural Questions","date":"2019-01-24","arxiv_id":"1901.08634","n_code_links":3,"syntology":{"ran":8,"of":10,"n_ran_checked":8,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["google-research/language"],"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":"self-attentive-model-for-headline-generation","title":"Self-Attentive Model for Headline Generation","date":"2019-01-23","arxiv_id":"1901.07786","n_code_links":0,"syntology":null},{"paper":"/paper/transfertransfo-a-transfer-learning-approach","slug":"transfertransfo-a-transfer-learning-approach","title":"TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents","date":"2019-01-23","arxiv_id":"1901.08149","n_code_links":23,"syntology":{"ran":18,"of":26,"n_ran_checked":11,"n_instrument":7,"unverified":8,"pointer_only":7,"phrase":"18 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; 7 where Syntology's instrument failed) · 8 unverified","official":null}},{"paper":"/paper/cross-lingual-language-model-pretraining","slug":"cross-lingual-language-model-pretraining","title":"Cross-lingual Language Model Pretraining","date":"2019-01-22","arxiv_id":"1901.07291","n_code_links":17,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":"/paper/linearized-multi-sampling-for-differentiable","slug":"linearized-multi-sampling-for-differentiable","title":"Linearized Multi-Sampling for Differentiable Image Transformation","date":"2019-01-22","arxiv_id":"1901.07124","n_code_links":1,"syntology":null},{"paper":"/paper/assessing-berts-syntactic-abilities","slug":"assessing-berts-syntactic-abilities","title":"Assessing BERT's Syntactic Abilities","date":"2019-01-16","arxiv_id":"1901.05287","n_code_links":3,"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":["yoavg/bert-syntax"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/passage-re-ranking-with-bert","slug":"passage-re-ranking-with-bert","title":"Passage Re-ranking with BERT","date":"2019-01-13","arxiv_id":"1901.04085","n_code_links":6,"syntology":{"ran":11,"of":13,"n_ran_checked":9,"n_instrument":2,"unverified":2,"pointer_only":2,"phrase":"11 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; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["nyu-dl/dl4marco-bert"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"grammatical-analysis-of-pretrained-sentence","title":"Linguistic Analysis of Pretrained Sentence Encoders with Acceptability Judgments","date":"2019-01-11","arxiv_id":"1901.03438","n_code_links":0,"syntology":null},{"paper":"/paper/equalizing-gender-biases-in-neural-machine","slug":"equalizing-gender-biases-in-neural-machine","title":"Equalizing Gender Biases in Neural Machine Translation with Word Embeddings Techniques","date":"2019-01-10","arxiv_id":"1901.03116","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-turing-completeness-of-modern-neural","title":"On the Turing Completeness of Modern Neural Network Architectures","date":"2019-01-10","arxiv_id":"1901.03429","n_code_links":0,"syntology":null},{"paper":null,"slug":"composite-shape-modeling-via-latent-space","title":"Composite Shape Modeling via Latent Space Factorization","date":"2019-01-09","arxiv_id":"1901.02968","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-xl-attentive-language-models","slug":"transformer-xl-attentive-language-models","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","date":"2019-01-09","arxiv_id":"1901.02860","n_code_links":37,"syntology":{"ran":67,"of":143,"n_ran_checked":49,"n_instrument":18,"unverified":76,"pointer_only":43,"phrase":"67 ran (of which 37 constructed an object rather than computing a result; 49 with no instrument failure: 4 honoured, 1 violated, 44 with no contract checked; 18 where Syntology's instrument failed) · 76 unverified","official":{"repos":["kimiyoung/transformer-xl"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":7,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["listed","official","unlocated"]}}},{"paper":"/paper/team-papelo-transformer-networks-at-fever","slug":"team-papelo-transformer-networks-at-fever","title":"Team Papelo: Transformer Networks at FEVER","date":"2019-01-08","arxiv_id":"1901.02534","n_code_links":1,"syntology":null},{"paper":null,"slug":"dppnet-approximating-determinantal-point","title":"DPPNet: Approximating Determinantal Point Processes with Deep Networks","date":"2019-01-07","arxiv_id":"1901.02051","n_code_links":0,"syntology":null},{"paper":"/paper/multilingual-constituency-parsing-with-self","slug":"multilingual-constituency-parsing-with-self","title":"Multilingual Constituency Parsing with Self-Attention and Pre-Training","date":"2018-12-31","arxiv_id":"1812.11760","n_code_links":4,"syntology":{"ran":22,"of":28,"n_ran_checked":19,"n_instrument":3,"unverified":6,"pointer_only":3,"phrase":"22 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified","official":{"repos":["nikitakit/self-attentive-parser"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"skeleton-transformer-networks-3d-human-pose","title":"Skeleton Transformer Networks: 3D Human Pose and Skinned Mesh from Single RGB Image","date":"2018-12-29","arxiv_id":"1812.11328","n_code_links":0,"syntology":null},{"paper":null,"slug":"looking-for-elmos-friends-sentence-level","title":"Can You Tell Me How to Get Past Sesame Street? Sentence-Level Pretraining Beyond Language Modeling","date":"2018-12-28","arxiv_id":"1812.10860","n_code_links":0,"syntology":null},{"paper":"/paper/dtmt-a-novel-deep-transition-architecture-for","slug":"dtmt-a-novel-deep-transition-architecture-for","title":"DTMT: A Novel Deep Transition Architecture for Neural Machine Translation","date":"2018-12-19","arxiv_id":"1812.07807","n_code_links":1,"syntology":null},{"paper":null,"slug":"multitask-painting-categorization-by-deep","title":"Multitask Painting Categorization by Deep Multibranch Neural Network","date":"2018-12-19","arxiv_id":"1812.08052","n_code_links":0,"syntology":null},{"paper":"/paper/self-attention-a-better-building-block-for","slug":"self-attention-a-better-building-block-for","title":"Self-Attention: A Better Building Block for Sentiment Analysis Neural Network Classifiers","date":"2018-12-19","arxiv_id":"1812.07860","n_code_links":1,"syntology":null},{"paper":"/paper/conditional-bert-contextual-augmentation","slug":"conditional-bert-contextual-augmentation","title":"Conditional BERT Contextual Augmentation","date":"2018-12-17","arxiv_id":"1812.06705","n_code_links":5,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"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","official":null}},{"paper":null,"slug":"nrityantar-pose-oblivious-indian-classical","title":"Nrityantar: Pose oblivious Indian classical dance sequence classification system","date":"2018-12-13","arxiv_id":"1812.05231","n_code_links":0,"syntology":null},{"paper":null,"slug":"hyperbolic-deep-learning-for-chinese-natural","title":"Hyperbolic Deep Learning for Chinese Natural Language Understanding","date":"2018-12-11","arxiv_id":"1812.10408","n_code_links":0,"syntology":null},{"paper":"/paper/learning-embedding-adaptation-for-few-shot","slug":"learning-embedding-adaptation-for-few-shot","title":"Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions","date":"2018-12-10","arxiv_id":"1812.03664","n_code_links":6,"syntology":null},{"paper":"/paper/sdnet-contextualized-attention-based-deep","slug":"sdnet-contextualized-attention-based-deep","title":"SDNet: Contextualized Attention-based Deep Network for Conversational Question Answering","date":"2018-12-10","arxiv_id":"1812.03593","n_code_links":6,"syntology":null},{"paper":null,"slug":"kernel-transformer-networks-for-compact","title":"Kernel Transformer Networks for Compact Spherical Convolution","date":"2018-12-07","arxiv_id":"1812.03115","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-ustc-nel-speech-translation-system-at","title":"The USTC-NEL Speech Translation system at IWSLT 2018","date":"2018-12-06","arxiv_id":"1812.02455","n_code_links":0,"syntology":null},{"paper":"/paper/video-action-transformer-network","slug":"video-action-transformer-network","title":"Video Action Transformer Network","date":"2018-12-06","arxiv_id":"1812.02707","n_code_links":0,"syntology":null},{"paper":"/paper/attending-to-mathematical-language-with","slug":"attending-to-mathematical-language-with","title":"Attending to Mathematical Language with Transformers","date":"2018-12-05","arxiv_id":"1812.02825","n_code_links":3,"syntology":null},{"paper":"/paper/practical-text-classification-with-large-pre","slug":"practical-text-classification-with-large-pre","title":"Practical Text Classification With Large Pre-Trained Language Models","date":"2018-12-04","arxiv_id":"1812.01207","n_code_links":1,"syntology":null},{"paper":null,"slug":"layer-wise-coordination-between-encoder-and","title":"Layer-Wise Coordination between Encoder and Decoder for Neural Machine Translation","date":"2018-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/learning-roi-transformer-for-detecting","slug":"learning-roi-transformer-for-detecting","title":"Learning RoI Transformer for Detecting Oriented Objects in Aerial Images","date":"2018-12-01","arxiv_id":"1812.00155","n_code_links":1,"syntology":{"ran":10,"of":11,"n_ran_checked":5,"n_instrument":5,"unverified":1,"pointer_only":11,"phrase":"10 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; 5 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/grammars-and-reinforcement-learning-for","slug":"grammars-and-reinforcement-learning-for","title":"Grammars and reinforcement learning for molecule optimization","date":"2018-11-27","arxiv_id":"1811.11222","n_code_links":1,"syntology":null},{"paper":"/paper/iterative-transformer-network-for-3d-point","slug":"iterative-transformer-network-for-3d-point","title":"Iterative Transformer Network for 3D Point Cloud","date":"2018-11-27","arxiv_id":"1811.11209","n_code_links":1,"syntology":null},{"paper":"/paper/gpipe-efficient-training-of-giant-neural","slug":"gpipe-efficient-training-of-giant-neural","title":"GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism","date":"2018-11-16","arxiv_id":"1811.06965","n_code_links":13,"syntology":{"ran":20,"of":25,"n_ran_checked":19,"n_instrument":1,"unverified":5,"pointer_only":16,"phrase":"20 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","official":null}},{"paper":null,"slug":"mathematical-analysis-of-adversarial-attacks","title":"Mathematical Analysis of Adversarial Attacks","date":"2018-11-15","arxiv_id":"1811.06492","n_code_links":0,"syntology":null},{"paper":null,"slug":"identification-of-internal-faults-in-indirect","title":"Identification of Internal Faults in Indirect Symmetrical Phase Shift Transformers Using Ensemble Learning","date":"2018-11-12","arxiv_id":"1811.04537","n_code_links":0,"syntology":null},{"paper":null,"slug":"input-combination-strategies-for-multi-source-1","title":"Input Combination Strategies for Multi-Source Transformer Decoder","date":"2018-11-12","arxiv_id":"1811.04716","n_code_links":0,"syntology":null},{"paper":"/paper/molecular-transformer-for-chemical-reaction","slug":"molecular-transformer-for-chemical-reaction","title":"Molecular Transformer - A Model for Uncertainty-Calibrated Chemical Reaction Prediction","date":"2018-11-06","arxiv_id":"1811.02633","n_code_links":1,"syntology":null},{"paper":"/paper/mesh-tensorflow-deep-learning-for","slug":"mesh-tensorflow-deep-learning-for","title":"Mesh-TensorFlow: Deep Learning for Supercomputers","date":"2018-11-05","arxiv_id":"1811.02084","n_code_links":1,"syntology":null},{"paper":"/paper/simple-distributed-and-accelerated","slug":"simple-distributed-and-accelerated","title":"Simple, Distributed, and Accelerated Probabilistic Programming","date":"2018-11-05","arxiv_id":"1811.02091","n_code_links":1,"syntology":null},{"paper":"/paper/sentence-encoders-on-stilts-supplementary","slug":"sentence-encoders-on-stilts-supplementary","title":"Sentence Encoders on STILTs: Supplementary Training on Intermediate Labeled-data Tasks","date":"2018-11-02","arxiv_id":"1811.01088","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-analysis-of-encoder-representations-in","title":"An Analysis of Encoder Representations in Transformer-Based Machine Translation","date":"2018-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"extracting-syntactic-trees-from-transformer","title":"Extracting Syntactic Trees from Transformer Encoder Self-Attentions","date":"2018-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"hybrid-self-attention-network-for-machine","title":"Hybrid Self-Attention Network for Machine Translation","date":"2018-11-01","arxiv_id":"1811.00253","n_code_links":0,"syntology":null},{"paper":null,"slug":"convolutional-self-attention-network","title":"Convolutional Self-Attention Network","date":"2018-10-31","arxiv_id":"1810.13320","n_code_links":0,"syntology":null},{"paper":null,"slug":"weakly-supervised-grammatical-error","title":"Weakly Supervised Grammatical Error Correction using Iterative Decoding","date":"2018-10-31","arxiv_id":"1811.01710","n_code_links":0,"syntology":null},{"paper":null,"slug":"parallel-attention-mechanisms-in-neural","title":"Parallel Attention Mechanisms in Neural Machine Translation","date":"2018-10-29","arxiv_id":"1810.12427","n_code_links":0,"syntology":null},{"paper":"/paper/recurrent-transformer-networks-for-semantic","slug":"recurrent-transformer-networks-for-semantic","title":"Recurrent Transformer Networks for Semantic Correspondence","date":"2018-10-29","arxiv_id":"1810.12155","n_code_links":1,"syntology":null},{"paper":"/paper/semi-supervised-target-level-sentiment","slug":"semi-supervised-target-level-sentiment","title":"Variational Semi-supervised Aspect-term Sentiment Analysis via Transformer","date":"2018-10-24","arxiv_id":"1810.10437","n_code_links":0,"syntology":null},{"paper":"/paper/area-attention","slug":"area-attention","title":"Area Attention","date":"2018-10-23","arxiv_id":"1810.10126","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-analysis-of-attention-mechanisms-the-case","title":"An Analysis of Attention Mechanisms: The Case of Word Sense Disambiguation in Neural Machine Translation","date":"2018-10-17","arxiv_id":"1810.07595","n_code_links":0,"syntology":null},{"paper":null,"slug":"metropolis-hastings-view-on-variational","title":"Metropolis-Hastings view on variational inference and adversarial training","date":"2018-10-16","arxiv_id":"1810.07151","n_code_links":0,"syntology":null},{"paper":"/paper/bert-pre-training-of-deep-bidirectional","slug":"bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","arxiv_id":"1810.04805","n_code_links":534,"syntology":{"ran":300,"of":659,"n_ran_checked":235,"n_instrument":65,"unverified":359,"pointer_only":164,"phrase":"300 ran (of which 75 constructed an object rather than computing a result; 235 with no instrument failure: 17 honoured, 4 violated, 214 with no contract checked; 65 where Syntology's instrument failed) · 359 unverified","official":{"repos":["google-research/bert"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"paper":"/paper/improving-the-transformer-translation-model","slug":"improving-the-transformer-translation-model","title":"Improving the Transformer Translation Model with Document-Level Context","date":"2018-10-08","arxiv_id":"1810.03581","n_code_links":3,"syntology":{"ran":1,"of":12,"n_ran_checked":1,"n_instrument":0,"unverified":11,"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) · 11 unverified","official":{"repos":["Glaceon31/Document-Transformer","thumt/THUMT"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":10,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"a-transformer-based-multi-source-automatic","title":"A Transformer-Based Multi-Source Automatic Post-Editing System","date":"2018-10-01","arxiv_id":null,"n_code_links":0,"syntology":null}],"record_sha256":"7063588743953013e120c3477457f5a786fbae1abc16d70884a7f03af249fe4b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}