{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/attention-dropout/papers/65","list_of":"/method/attention-dropout","method":"Attention Dropout","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":65,"pages_in_order":109,"rows_per_page":100,"rows":[6401,6500],"of":10892,"counts":{"archive_papers_tagged":10892,"with_a_code_link":4634,"where_syntology_ran_a_sample":1270,"not_listed_spam_title":0,"listed":10892,"listed_where_code_ran":1270,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1043,"every_run_a_failure_of_syntologys_instrument":227,"listed_with_a_run_with_no_instrument_failure":1043,"listed_every_run_a_failure_of_syntologys_instrument":227,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/attention-dropout","prev":"/method/attention-dropout/papers/64","next":"/method/attention-dropout/papers/66","papers":[{"paper":null,"slug":"supervised-contrastive-learning-as-multi","title":"Supervised Contrastive Learning as Multi-Objective Optimization for Fine-Tuning Large Pre-trained Language Models","date":"2022-09-28","arxiv_id":"2209.14161","n_code_links":0,"syntology":null},{"paper":"/paper/who-is-gpt-3-an-exploration-of-personality","slug":"who-is-gpt-3-an-exploration-of-personality","title":"Who is GPT-3? An Exploration of Personality, Values and Demographics","date":"2022-09-28","arxiv_id":"2209.14338","n_code_links":1,"syntology":null},{"paper":"/paper/yato-yet-another-deep-learning-based-text","slug":"yato-yet-another-deep-learning-based-text","title":"YATO: Yet Another deep learning based Text analysis Open toolkit","date":"2022-09-28","arxiv_id":"2209.13877","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-critical-appraisal-of-equity-in","title":"How GPT-3 responds to different publics on climate change and Black Lives Matter: A critical appraisal of equity in conversational AI","date":"2022-09-27","arxiv_id":"2209.13627","n_code_links":0,"syntology":null},{"paper":null,"slug":"extractive-question-answering-on-queries-in","title":"Extractive Question Answering on Queries in Hindi and Tamil","date":"2022-09-27","arxiv_id":"2210.06356","n_code_links":0,"syntology":null},{"paper":"/paper/outlier-suppression-pushing-the-limit-of-low","slug":"outlier-suppression-pushing-the-limit-of-low","title":"Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models","date":"2022-09-27","arxiv_id":"2209.13325","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":3,"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) · 1 unverified","official":{"repos":["wimh966/outlier_suppression"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"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":null,"slug":"do-ever-larger-octopi-still-amplify-reporting","title":"Do ever larger octopi still amplify reporting biases? Evidence from judgments of typical colour","date":"2022-09-26","arxiv_id":"2209.12786","n_code_links":0,"syntology":null},{"paper":"/paper/news-summarization-and-evaluation-in-the-era","slug":"news-summarization-and-evaluation-in-the-era","title":"News Summarization and Evaluation in the Era of GPT-3","date":"2022-09-26","arxiv_id":"2209.12356","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-simple-and-efficient-task-adaptive","title":"Towards Simple and Efficient Task-Adaptive Pre-training for Text Classification","date":"2022-09-26","arxiv_id":"2209.12943","n_code_links":0,"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":null,"slug":"bigger-faster-two-stage-neural-architecture","title":"SpeedLimit: Neural Architecture Search for Quantized Transformer Models","date":"2022-09-25","arxiv_id":"2209.12127","n_code_links":0,"syntology":null},{"paper":null,"slug":"sentiment-analysis-on-inflation-after-covid","title":"Sentiment Analysis on Inflation after Covid-19","date":"2022-09-25","arxiv_id":"2209.14737","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-transformer-models-effectively-detect","title":"Can Transformer Models Effectively Detect Software Aspects in StackOverflow Discussion?","date":"2022-09-24","arxiv_id":"2209.12065","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-chess-with-language-models-and","title":"Learning Chess With Language Models and Transformers","date":"2022-09-24","arxiv_id":"2209.11902","n_code_links":0,"syntology":null},{"paper":null,"slug":"moral-mimicry-large-language-models-produce","title":"Moral Mimicry: Large Language Models Produce Moral Rationalizations Tailored to Political Identity","date":"2022-09-24","arxiv_id":"2209.12106","n_code_links":0,"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":null,"slug":"idea-interactive-double-attentions-from-label","title":"IDEA: Interactive DoublE Attentions from Label Embedding for Text Classification","date":"2022-09-23","arxiv_id":"2209.11407","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-case-report-on-the-a-i-locked-in-problem","title":"A Case Report On The \"A.I. Locked-In Problem\": social concerns with modern NLP","date":"2022-09-22","arxiv_id":"2209.12687","n_code_links":0,"syntology":null},{"paper":"/paper/adaptation-of-domain-specific-transformer","slug":"adaptation-of-domain-specific-transformer","title":"Adaptation of domain-specific transformer models with text oversampling for sentiment analysis of social media posts on Covid-19 vaccines","date":"2022-09-22","arxiv_id":"2209.10966","n_code_links":1,"syntology":null},{"paper":null,"slug":"air-jpmc-smm4h-22-classifying-self-reported","title":"AIR-JPMC@SMM4H'22: Classifying Self-Reported Intimate Partner Violence in Tweets with Multiple BERT-based Models","date":"2022-09-22","arxiv_id":"2209.10763","n_code_links":0,"syntology":null},{"paper":null,"slug":"dfx-a-low-latency-multi-fpga-appliance-for","title":"DFX: A Low-latency Multi-FPGA Appliance for Accelerating Transformer-based Text Generation","date":"2022-09-22","arxiv_id":"2209.10797","n_code_links":0,"syntology":null},{"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":"/paper/bias-at-a-second-glance-a-deep-dive-into-bias","slug":"bias-at-a-second-glance-a-deep-dive-into-bias","title":"Bias at a Second Glance: A Deep Dive into Bias for German Educational Peer-Review Data Modeling","date":"2022-09-21","arxiv_id":"2209.10335","n_code_links":2,"syntology":{"ran":3,"of":6,"n_ran_checked":3,"n_instrument":0,"unverified":3,"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","official":{"repos":["epfl-ml4ed/bias-at-a-second-glance"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["listed"]}}},{"paper":"/paper/cae-mechanism-to-diminish-the-class","slug":"cae-mechanism-to-diminish-the-class","title":"CAE: Mechanism to Diminish the Class Imbalanced in SLU Slot Filling Task","date":"2022-09-21","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"representing-affect-information-in-word","title":"Representing Affect Information in Word Embeddings","date":"2022-09-21","arxiv_id":"2209.10583","n_code_links":0,"syntology":null},{"paper":null,"slug":"subject-verb-agreement-error-patterns-in","title":"Subject Verb Agreement Error Patterns in Meaningless Sentences: Humans vs. BERT","date":"2022-09-21","arxiv_id":"2209.10538","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":"text-revealer-private-text-reconstruction-via","title":"Text Revealer: Private Text Reconstruction via Model Inversion Attacks against Transformers","date":"2022-09-21","arxiv_id":"2209.10505","n_code_links":0,"syntology":null},{"paper":null,"slug":"integer-fine-tuning-of-transformer-based","title":"Towards Fine-tuning Pre-trained Language Models with Integer Forward and Backward Propagation","date":"2022-09-20","arxiv_id":"2209.09815","n_code_links":0,"syntology":null},{"paper":null,"slug":"one-to-many-semantic-communication-systems","title":"One-to-Many Semantic Communication Systems: Design, Implementation, Performance Evaluation","date":"2022-09-20","arxiv_id":"2209.09425","n_code_links":0,"syntology":null},{"paper":"/paper/unsupervised-early-exit-in-dnns-with-multiple","slug":"unsupervised-early-exit-in-dnns-with-multiple","title":"Unsupervised Early Exit in DNNs with Multiple Exits","date":"2022-09-20","arxiv_id":"2209.09480","n_code_links":1,"syntology":null},{"paper":"/paper/meta-adapters-parameter-efficient-few-shot","slug":"meta-adapters-parameter-efficient-few-shot","title":"Meta-Adapters: Parameter Efficient Few-shot Fine-tuning through Meta-Learning","date":"2022-09-19","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"will-it-blend-mixing-training-paradigms","title":"Will It Blend? Mixing Training Paradigms & Prompting for Argument Quality Prediction","date":"2022-09-19","arxiv_id":"2209.08966","n_code_links":0,"syntology":null},{"paper":"/paper/detecting-generated-scientific-papers-using","slug":"detecting-generated-scientific-papers-using","title":"Detecting Generated Scientific Papers using an Ensemble of Transformer Models","date":"2022-09-17","arxiv_id":"2209.08283","n_code_links":1,"syntology":null},{"paper":"/paper/learning-to-answer-semantic-queries-over-code","slug":"learning-to-answer-semantic-queries-over-code","title":"CodeQueries: A Dataset of Semantic Queries over Code","date":"2022-09-17","arxiv_id":"2209.08372","n_code_links":1,"syntology":null},{"paper":null,"slug":"changing-the-representation-examining-1","title":"Changing the Representation: Examining Language Representation for Neural Sign Language Production","date":"2022-09-16","arxiv_id":"2210.06312","n_code_links":0,"syntology":null},{"paper":"/paper/psychologically-informed-chain-of-thought","slug":"psychologically-informed-chain-of-thought","title":"Psychologically-informed chain-of-thought prompts for metaphor understanding in large language models","date":"2022-09-16","arxiv_id":"2209.08141","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":0,"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) · 0 unverified","official":{"repos":["benpry/chain-of-thought-metaphor"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"text-and-patterns-for-effective-chain-of","title":"Text and Patterns: For Effective Chain of Thought, It Takes Two to Tango","date":"2022-09-16","arxiv_id":"2209.07686","n_code_links":0,"syntology":null},{"paper":null,"slug":"machine-reading-fast-and-slow-when-do-models","title":"Machine Reading, Fast and Slow: When Do Models \"Understand\" Language?","date":"2022-09-15","arxiv_id":"2209.07430","n_code_links":0,"syntology":null},{"paper":null,"slug":"uchecker-masked-pretrained-language-models-as","title":"uChecker: Masked Pretrained Language Models as Unsupervised Chinese Spelling Checkers","date":"2022-09-15","arxiv_id":"2209.07068","n_code_links":0,"syntology":null},{"paper":null,"slug":"automated-fidelity-assessment-for-strategy","title":"Automated Fidelity Assessment for Strategy Training in Inpatient Rehabilitation using Natural Language Processing","date":"2022-09-14","arxiv_id":"2209.06727","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-based-ensemble-approaches-for-hate","title":"BERT-based Ensemble Approaches for Hate Speech Detection","date":"2022-09-14","arxiv_id":"2209.06505","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-quantized-sparse-matrix-operations","slug":"efficient-quantized-sparse-matrix-operations","title":"Efficient Quantized Sparse Matrix Operations on Tensor Cores","date":"2022-09-14","arxiv_id":"2209.06979","n_code_links":1,"syntology":null},{"paper":null,"slug":"out-of-one-many-using-language-models-to","title":"Out of One, Many: Using Language Models to Simulate Human Samples","date":"2022-09-14","arxiv_id":"2209.06899","n_code_links":0,"syntology":null},{"paper":null,"slug":"pre-training-for-information-retrieval-are","title":"Pre-training for Information Retrieval: Are Hyperlinks Fully Explored?","date":"2022-09-14","arxiv_id":"2209.06583","n_code_links":0,"syntology":null},{"paper":null,"slug":"cnn-trans-enc-a-cnn-enhanced-transformer","title":"CNN-Trans-Enc: A CNN-Enhanced Transformer-Encoder On Top Of Static BERT representations for Document Classification","date":"2022-09-13","arxiv_id":"2209.06344","n_code_links":0,"syntology":null},{"paper":null,"slug":"robin-a-novel-online-suicidal-text-corpus-of-1","title":"Robin: A Novel Online Suicidal Text Corpus of Substantial Breadth and Scale","date":"2022-09-13","arxiv_id":"2209.05707","n_code_links":0,"syntology":null},{"paper":null,"slug":"skin-skimming-intensive-long-text","title":"SkIn: Skimming-Intensive Long-Text Classification Using BERT for Medical Corpus","date":"2022-09-13","arxiv_id":"2209.05741","n_code_links":0,"syntology":null},{"paper":null,"slug":"classification-of-hazard-event-via-language","title":"A new hazard event classification model via deep learning and multifractal","date":"2022-09-12","arxiv_id":"2209.05263","n_code_links":0,"syntology":null},{"paper":null,"slug":"deck-behavioral-tests-to-improve-1","title":"DECK: Behavioral Tests to Improve Interpretability and Generalizability of BERT Models Detecting Depression from Text","date":"2022-09-12","arxiv_id":"2209.05286","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":"probing-for-understanding-of-english-verb","title":"Probing for Understanding of English Verb Classes and Alternations in Large Pre-trained Language Models","date":"2022-09-11","arxiv_id":"2209.04811","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":null,"slug":"yes-dlgm-a-novel-hierarchical-model-for","title":"Yes, DLGM! A novel hierarchical model for hazard classification","date":"2022-09-10","arxiv_id":"2209.04576","n_code_links":0,"syntology":null},{"paper":"/paper/echocotr-estimation-of-the-left-ventricular","slug":"echocotr-estimation-of-the-left-ventricular","title":"EchoCoTr: Estimation of the Left Ventricular Ejection Fraction from Spatiotemporal Echocardiography","date":"2022-09-09","arxiv_id":"2209.04242","n_code_links":1,"syntology":null},{"paper":null,"slug":"trigger-warnings-bootstrapping-a-violence","title":"Trigger Warnings: Bootstrapping a Violence Detector for FanFiction","date":"2022-09-09","arxiv_id":"2209.04409","n_code_links":0,"syntology":null},{"paper":"/paper/claclab-at-socialdisner-using-medical","slug":"claclab-at-socialdisner-using-medical","title":"CLaCLab at SocialDisNER: Using Medical Gazetteers for Named-Entity Recognition of Disease Mentions in Spanish Tweets","date":"2022-09-08","arxiv_id":"2209.03528","n_code_links":1,"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":"transformer-based-classification-of-premise","title":"5q032e@SMM4H'22: Transformer-based classification of premise in tweets related to COVID-19","date":"2022-09-08","arxiv_id":"2209.03851","n_code_links":0,"syntology":null},{"paper":null,"slug":"why-so-toxic-measuring-and-triggering-toxic","title":"Why So Toxic? Measuring and Triggering Toxic Behavior in Open-Domain Chatbots","date":"2022-09-07","arxiv_id":"2209.03463","n_code_links":0,"syntology":null},{"paper":"/paper/multilingual-bidirectional-unsupervised","slug":"multilingual-bidirectional-unsupervised","title":"Multilingual Bidirectional Unsupervised Translation Through Multilingual Finetuning and Back-Translation","date":"2022-09-06","arxiv_id":"2209.02821","n_code_links":1,"syntology":null},{"paper":"/paper/chemberta-2-towards-chemical-foundation","slug":"chemberta-2-towards-chemical-foundation","title":"ChemBERTa-2: Towards Chemical Foundation Models","date":"2022-09-05","arxiv_id":"2209.01712","n_code_links":2,"syntology":null},{"paper":null,"slug":"distilling-the-knowledge-of-bert-for-ctc","title":"Distilling the Knowledge of BERT for CTC-based ASR","date":"2022-09-05","arxiv_id":"2209.02030","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-the-susceptibility-of-pre-trained","title":"Evaluating the Susceptibility of Pre-Trained Language Models via Handcrafted Adversarial Examples","date":"2022-09-05","arxiv_id":"2209.02128","n_code_links":0,"syntology":null},{"paper":"/paper/do-large-language-models-know-what-humans","slug":"do-large-language-models-know-what-humans","title":"Do Large Language Models know what humans know?","date":"2022-09-04","arxiv_id":"2209.01515","n_code_links":1,"syntology":null},{"paper":null,"slug":"every-picture-tells-a-story-image-grounded","title":"Every picture tells a story: Image-grounded controllable stylistic story generation","date":"2022-09-04","arxiv_id":"2209.01638","n_code_links":0,"syntology":null},{"paper":null,"slug":"generalization-in-neural-networks-a-broad","title":"Generalization in Neural Networks: A Broad Survey","date":"2022-09-04","arxiv_id":"2209.01610","n_code_links":0,"syntology":null},{"paper":"/paper/elaboration-generating-commonsense-question","slug":"elaboration-generating-commonsense-question","title":"Elaboration-Generating Commonsense Question Answering at Scale","date":"2022-09-02","arxiv_id":"2209.01232","n_code_links":1,"syntology":null},{"paper":"/paper/folio-natural-language-reasoning-with-first","slug":"folio-natural-language-reasoning-with-first","title":"FOLIO: Natural Language Reasoning with First-Order Logic","date":"2022-09-02","arxiv_id":"2209.00840","n_code_links":1,"syntology":null},{"paper":null,"slug":"gres-graphical-cross-domain-recommendation","title":"GReS: Graphical Cross-domain Recommendation for Supply Chain Platform","date":"2022-09-02","arxiv_id":"2209.01031","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-semantic-understanding-with-self","title":"Enhancing Semantic Understanding with Self-supervised Methods for Abstractive Dialogue Summarization","date":"2022-09-01","arxiv_id":"2209.00278","n_code_links":0,"syntology":null},{"paper":"/paper/isotropic-representation-can-improve-dense","slug":"isotropic-representation-can-improve-dense","title":"Isotropic Representation Can Improve Dense Retrieval","date":"2022-09-01","arxiv_id":"2209.00218","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-scale-contrastive-co-training-for-event","title":"Distilling Multi-Scale Knowledge for Event Temporal Relation Extraction","date":"2022-09-01","arxiv_id":"2209.00568","n_code_links":0,"syntology":null},{"paper":"/paper/negation-detection-in-dutch-clinical-texts-an","slug":"negation-detection-in-dutch-clinical-texts-an","title":"Negation detection in Dutch clinical texts: an evaluation of rule-based and machine learning methods","date":"2022-09-01","arxiv_id":"2209.00470","n_code_links":1,"syntology":null},{"paper":null,"slug":"few-shot-learning-for-clinical-natural","title":"Few-Shot Learning for Clinical Natural Language Processing Using Siamese Neural Networks","date":"2022-08-31","arxiv_id":"2208.14923","n_code_links":0,"syntology":null},{"paper":"/paper/large-scale-multi-granular-concept-extraction","slug":"large-scale-multi-granular-concept-extraction","title":"Large-scale Multi-granular Concept Extraction Based on Machine Reading Comprehension","date":"2022-08-30","arxiv_id":"2208.14139","n_code_links":1,"syntology":null},{"paper":"/paper/no-means-no-a-non-im-proper-modeling-approach","slug":"no-means-no-a-non-im-proper-modeling-approach","title":"No means ‘No’; a non-im-proper modeling approach, with embedded speculative context","date":"2022-08-30","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"swiftpruner-reinforced-evolutionary-pruning","title":"SwiftPruner: Reinforced Evolutionary Pruning for Efficient Ad Relevance","date":"2022-08-30","arxiv_id":"2209.00625","n_code_links":0,"syntology":null},{"paper":"/paper/transformers-with-learnable-activation","slug":"transformers-with-learnable-activation","title":"Transformers with Learnable Activation Functions","date":"2022-08-30","arxiv_id":"2208.14111","n_code_links":2,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"pointer_only":1,"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","official":{"repos":["ukplab/2022-raft"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"multi-dimensional-racism-classification","title":"Multi-dimensional Racism Classification during COVID-19: Stigmatization, Offensiveness, Blame, and Exclusion","date":"2022-08-29","arxiv_id":"2208.13318","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":"building-the-intent-landscape-of-real-world","title":"Building the Intent Landscape of Real-World Conversational Corpora with Extractive Question-Answering Transformers","date":"2022-08-26","arxiv_id":"2208.12886","n_code_links":0,"syntology":null},{"paper":"/paper/task-specific-pre-training-and-prompt","slug":"task-specific-pre-training-and-prompt","title":"Task-specific Pre-training and Prompt Decomposition for Knowledge Graph Population with Language Models","date":"2022-08-26","arxiv_id":"2208.12539","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-reality-and-the-limits-of-language-data","title":"On Reality and the Limits of Language Data: Aligning LLMs with Human Norms","date":"2022-08-25","arxiv_id":"2208.11981","n_code_links":0,"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/addressing-token-uniformity-in-transformers","slug":"addressing-token-uniformity-in-transformers","title":"Addressing Token Uniformity in Transformers via Singular Value Transformation","date":"2022-08-24","arxiv_id":"2208.11790","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"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) · 0 unverified","official":{"repos":["hanqi-qi/tokenuni"],"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"]}}},{"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":null,"slug":"evaluate-confidence-instead-of-perplexity-for","title":"Evaluate Confidence Instead of Perplexity for Zero-shot Commonsense Reasoning","date":"2022-08-23","arxiv_id":"2208.11007","n_code_links":0,"syntology":null},{"paper":"/paper/prompting-as-probing-using-language-models","slug":"prompting-as-probing-using-language-models","title":"Prompting as Probing: Using Language Models for Knowledge Base Construction","date":"2022-08-23","arxiv_id":"2208.11057","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":2,"n_instrument":4,"unverified":0,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["hemile/iswc-challenge"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"a-syntax-aware-bert-for-identifying-well","title":"A Syntax Aware BERT for Identifying Well-Formed Queries in a Curriculum Framework","date":"2022-08-21","arxiv_id":"2208.09912","n_code_links":0,"syntology":null},{"paper":null,"slug":"cmsbert-clr-context-driven-modality-shifting","title":"CMSBERT-CLR: Context-driven Modality Shifting BERT with Contrastive Learning for linguistic, visual, acoustic Representations","date":"2022-08-21","arxiv_id":"2209.07424","n_code_links":0,"syntology":null},{"paper":"/paper/bspell-a-cnn-blended-bert-based-bengali-spell","slug":"bspell-a-cnn-blended-bert-based-bengali-spell","title":"BSpell: A CNN-Blended BERT Based Bangla Spell Checker","date":"2022-08-20","arxiv_id":"2208.09709","n_code_links":1,"syntology":null},{"paper":null,"slug":"combining-compressions-for-multiplicative","title":"Combining Compressions for Multiplicative Size Scaling on Natural Language Tasks","date":"2022-08-20","arxiv_id":"2208.09684","n_code_links":0,"syntology":null},{"paper":null,"slug":"pretrained-language-encoders-are-natural","title":"Pretrained Language Encoders are Natural Tagging Frameworks for Aspect Sentiment Triplet Extraction","date":"2022-08-20","arxiv_id":"2208.09617","n_code_links":0,"syntology":null},{"paper":"/paper/representing-knowledge-by-spans-a-knowledge","slug":"representing-knowledge-by-spans-a-knowledge","title":"SPOT: Knowledge-Enhanced Language Representations for Information Extraction","date":"2022-08-20","arxiv_id":"2208.09625","n_code_links":0,"syntology":null},{"paper":null,"slug":"graph-augmented-cyclic-learning-framework-for","title":"Graph-Augmented Cyclic Learning Framework for Similarity Estimation of Medical Clinical Notes","date":"2022-08-19","arxiv_id":"2208.09437","n_code_links":0,"syntology":null},{"paper":"/paper/unicausal-unified-benchmark-and-model-for","slug":"unicausal-unified-benchmark-and-model-for","title":"UniCausal: Unified Benchmark and Repository for Causal Text Mining","date":"2022-08-19","arxiv_id":"2208.09163","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}],"record_sha256":"eee62222ff87c2467aee4d1e9058e04a048e74d0c38933d066755db3a0a8f747","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}