{"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-warmup-with-linear-decay/papers/41","list_of":"/method/linear-warmup-with-linear-decay","method":"Linear Warmup With Linear Decay","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":41,"pages_in_order":71,"rows_per_page":100,"rows":[4001,4100],"of":7076,"counts":{"archive_papers_tagged":7076,"with_a_code_link":2913,"where_syntology_ran_a_sample":650,"not_listed_spam_title":0,"listed":7076,"listed_where_code_ran":650,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":531,"every_run_a_failure_of_syntologys_instrument":119,"listed_with_a_run_with_no_instrument_failure":531,"listed_every_run_a_failure_of_syntologys_instrument":119,"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-warmup-with-linear-decay","prev":"/method/linear-warmup-with-linear-decay/papers/40","next":"/method/linear-warmup-with-linear-decay/papers/42","papers":[{"paper":null,"slug":"speech-tasks-relevant-to-sleepiness","title":"Speech Tasks Relevant to Sleepiness Determined with Deep Transfer Learning","date":"2021-11-29","arxiv_id":"2111.14684","n_code_links":0,"syntology":null},{"paper":null,"slug":"tapping-bert-for-preposition-sense","title":"Tapping BERT for Preposition Sense Disambiguation","date":"2021-11-27","arxiv_id":"2111.13972","n_code_links":0,"syntology":null},{"paper":null,"slug":"predicting-document-coverage-for-relation","title":"Predicting Document Coverage for Relation Extraction","date":"2021-11-26","arxiv_id":"2111.13611","n_code_links":0,"syntology":null},{"paper":null,"slug":"does-constituency-analysis-enhance-domain","title":"Does constituency analysis enhance domain-specific pre-trained BERT models for relation extraction?","date":"2021-11-25","arxiv_id":"2112.02955","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-the-robustness-of-retrieval","slug":"evaluating-the-robustness-of-retrieval","title":"Evaluating the Robustness of Retrieval Pipelines with Query Variation Generators","date":"2021-11-25","arxiv_id":"2111.13057","n_code_links":1,"syntology":null},{"paper":null,"slug":"new-approaches-to-long-document-summarization","title":"New Approaches to Long Document Summarization: Fourier Transform Based Attention in a Transformer Model","date":"2021-11-25","arxiv_id":"2111.15473","n_code_links":0,"syntology":null},{"paper":null,"slug":"probabilistic-impact-score-generation-using","title":"Probabilistic Impact Score Generation using Ktrain-BERT to Identify Hate Words from Twitter Discussions","date":"2021-11-25","arxiv_id":"2111.12939","n_code_links":0,"syntology":null},{"paper":null,"slug":"recommending-multiple-positive-citations-for","title":"Recommending Multiple Positive Citations for Manuscript via Content-Dependent Modeling and Multi-Positive Triplet","date":"2021-11-25","arxiv_id":"2111.12899","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-based-korean-pretrained-language","title":"Transformer-based Korean Pretrained Language Models: A Survey on Three Years of Progress","date":"2021-11-25","arxiv_id":"2112.03014","n_code_links":0,"syntology":null},{"paper":"/paper/peco-perceptual-codebook-for-bert-pre","slug":"peco-perceptual-codebook-for-bert-pre","title":"PeCo: Perceptual Codebook for BERT Pre-training of Vision Transformers","date":"2021-11-24","arxiv_id":"2111.12710","n_code_links":1,"syntology":null},{"paper":"/paper/dabs-a-domain-agnostic-benchmark-for-self","slug":"dabs-a-domain-agnostic-benchmark-for-self","title":"DABS: A Domain-Agnostic Benchmark for Self-Supervised Learning","date":"2021-11-23","arxiv_id":"2111.12062","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["alextamkin/dabs"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/variational-learning-for-unsupervised-1","slug":"variational-learning-for-unsupervised-1","title":"Variational Learning for Unsupervised Knowledge Grounded Dialogs","date":"2021-11-23","arxiv_id":"2112.00653","n_code_links":1,"syntology":null},{"paper":null,"slug":"finding-the-winning-ticket-of-bert-for-binary","title":"Can depth-adaptive BERT perform better on binary classification tasks","date":"2021-11-22","arxiv_id":"2111.10951","n_code_links":0,"syntology":null},{"paper":null,"slug":"does-bert-look-at-sentiment-lexicon","title":"Does BERT look at sentiment lexicon?","date":"2021-11-19","arxiv_id":"2111.10100","n_code_links":0,"syntology":null},{"paper":null,"slug":"lexicon-based-methods-vs-bert-for-text","title":"Lexicon-based Methods vs. BERT for Text Sentiment Analysis","date":"2021-11-19","arxiv_id":"2111.10097","n_code_links":0,"syntology":null},{"paper":"/paper/debertav3-improving-deberta-using-electra","slug":"debertav3-improving-deberta-using-electra","title":"DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing","date":"2021-11-18","arxiv_id":"2111.09543","n_code_links":3,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["microsoft/DeBERTa"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"dynamic-tinybert-boost-tinybert-s-inference","title":"Dynamic-TinyBERT: Boost TinyBERT's Inference Efficiency by Dynamic Sequence Length","date":"2021-11-18","arxiv_id":"2111.09645","n_code_links":0,"syntology":null},{"paper":null,"slug":"lanobert-system-log-anomaly-detection-based","title":"LAnoBERT: System Log Anomaly Detection based on BERT Masked Language Model","date":"2021-11-18","arxiv_id":"2111.09564","n_code_links":0,"syntology":null},{"paper":"/paper/robertuito-a-pre-trained-language-model-for","slug":"robertuito-a-pre-trained-language-model-for","title":"RoBERTuito: a pre-trained language model for social media text in Spanish","date":"2021-11-18","arxiv_id":"2111.09453","n_code_links":1,"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":["pysentimiento/robertuito"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/the-power-of-selecting-key-blocks-with-local","slug":"the-power-of-selecting-key-blocks-with-local","title":"The Power of Selecting Key Blocks with Local Pre-ranking for Long Document Information Retrieval","date":"2021-11-18","arxiv_id":"2111.09852","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-comparative-study-on-transfer-learning-and","title":"A Comparative Study on Transfer Learning and Distance Metrics in Semantic Clustering over the COVID-19 Tweets","date":"2021-11-16","arxiv_id":"2111.08658","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-flexible-multi-task-model-for-bert-serving-1","title":"A Flexible Multi-Task Model for BERT Serving","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-graph-enhanced-bert-model-for-event","title":"A Graph Enhanced BERT Model for Event Prediction","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-sentence-is-worth-128-pseudo-tokens-a","title":"A Sentence is Worth 128 Pseudo Tokens: A Semantic-Aware Contrastive Learning Framework for Sentence Embeddings","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-structured-semantic-reinforcement-method","title":"A Structured Semantic Reinforcement method for Task-Oriented Dialogue","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"adapler-speeding-up-inference-by-adaptive","title":"AdapLeR: Speeding up Inference by Adaptive Length Reduction","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"an-isotropy-analysis-in-the-multilingual-bert-1","title":"An Isotropy Analysis in the Multilingual BERT Embedding Space","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"anna-enhanced-language-representation-for","title":"ANNA: Enhanced Language Representation for Question Answering","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"assessing-the-coherence-modeling-capabilities","title":"Assessing the Coherence Modeling Capabilities of Pretrained Transformer-based Language Models","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/attention-based-multi-hypothesis-fusion-for","slug":"attention-based-multi-hypothesis-fusion-for","title":"Attention-based Multi-hypothesis Fusion for Speech Summarization","date":"2021-11-16","arxiv_id":"2111.08201","n_code_links":2,"syntology":null},{"paper":null,"slug":"bert-got-a-date-introducing-transformers-to-1","title":"BERT got a Date: Introducing Transformers to Temporal Tagging","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-is-robust-a-case-against-synonym-based-1","title":"BERT is Robust! A Case Against Synonym-Based Adversarial Examples in Text Classification","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"bigfive-a-dataset-of-coarse-and-fine-grained","title":"BigFive: A Dataset of Coarse- and Fine-Grained Personality Characteristics","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"bort-back-and-denoising-reconstruction-for","title":"BORT: Back and Denoising Reconstruction for End-to-End Task-Oriented Dialog","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/building-chinese-biomedical-language-models-1","slug":"building-chinese-biomedical-language-models-1","title":"Building Chinese Biomedical Language Models via Multi-Level Text Discrimination","date":"2021-11-16","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"chinese-word-attention-based-on-valid","title":"Chinese Word Attention based on Valid Division of Sentence","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"contextualized-sensorimotor-norms-multi","title":"Contextualized Sensorimotor Norms: multi-dimensional measures of sensorimotor strength for ambiguous English words, in context","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-domain-named-entity-recognition-via","title":"Cross-domain Named Entity Recognition via Graph Matching","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/cvss-bert-explainable-natural-language","slug":"cvss-bert-explainable-natural-language","title":"CVSS-BERT: Explainable Natural Language Processing to Determine the Severity of a Computer Security Vulnerability from its Description","date":"2021-11-16","arxiv_id":"2111.08510","n_code_links":1,"syntology":null},{"paper":null,"slug":"data-contamination-from-memorization-to","title":"Data Contamination: From Memorization to Exploitation","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"dawson-data-augmentation-using-weak","title":"DAWSON: Data Augmentation using Weak Supervision On Natural Language","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-to-bottom-weights-decay-a-systemic","title":"Deep-to-bottom Weights Decay: A Systemic Knowledge Review Learning Technique for Transformer Layers in Knowledge Distillation","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"discontinuous-constituency-and-bert-a-case","title":"Discontinuous Constituency and BERT: A Case Study of Dutch","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"eliteplm-an-empirical-study-on-general","title":"ElitePLM: An Empirical Study on General Language Ability Evaluation of Pretrained Language Models","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"elle-efficient-lifelong-pre-training-for","title":"ELLE: Efficient Lifelong Pre-training for Emerging Data","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"end-to-end-task-oriented-dialog-policy","title":"End-to-end Task-oriented Dialog Policy Learning based on Pre-trained Language Model","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"event-detection-via-derangement-question","title":"Event Detection via Derangement Question Answering","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"eventbert","title":"EventBERT","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"explicit-modeling-the-context-for-chinese-ner","title":"Explicit Modeling the Context for Chinese NER","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"eye-gaze-and-self-attention-how-humans-and","title":"Eye Gaze and Self-attention: How Humans and Transformers Attend Words in Sentences","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"feature-rich-open-vocabulary-interpretable","title":"Feature-rich Open-vocabulary Interpretable Neural Representations for All of the World’s 7000 Languages","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"feature-structure-distillation-for-bert","title":"Feature Structure Distillation for BERT Transferring","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"gabert-an-irish-language-model-1","title":"gaBERT — an Irish Language Model","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"get-the-point-graph-enhanced-candidate","title":"Get the Point! Graph Enhanced Candidate Retrieval for Zero-shot Entity Linking","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"glm-general-language-model-pretraining-with","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"graph-based-fine-grained-multimodal-attention","title":"Graph-based Fine-grained Multimodal Attention Mechanism for Sentiment Analysis","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"how-does-the-pre-training-objective-affect","title":"How does the pre-training objective affect what large language models learn about linguistic properties?","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"impact-of-tokenization-on-language-models-an","title":"Impact of Tokenization on Language Models: An Analysis for Turkish","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-neural-models-for-radiology-report","title":"Improving Neural Models for Radiology Report Retrieval with Lexicon-based Automated Annotation","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-unsupervised-sentence","title":"Improving Unsupervised Sentence Simplification Using Fine-Tuned Masked Language Models","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"input-specific-attention-subnetworks-for","title":"Input-specific Attention Subnetworks for Adversarial Detection","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/integrated-semantic-and-phonetic-post-1","slug":"integrated-semantic-and-phonetic-post-1","title":"Integrated Semantic and Phonetic Post-correction for Chinese Speech Recognition","date":"2021-11-16","arxiv_id":"2111.08400","n_code_links":1,"syntology":null},{"paper":"/paper/interpreting-language-models-through","slug":"interpreting-language-models-through","title":"Interpreting Language Models Through Knowledge Graph Extraction","date":"2021-11-16","arxiv_id":"2111.08546","n_code_links":1,"syntology":null},{"paper":null,"slug":"interpreting-the-robustness-of-neural-nlp","title":"Interpreting the Robustness of Neural NLP Models to Textual Perturbations","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"investigating-the-use-of-bert-anchors-for","title":"Investigating the Use of BERT Anchors for Bilingual Lexicon Induction with Minimal Supervision","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"is-neural-topic-modelling-better-than","title":"Is Neural Topic Modelling Better than Clustering? An Empirical Study on Clustering with Contextual Embeddings for Topics","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"is-whole-word-masking-always-better-for","title":"\"Is Whole Word Masking Always Better for Chinese BERT?\": Probing on Chinese Grammatical Error Correction","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"kinyabert-a-morphology-aware-kinyarwanda","title":"KinyaBERT: a Morphology-aware Kinyarwanda Language Model","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-enhanced-embedding-improve-model","title":"Knowledge Enhanced Embedding: Improve Model Generalization Through Knowledge Graphs","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"language-level-classification-on-german-texts","title":"Language Level Classification on German Texts using a Neural Approach","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-ignore-adversarial-attacks","title":"Learning to Ignore Adversarial Attacks","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"looking-into-the-black-box-how-are-idioms","title":"Looking Into the Black Box - How Are Idioms Processed in BERT?","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"lordbert-embedding-long-text-by-segment","title":"LordBERT: Embedding Long Text by Segment Ordering with BERT","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"marcqap-effective-context-modeling-for","title":"MarCQAp: Effective Context Modeling for Conversational Question Answering","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/markbert-marking-word-boundaries-improves","slug":"markbert-marking-word-boundaries-improves","title":"MarkBERT: Marking Word Boundaries Improves Chinese BERT","date":"2021-11-16","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"mderank-a-masked-document-embedding-rank-1","title":"MDERank: A Masked Document Embedding Rank Approach for Unsupervised Keyphrase Extraction","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"metadata-shaping-natural-language-annotations-1","title":"Metadata Shaping: Natural Language Annotations for the Long Tail","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"nsp-bert-a-prompt-based-zero-shot-learner-1","title":"NSP-BERT: A Prompt-based Zero-Shot Learner Through an Original Pre-training Task —— Next Sentence Prediction","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-robustness-of-reading-comprehension-1","title":"On the Robustness of Reading Comprehension Models to Entity Renaming","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"pare-a-simple-and-strong-baseline-for","title":"PARE: A Simple and Strong Baseline for Monolingual and Multilingual Distantly Supervised Relation Extraction","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"perturbations-in-the-wild-leveraging-human","title":"Perturbations in the Wild: Leveraging Human-Written Text Perturbations for Realistic Adversarial Attack and Defense","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"pinyin-bert-a-new-solution-to-chinese-pinyin","title":"Pinyin-bert: A new solution to Chinese pinyin to character conversion task","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"probing-berts-priors-with-serial-reproduction","title":"Probing BERT’s priors with serial reproduction chains","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"promptbert-improving-bert-sentence-embeddings","title":"PromptBERT: Improving BERT Sentence Embeddings with Prompts","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"reco-reliable-multi-hop-causal-reasoning-via","title":"ReCo: Reliable Multi-hop Causal Reasoning via Structural Causal Recurrent Unit","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"representation-of-ambiguity-in-pre-trained","title":"Representation of Ambiguity in Pre-Trained Sentence Embeddings","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"sambert-improve-aspect-sentiment-triplet","title":"SAMBERT: Improve Aspect Sentiment Triplet Extraction by Segmenting the Attention Maps of BERT","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"self-supervised-contrastive-learning-with-1","title":"Self-Supervised Contrastive Learning with Adversarial Perturbations for Robust Pretrained Language Models","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"shield-defending-textual-neural-networks","title":"SHIELD: Defending Textual Neural Networks against Black-Box Adversarial Attacks with Stochastic Multi-Expert Patcher","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"softmax-bottleneck-makes-language-models","title":"Softmax Bottleneck Makes Language Models Unable to Represent Multi-mode Word Distributions","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"taco-pre-training-of-deep-transformers-with","title":"TACO: Pre-training of Deep Transformers with Attention Convolution using Disentangled Positional Representation","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"the-impact-of-lexical-and-grammatical","title":"The impact of lexical and grammatical processing on generating code from natural language","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-fully-self-supervised-learning-of","title":"Towards Fully Self-Supervised Learning of Knowledge from Unstructured Text","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-improving-topic-models-with-the-bert","title":"Towards Improving Topic Models with the BERT-based Neural Topic Encoder","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"understanding-attention-in-machine-reading-1","title":"Understanding Attention in Machine Reading Comprehension","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"unicon-unsupervised-intent-discovery-via","title":"UNICON: Unsupervised Intent Discovery via Semantic-level Contrastive Learning","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"unsupervised-multiple-choice-question","title":"Unsupervised multiple-choice question generation for out-of-domain Q\\&A fine-tuning","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"weight-squeezing-reparameterization-for-2","title":"Weight Squeezing: Reparameterization for Knowledge Transfer and Model Compression","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"when-classifying-grammatical-role-bert-doesn","title":"When classifying grammatical role, BERT doesn't care about word order... except when it matters","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"assessing-gender-bias-in-medical-and","title":"Assessing gender bias in medical and scientific masked language models with StereoSet","date":"2021-11-15","arxiv_id":"2111.08088","n_code_links":0,"syntology":null}],"record_sha256":"5cddf2c95640bbe2072668a9a04c68a8a23fa5dbd683a53e0c8abe0e21f891f3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}