{"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/glu/papers/6","list_of":"/method/glu","method":"Gated Linear Unit","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":6,"pages_in_order":8,"rows_per_page":100,"rows":[501,600],"of":798,"counts":{"archive_papers_tagged":798,"with_a_code_link":400,"where_syntology_ran_a_sample":115,"not_listed_spam_title":0,"listed":798,"listed_where_code_ran":115,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":99,"every_run_a_failure_of_syntologys_instrument":16,"listed_with_a_run_with_no_instrument_failure":99,"listed_every_run_a_failure_of_syntologys_instrument":16,"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/glu","prev":"/method/glu/papers/5","next":"/method/glu/papers/7","papers":[{"paper":"/paper/scaling-instruction-finetuned-language-models","slug":"scaling-instruction-finetuned-language-models","title":"Scaling Instruction-Finetuned Language Models","date":"2022-10-20","arxiv_id":"2210.11416","n_code_links":9,"syntology":{"ran":8,"of":17,"n_ran_checked":1,"n_instrument":7,"unverified":9,"pointer_only":2,"phrase":"8 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 7 where Syntology's instrument failed) · 9 unverified","official":null}},{"paper":"/paper/self-supervised-graph-masking-pre-training","slug":"self-supervised-graph-masking-pre-training","title":"Self-supervised Graph Masking Pre-training for Graph-to-Text Generation","date":"2022-10-19","arxiv_id":"2210.10599","n_code_links":1,"syntology":null},{"paper":"/paper/swinv2-imagen-hierarchical-vision-transformer","slug":"swinv2-imagen-hierarchical-vision-transformer","title":"Swinv2-Imagen: Hierarchical Vision Transformer Diffusion Models for Text-to-Image Generation","date":"2022-10-18","arxiv_id":"2210.09549","n_code_links":0,"syntology":null},{"paper":"/paper/john-is-50-years-old-can-his-son-be-65","slug":"john-is-50-years-old-can-his-son-be-65","title":"\"John is 50 years old, can his son be 65?\" Evaluating NLP Models' Understanding of Feasibility","date":"2022-10-14","arxiv_id":"2210.07471","n_code_links":1,"syntology":null},{"paper":null,"slug":"self-repetition-in-abstractive-neural","title":"Self-Repetition in Abstractive Neural Summarizers","date":"2022-10-14","arxiv_id":"2210.08145","n_code_links":0,"syntology":null},{"paper":null,"slug":"tone-prediction-and-orthographic-conversion","title":"Tone prediction and orthographic conversion for Basaa","date":"2022-10-13","arxiv_id":"2210.06986","n_code_links":0,"syntology":null},{"paper":"/paper/frustratingly-simple-entity-tracking-with","slug":"frustratingly-simple-entity-tracking-with","title":"Entity Tracking via Effective Use of Multi-Task Learning Model and Mention-guided Decoding","date":"2022-10-12","arxiv_id":"2210.06444","n_code_links":2,"syntology":{"ran":3,"of":4,"n_ran_checked":0,"n_instrument":3,"unverified":1,"pointer_only":4,"phrase":"3 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; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["iamjanvijay/meet","iamjanvijay/set"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/instruction-tuning-for-few-shot-aspect-based","slug":"instruction-tuning-for-few-shot-aspect-based","title":"Instruction Tuning for Few-Shot Aspect-Based Sentiment Analysis","date":"2022-10-12","arxiv_id":"2210.06629","n_code_links":1,"syntology":null},{"paper":null,"slug":"rankt5-fine-tuning-t5-for-text-ranking-with","title":"RankT5: Fine-Tuning T5 for Text Ranking with Ranking Losses","date":"2022-10-12","arxiv_id":"2210.10634","n_code_links":0,"syntology":null},{"paper":"/paper/are-pretrained-multilingual-models-equally-1","slug":"are-pretrained-multilingual-models-equally-1","title":"Are Pretrained Multilingual Models Equally Fair Across Languages?","date":"2022-10-11","arxiv_id":"2210.05457","n_code_links":1,"syntology":null},{"paper":null,"slug":"reflection-of-thought-inversely-eliciting","title":"Reflection of Thought: Inversely Eliciting Numerical Reasoning in Language Models via Solving Linear Systems","date":"2022-10-11","arxiv_id":"2210.05075","n_code_links":0,"syntology":null},{"paper":"/paper/t5-for-hate-speech-augmented-data-and","slug":"t5-for-hate-speech-augmented-data-and","title":"T5 for Hate Speech, Augmented Data and Ensemble","date":"2022-10-11","arxiv_id":"2210.05480","n_code_links":1,"syntology":null},{"paper":"/paper/asdot-any-shot-data-to-text-generation-with","slug":"asdot-any-shot-data-to-text-generation-with","title":"ASDOT: Any-Shot Data-to-Text Generation with Pretrained Language Models","date":"2022-10-09","arxiv_id":"2210.04325","n_code_links":1,"syntology":null},{"paper":"/paper/chard-clinical-health-aware-reasoning-across","slug":"chard-clinical-health-aware-reasoning-across","title":"CHARD: Clinical Health-Aware Reasoning Across Dimensions for Text Generation Models","date":"2022-10-09","arxiv_id":"2210.04191","n_code_links":1,"syntology":null},{"paper":null,"slug":"improve-transformer-pre-training-with","title":"Better Pre-Training by Reducing Representation Confusion","date":"2022-10-09","arxiv_id":"2210.04246","n_code_links":0,"syntology":null},{"paper":null,"slug":"generating-quizzes-to-support-training-on","title":"Generating Quizzes to Support Training on Quality Management and Assurance in Space Science and Engineering","date":"2022-10-07","arxiv_id":"2210.03427","n_code_links":0,"syntology":null},{"paper":"/paper/how-large-language-models-are-transforming","slug":"how-large-language-models-are-transforming","title":"How Large Language Models are Transforming Machine-Paraphrased Plagiarism","date":"2022-10-07","arxiv_id":"2210.03568","n_code_links":3,"syntology":null},{"paper":"/paper/nmtsloth-understanding-and-testing-efficiency","slug":"nmtsloth-understanding-and-testing-efficiency","title":"LLMEffiChecker: Understanding and Testing Efficiency Degradation of Large Language Models","date":"2022-10-07","arxiv_id":"2210.03696","n_code_links":1,"syntology":null},{"paper":"/paper/promptkg-a-prompt-learning-framework-for","slug":"promptkg-a-prompt-learning-framework-for","title":"LambdaKG: A Library for Pre-trained Language Model-Based Knowledge Graph Embeddings","date":"2022-10-01","arxiv_id":"2210.00305","n_code_links":2,"syntology":null},{"paper":null,"slug":"bidirectional-language-models-are-also-few","title":"Bidirectional Language Models Are Also Few-shot Learners","date":"2022-09-29","arxiv_id":"2209.14500","n_code_links":0,"syntology":null},{"paper":"/paper/wikides-a-wikipedia-based-dataset-for","slug":"wikides-a-wikipedia-based-dataset-for","title":"WikiDes: A Wikipedia-Based Dataset for Generating Short Descriptions from Paragraphs","date":"2022-09-27","arxiv_id":"2209.13101","n_code_links":1,"syntology":null},{"paper":"/paper/application-of-deep-learning-in-generating-1","slug":"application-of-deep-learning-in-generating-1","title":"Application of Deep Learning in Generating Structured Radiology Reports: A Transformer-Based Technique","date":"2022-09-25","arxiv_id":"2209.12177","n_code_links":1,"syntology":null},{"paper":"/paper/et5-a-novel-end-to-end-framework-for","slug":"et5-a-novel-end-to-end-framework-for","title":"ET5: A Novel End-to-end Framework for Conversational Machine Reading Comprehension","date":"2022-09-23","arxiv_id":"2209.11484","n_code_links":1,"syntology":null},{"paper":"/paper/on-efficient-reinforcement-learning-for-full","slug":"on-efficient-reinforcement-learning-for-full","title":"On Efficient Reinforcement Learning for Full-length Game of StarCraft II","date":"2022-09-23","arxiv_id":"2209.11553","n_code_links":2,"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":["liuruoze/hiernet-sc2","liuruoze/mini-AlphaStar"],"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":["official"]}}},{"paper":"/paper/xf2t-cross-lingual-fact-to-text-generation","slug":"xf2t-cross-lingual-fact-to-text-generation","title":"XF2T: Cross-lingual Fact-to-Text Generation for Low-Resource Languages","date":"2022-09-22","arxiv_id":"2209.11252","n_code_links":0,"syntology":null},{"paper":null,"slug":"t5ql-taming-language-models-for-sql","title":"T5QL: Taming language models for SQL generation","date":"2022-09-21","arxiv_id":"2209.10254","n_code_links":0,"syntology":null},{"paper":null,"slug":"chain-of-explanation-new-prompting-method-to","title":"Chain of Explanation: New Prompting Method to Generate Higher Quality Natural Language Explanation for Implicit Hate Speech","date":"2022-09-11","arxiv_id":"2209.04889","n_code_links":0,"syntology":null},{"paper":null,"slug":"simple-and-effective-gradient-based-tuning-of","title":"Simple and Effective Gradient-Based Tuning of Sequence-to-Sequence Models","date":"2022-09-10","arxiv_id":"2209.04683","n_code_links":0,"syntology":null},{"paper":"/paper/idiapers-causal-news-corpus-2022-extracting","slug":"idiapers-causal-news-corpus-2022-extracting","title":"IDIAPers @ Causal News Corpus 2022: Extracting Cause-Effect-Signal Triplets via Pre-trained Autoregressive Language Model","date":"2022-09-08","arxiv_id":"2209.03891","n_code_links":1,"syntology":null},{"paper":null,"slug":"interpreting-black-box-machine-learning","title":"Interpreting Black-box Machine Learning Models for High Dimensional Datasets","date":"2022-08-29","arxiv_id":"2208.13405","n_code_links":0,"syntology":null},{"paper":"/paper/mdia-a-benchmark-for-multilingual-dialogue","slug":"mdia-a-benchmark-for-multilingual-dialogue","title":"MDIA: A Benchmark for Multilingual Dialogue Generation in 46 Languages","date":"2022-08-27","arxiv_id":"2208.13078","n_code_links":1,"syntology":null},{"paper":"/paper/autoqgs-auto-prompt-for-low-resource","slug":"autoqgs-auto-prompt-for-low-resource","title":"AutoQGS: Auto-Prompt for Low-Resource Knowledge-based Question Generation from SPARQL","date":"2022-08-26","arxiv_id":"2208.12461","n_code_links":1,"syntology":null},{"paper":null,"slug":"training-a-t5-using-lab-sized-resources","title":"Training a T5 Using Lab-sized Resources","date":"2022-08-25","arxiv_id":"2208.12097","n_code_links":0,"syntology":null},{"paper":"/paper/diverse-title-generation-for-stack-overflow","slug":"diverse-title-generation-for-stack-overflow","title":"Diverse Title Generation for Stack Overflow Posts with Multiple Sampling Enhanced Transformer","date":"2022-08-24","arxiv_id":"2208.11523","n_code_links":1,"syntology":null},{"paper":"/paper/mulzdg-multilingual-code-switching-framework","slug":"mulzdg-multilingual-code-switching-framework","title":"MulZDG: Multilingual Code-Switching Framework for Zero-shot Dialogue Generation","date":"2022-08-18","arxiv_id":"2208.08629","n_code_links":1,"syntology":null},{"paper":null,"slug":"summarizing-patients-problems-from-hospital","title":"Summarizing Patients Problems from Hospital Progress Notes Using Pre-trained Sequence-to-Sequence Models","date":"2022-08-17","arxiv_id":"2208.08408","n_code_links":0,"syntology":null},{"paper":null,"slug":"continuous-active-learning-using-pretrained","title":"Continuous Active Learning Using Pretrained Transformers","date":"2022-08-15","arxiv_id":"2208.06955","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-boring-yet-effective-approach-for-the","title":"A Boring-yet-effective Approach for the Product Ranking Task of the Amazon KDD Cup 2022","date":"2022-08-09","arxiv_id":"2208.06264","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-knowledge-bank-for-pretrained","title":"Neural Knowledge Bank for Pretrained Transformers","date":"2022-07-31","arxiv_id":"2208.00399","n_code_links":0,"syntology":null},{"paper":"/paper/hornet-efficient-high-order-spatial","slug":"hornet-efficient-high-order-spatial","title":"HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutions","date":"2022-07-28","arxiv_id":"2207.14284","n_code_links":8,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["raoyongming/hornet"],"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"]}}},{"paper":"/paper/sequence-to-sequence-pretraining-for-a-less","slug":"sequence-to-sequence-pretraining-for-a-less","title":"Sequence to sequence pretraining for a less-resourced Slovenian language","date":"2022-07-28","arxiv_id":"2207.13988","n_code_links":1,"syntology":null},{"paper":"/paper/no-more-fine-tuning-an-experimental","slug":"no-more-fine-tuning-an-experimental","title":"No More Fine-Tuning? An Experimental Evaluation of Prompt Tuning in Code Intelligence","date":"2022-07-24","arxiv_id":"2207.11680","n_code_links":1,"syntology":{"ran":7,"of":14,"n_ran_checked":6,"n_instrument":1,"unverified":7,"pointer_only":2,"phrase":"7 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; 1 where Syntology's instrument failed) · 7 unverified","official":{"repos":["adf1178/pt4code"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"context-based-lemmatizer-for-polish-language","title":"Context based lemmatizer for Polish language","date":"2022-07-23","arxiv_id":"2207.11565","n_code_links":0,"syntology":null},{"paper":null,"slug":"effectiveness-of-french-language-models-on","title":"Effectiveness of French Language Models on Abstractive Dialogue Summarization Task","date":"2022-07-17","arxiv_id":"2207.08305","n_code_links":0,"syntology":null},{"paper":"/paper/doccoder-generating-code-by-retrieving-and","slug":"doccoder-generating-code-by-retrieving-and","title":"DocPrompting: Generating Code by Retrieving the Docs","date":"2022-07-13","arxiv_id":"2207.05987","n_code_links":2,"syntology":{"ran":4,"of":9,"n_ran_checked":2,"n_instrument":2,"unverified":5,"pointer_only":0,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","official":{"repos":["shuyanzhou/doccoder","shuyanzhou/docprompting"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/re2g-retrieve-rerank-generate-2","slug":"re2g-retrieve-rerank-generate-2","title":"Re2G: Retrieve, Rerank, Generate","date":"2022-07-13","arxiv_id":"2207.06300","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":6,"n_instrument":1,"unverified":1,"pointer_only":1,"phrase":"7 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ibm/kgi-slot-filling"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"learning-to-diversify-for-product-question","title":"Learning to Diversify for Product Question Generation","date":"2022-07-06","arxiv_id":"2207.02534","n_code_links":0,"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":"/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":"/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/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":"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/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":"/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/gasp-gated-attention-for-saliency-prediction-1","slug":"gasp-gated-attention-for-saliency-prediction-1","title":"GASP: Gated Attention For Saliency Prediction","date":"2022-06-09","arxiv_id":"2206.04590","n_code_links":1,"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":"/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":null,"slug":"conditional-set-generation-using-seq2seq-1","title":"Conditional set generation using Seq2seq models","date":"2022-05-25","arxiv_id":"2205.12485","n_code_links":0,"syntology":null},{"paper":"/paper/robustlr-evaluating-robustness-to-logical","slug":"robustlr-evaluating-robustness-to-logical","title":"RobustLR: Evaluating Robustness to Logical Perturbation in Deductive Reasoning","date":"2022-05-25","arxiv_id":"2205.12598","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["ink-usc/robustlr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/tacube-pre-computing-data-cubes-for-answering","slug":"tacube-pre-computing-data-cubes-for-answering","title":"TaCube: Pre-computing Data Cubes for Answering Numerical-Reasoning Questions over Tabular Data","date":"2022-05-25","arxiv_id":"2205.12682","n_code_links":1,"syntology":null},{"paper":null,"slug":"edit5-semi-autoregressive-text-editing-with","title":"EdiT5: Semi-Autoregressive Text-Editing with T5 Warm-Start","date":"2022-05-24","arxiv_id":"2205.12209","n_code_links":0,"syntology":null},{"paper":"/paper/flute-figurative-language-understanding-and","slug":"flute-figurative-language-understanding-and","title":"FLUTE: Figurative Language Understanding through Textual Explanations","date":"2022-05-24","arxiv_id":"2205.12404","n_code_links":1,"syntology":null},{"paper":"/paper/geomlama-geo-diverse-commonsense-probing-on","slug":"geomlama-geo-diverse-commonsense-probing-on","title":"GeoMLAMA: Geo-Diverse Commonsense Probing on Multilingual Pre-Trained Language Models","date":"2022-05-24","arxiv_id":"2205.12247","n_code_links":1,"syntology":null},{"paper":null,"slug":"medical-scientific-table-to-text-generation","title":"Medical Scientific Table-to-Text Generation with Human-in-the-Loop under the Data Sparsity Constraint","date":"2022-05-24","arxiv_id":"2205.12368","n_code_links":0,"syntology":null},{"paper":"/paper/workflow-discovery-from-dialogues-in-the-low","slug":"workflow-discovery-from-dialogues-in-the-low","title":"Workflow Discovery from Dialogues in the Low Data Regime","date":"2022-05-24","arxiv_id":"2205.11690","n_code_links":1,"syntology":null},{"paper":"/paper/a-question-answer-driven-approach-to-reveal","slug":"a-question-answer-driven-approach-to-reveal","title":"A Question-Answer Driven Approach to Reveal Affirmative Interpretations from Verbal Negations","date":"2022-05-23","arxiv_id":"2205.11467","n_code_links":1,"syntology":null},{"paper":"/paper/banglanlg-benchmarks-and-resources-for","slug":"banglanlg-benchmarks-and-resources-for","title":"BanglaNLG and BanglaT5: Benchmarks and Resources for Evaluating Low-Resource Natural Language Generation in Bangla","date":"2022-05-23","arxiv_id":"2205.11081","n_code_links":2,"syntology":null},{"paper":"/paper/life-after-bert-what-do-other-muppets-2","slug":"life-after-bert-what-do-other-muppets-2","title":"Life after BERT: What do Other Muppets Understand about Language?","date":"2022-05-21","arxiv_id":"2205.10696","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluation-of-transfer-learning-for-polish-1","title":"Evaluation of Transfer Learning for Polish with a Text-to-Text Model","date":"2022-05-18","arxiv_id":"2205.08808","n_code_links":0,"syntology":null},{"paper":null,"slug":"pash-at-trec-2021-deep-learning-track","title":"PASH at TREC 2021 Deep Learning Track: Generative Enhanced Model for Multi-stage Ranking","date":"2022-05-18","arxiv_id":"2205.11245","n_code_links":0,"syntology":null},{"paper":null,"slug":"m6-rec-generative-pretrained-language-models","title":"M6-Rec: Generative Pretrained Language Models are Open-Ended Recommender Systems","date":"2022-05-17","arxiv_id":"2205.08084","n_code_links":0,"syntology":null},{"paper":null,"slug":"skill-structured-knowledge-infusion-for-large","title":"SKILL: Structured Knowledge Infusion for Large Language Models","date":"2022-05-17","arxiv_id":"2205.08184","n_code_links":0,"syntology":null},{"paper":"/paper/downstream-transformer-generation-of-question","slug":"downstream-transformer-generation-of-question","title":"Downstream Transformer Generation of Question-Answer Pairs with Preprocessing and Postprocessing Pipelines","date":"2022-05-15","arxiv_id":"2205.07387","n_code_links":1,"syntology":null},{"paper":"/paper/rasat-integrating-relational-structures-into","slug":"rasat-integrating-relational-structures-into","title":"RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL","date":"2022-05-14","arxiv_id":"2205.06983","n_code_links":1,"syntology":{"ran":5,"of":9,"n_ran_checked":5,"n_instrument":0,"unverified":4,"pointer_only":1,"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) · 4 unverified","official":{"repos":["lumia-group/rasat"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/unifying-language-learning-paradigms","slug":"unifying-language-learning-paradigms","title":"UL2: Unifying Language Learning Paradigms","date":"2022-05-10","arxiv_id":"2205.05131","n_code_links":2,"syntology":{"ran":15,"of":16,"n_ran_checked":15,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["google-research/google-research"],"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":"vector-representations-of-idioms-in","title":"Vector Representations of Idioms in Conversational Systems","date":"2022-05-07","arxiv_id":"2205.03666","n_code_links":0,"syntology":null},{"paper":"/paper/two-new-datasets-for-italian-language","slug":"two-new-datasets-for-italian-language","title":"Two New Datasets for Italian-Language Abstractive Text Summarization","date":"2022-04-29","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/modern-baselines-for-sparql-semantic-parsing","slug":"modern-baselines-for-sparql-semantic-parsing","title":"Modern Baselines for SPARQL Semantic Parsing","date":"2022-04-27","arxiv_id":"2204.12793","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-arabic-sentence-simplification-via","title":"Towards Arabic Sentence Simplification via Classification and Generative Approaches","date":"2022-04-20","arxiv_id":"2204.09292","n_code_links":0,"syntology":null},{"paper":"/paper/massive-a-1m-example-multilingual-natural","slug":"massive-a-1m-example-multilingual-natural","title":"MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages","date":"2022-04-18","arxiv_id":"2204.08582","n_code_links":6,"syntology":{"ran":8,"of":10,"n_ran_checked":8,"n_instrument":0,"unverified":2,"pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["alexa/massive"],"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":["listed","official"]}}},{"paper":null,"slug":"wordalchemy-a-transformer-based-reverse","title":"WordAlchemy: A transformer-based Reverse Dictionary","date":"2022-04-16","arxiv_id":"2204.10181","n_code_links":0,"syntology":null},{"paper":null,"slug":"ml-ltu-at-semeval-2022-task-4-t5-towards","title":"ML_LTU at SemEval-2022 Task 4: T5 Towards Identifying Patronizing and Condescending Language","date":"2022-04-15","arxiv_id":"2204.07432","n_code_links":0,"syntology":null},{"paper":"/paper/revisiting-markovian-generative-architectures","slug":"revisiting-markovian-generative-architectures","title":"Building Markovian Generative Architectures over Pretrained LM Backbones for Efficient Task-Oriented Dialog Systems","date":"2022-04-13","arxiv_id":"2204.06452","n_code_links":2,"syntology":null},{"paper":"/paper/enhance-incomplete-utterance-restoration-by","slug":"enhance-incomplete-utterance-restoration-by","title":"Enhance Incomplete Utterance Restoration by Joint Learning Token Extraction and Text Generation","date":"2022-04-08","arxiv_id":"2204.03958","n_code_links":1,"syntology":null},{"paper":"/paper/mmtafrica-multilingual-machine-translation-1","slug":"mmtafrica-multilingual-machine-translation-1","title":"MMTAfrica: Multilingual Machine Translation for African Languages","date":"2022-04-08","arxiv_id":"2204.04306","n_code_links":1,"syntology":null},{"paper":"/paper/byt5-model-for-massively-multilingual","slug":"byt5-model-for-massively-multilingual","title":"ByT5 model for massively multilingual grapheme-to-phoneme conversion","date":"2022-04-06","arxiv_id":"2204.03067","n_code_links":1,"syntology":null},{"paper":null,"slug":"contextual-attention-mechanism-srgan-based","title":"Contextual Attention Mechanism, SRGAN Based Inpainting System for Eliminating Interruptions from Images","date":"2022-04-06","arxiv_id":"2204.02591","n_code_links":0,"syntology":null},{"paper":"/paper/example-based-hypernetworks-for-out-of","slug":"example-based-hypernetworks-for-out-of","title":"Example-based Hypernetworks for Out-of-Distribution Generalization","date":"2022-03-27","arxiv_id":"2203.14276","n_code_links":1,"syntology":null},{"paper":"/paper/ensembling-and-knowledge-distilling-of-large-1","slug":"ensembling-and-knowledge-distilling-of-large-1","title":"Ensembling and Knowledge Distilling of Large Sequence Taggers for Grammatical Error Correction","date":"2022-03-24","arxiv_id":"2203.13064","n_code_links":1,"syntology":null},{"paper":"/paper/recommendation-as-language-processing-rlp-a","slug":"recommendation-as-language-processing-rlp-a","title":"Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)","date":"2022-03-24","arxiv_id":"2203.13366","n_code_links":2,"syntology":null},{"paper":null,"slug":"arabart-a-pretrained-arabic-sequence-to-1","title":"AraBART: a Pretrained Arabic Sequence-to-Sequence Model for Abstractive Summarization","date":"2022-03-21","arxiv_id":"2203.10945","n_code_links":0,"syntology":null},{"paper":"/paper/dq-bart-efficient-sequence-to-sequence-model","slug":"dq-bart-efficient-sequence-to-sequence-model","title":"DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and Quantization","date":"2022-03-21","arxiv_id":"2203.11239","n_code_links":2,"syntology":{"ran":1,"of":5,"n_ran_checked":0,"n_instrument":1,"unverified":4,"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) · 4 unverified","official":{"repos":["amazon-research/dq-bart"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["listed"]}}},{"paper":"/paper/coloring-the-blank-slate-pre-training-imparts-1","slug":"coloring-the-blank-slate-pre-training-imparts-1","title":"Coloring the Blank Slate: Pre-training Imparts a Hierarchical Inductive Bias to Sequence-to-sequence Models","date":"2022-03-17","arxiv_id":"2203.09397","n_code_links":1,"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: 3 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sebschu/multilingual-transformations"],"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/it5-large-scale-text-to-text-pretraining-for","slug":"it5-large-scale-text-to-text-pretraining-for","title":"IT5: Text-to-text Pretraining for Italian Language Understanding and Generation","date":"2022-03-07","arxiv_id":"2203.03759","n_code_links":3,"syntology":null},{"paper":"/paper/parameter-efficient-mixture-of-experts","slug":"parameter-efficient-mixture-of-experts","title":"Parameter-Efficient Mixture-of-Experts Architecture for Pre-trained Language Models","date":"2022-03-02","arxiv_id":"2203.01104","n_code_links":2,"syntology":{"ran":5,"of":5,"n_ran_checked":3,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"5 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["rucaibox/mpo","rucaibox/mpoe"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"e-lang-energy-based-joint-inferencing-of-1","title":"E-LANG: Energy-Based Joint Inferencing of Super and Swift Language Models","date":"2022-03-01","arxiv_id":"2203.00748","n_code_links":0,"syntology":null},{"paper":null,"slug":"hyperprompt-prompt-based-task-conditioning-of","title":"HyperPrompt: Prompt-based Task-Conditioning of Transformers","date":"2022-03-01","arxiv_id":"2203.00759","n_code_links":0,"syntology":null},{"paper":null,"slug":"harmonic-gated-compensation-network-plus-for","title":"Harmonic gated compensation network plus for ICASSP 2022 DNS CHALLENGE","date":"2022-02-25","arxiv_id":"2202.12643","n_code_links":0,"syntology":null},{"paper":null,"slug":"mixture-of-experts-with-expert-choice-routing","title":"Mixture-of-Experts with Expert Choice Routing","date":"2022-02-18","arxiv_id":"2202.09368","n_code_links":0,"syntology":null}],"record_sha256":"e3dcd05b24a549fc28dcb4fa031175543a3dbbcc2d8310e4b59489aff04218a0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}