{"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/wordpiece/papers/41","list_of":"/method/wordpiece","method":"WordPiece","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":7063,"counts":{"archive_papers_tagged":7063,"with_a_code_link":2910,"where_syntology_ran_a_sample":650,"not_listed_spam_title":0,"listed":7063,"listed_where_code_ran":650,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":529,"every_run_a_failure_of_syntologys_instrument":121,"listed_with_a_run_with_no_instrument_failure":529,"listed_every_run_a_failure_of_syntologys_instrument":121,"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/wordpiece","prev":"/method/wordpiece/papers/40","next":"/method/wordpiece/papers/42","papers":[{"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":"life-after-bert-what-do-other-muppets","title":"Life after BERT: What do Other Muppets Understand about Language?","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":"palbert-teaching-albert-to-ponder","title":"PALBERT: Teaching ALBERT to Ponder","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},{"paper":null,"slug":"exploring-story-generation-with-multi-task","title":"Exploring Story Generation with Multi-task Objectives in Variational Autoencoders","date":"2021-11-15","arxiv_id":"2111.08133","n_code_links":0,"syntology":null},{"paper":"/paper/iiitt-dravidian-codemix-fire2021","slug":"iiitt-dravidian-codemix-fire2021","title":"IIITT@Dravidian-CodeMix-FIRE2021: Transliterate or translate? Sentiment analysis of code-mixed text in Dravidian languages","date":"2021-11-15","arxiv_id":"2111.07906","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-prosody-for-unseen-texts-in-speech","title":"Improving Prosody for Unseen Texts in Speech Synthesis by Utilizing Linguistic Information and Noisy Data","date":"2021-11-15","arxiv_id":"2111.07549","n_code_links":0,"syntology":null},{"paper":null,"slug":"scaling-law-for-recommendation-models-towards","title":"Scaling Law for Recommendation Models: Towards General-purpose User Representations","date":"2021-11-15","arxiv_id":"2111.11294","n_code_links":0,"syntology":null},{"paper":null,"slug":"will-you-find-these-shortcuts-a-protocol-for","title":"\"Will You Find These Shortcuts?\" A Protocol for Evaluating the Faithfulness of Input Salience Methods for Text Classification","date":"2021-11-14","arxiv_id":"2111.07367","n_code_links":0,"syntology":null},{"paper":null,"slug":"socialbert-transformers-for-online","title":"SocialBERT -- Transformers for Online SocialNetwork Language Modelling","date":"2021-11-13","arxiv_id":"2111.07148","n_code_links":0,"syntology":null},{"paper":"/paper/ms-latte-a-dataset-of-where-and-when-to-do","slug":"ms-latte-a-dataset-of-where-and-when-to-do","title":"MS-LaTTE: A Dataset of Where and When To-do Tasks are Completed","date":"2021-11-12","arxiv_id":"2111.06902","n_code_links":1,"syntology":null},{"paper":"/paper/character-level-hypernetworks-for-hate-speech","slug":"character-level-hypernetworks-for-hate-speech","title":"Character-level HyperNetworks for Hate Speech Detection","date":"2021-11-11","arxiv_id":"2111.06336","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-large-scale-language-models-and","title":"Improving Large-scale Language Models and Resources for Filipino","date":"2021-11-11","arxiv_id":"2111.06053","n_code_links":0,"syntology":null},{"paper":null,"slug":"amazon-sagemaker-model-parallelism-a-general","title":"Amazon SageMaker Model Parallelism: A General and Flexible Framework for Large Model Training","date":"2021-11-10","arxiv_id":"2111.05972","n_code_links":0,"syntology":null},{"paper":"/paper/bagbert-bert-based-bagging-stacking-for-multi","slug":"bagbert-bert-based-bagging-stacking-for-multi","title":"BagBERT: BERT-based bagging-stacking for multi-topic classification","date":"2021-11-10","arxiv_id":"2111.05808","n_code_links":1,"syntology":null},{"paper":null,"slug":"cehr-bert-incorporating-temporal-information","title":"CEHR-BERT: Incorporating temporal information from structured EHR data to improve prediction tasks","date":"2021-11-10","arxiv_id":"2111.08585","n_code_links":0,"syntology":null},{"paper":"/paper/prune-once-for-all-sparse-pre-trained","slug":"prune-once-for-all-sparse-pre-trained","title":"Prune Once for All: Sparse Pre-Trained Language Models","date":"2021-11-10","arxiv_id":"2111.05754","n_code_links":2,"syntology":null},{"paper":null,"slug":"dsbert-unsupervised-dialogue-structure","title":"DSBERT:Unsupervised Dialogue Structure learning with BERT","date":"2021-11-09","arxiv_id":"2111.04933","n_code_links":0,"syntology":null},{"paper":null,"slug":"fpm-a-collection-of-large-scale-foundation","title":"FPM: A Collection of Large-scale Foundation Pre-trained Language Models","date":"2021-11-09","arxiv_id":"2111.04909","n_code_links":0,"syntology":null},{"paper":null,"slug":"human-in-the-loop-disinformation-detection","title":"Human-in-the-Loop Disinformation Detection: Stance, Sentiment, or Something Else?","date":"2021-11-09","arxiv_id":"2111.05139","n_code_links":0,"syntology":null},{"paper":"/paper/ai-upv-at-iberlef-2021-detoxis-task-toxicity","slug":"ai-upv-at-iberlef-2021-detoxis-task-toxicity","title":"AI-UPV at IberLEF-2021 DETOXIS task: Toxicity Detection in Immigration-Related Web News Comments Using Transformers and Statistical Models","date":"2021-11-08","arxiv_id":"2111.04530","n_code_links":1,"syntology":null},{"paper":"/paper/chemical-detection-and-indexing-in-pubmed","slug":"chemical-detection-and-indexing-in-pubmed","title":"Chemical detection and indexing in PubMed full text articles using deep learning and rule-based methods","date":"2021-11-08","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"detecting-depression-in-thai-blog-posts-a-1","title":"Detecting Depression in Thai Blog Posts: a Dataset and a Baseline","date":"2021-11-08","arxiv_id":"2111.04574","n_code_links":0,"syntology":null},{"paper":"/paper/guiding-multi-step-rearrangement-tasks-with","slug":"guiding-multi-step-rearrangement-tasks-with","title":"Guiding Multi-Step Rearrangement Tasks with Natural Language Instructions","date":"2021-11-08","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":"/paper/sexism-prediction-in-spanish-and-english","slug":"sexism-prediction-in-spanish-and-english","title":"Sexism Prediction in Spanish and English Tweets Using Monolingual and Multilingual BERT and Ensemble Models","date":"2021-11-08","arxiv_id":"2111.04551","n_code_links":1,"syntology":null},{"paper":"/paper/synthesizing-collective-communication","slug":"synthesizing-collective-communication","title":"TACCL: Guiding Collective Algorithm Synthesis using Communication Sketches","date":"2021-11-08","arxiv_id":"2111.04867","n_code_links":2,"syntology":null},{"paper":"/paper/tacl-improving-bert-pre-training-with-token","slug":"tacl-improving-bert-pre-training-with-token","title":"TaCL: Improving BERT Pre-training with Token-aware Contrastive Learning","date":"2021-11-07","arxiv_id":"2111.04198","n_code_links":2,"syntology":null},{"paper":null,"slug":"profitable-trade-off-between-memory-and","title":"Profitable Trade-Off Between Memory and Performance In Multi-Domain Chatbot Architectures","date":"2021-11-06","arxiv_id":"2111.03963","n_code_links":0,"syntology":null},{"paper":null,"slug":"context-aware-transformer-transducer-for","title":"Context-Aware Transformer Transducer for Speech Recognition","date":"2021-11-05","arxiv_id":"2111.03250","n_code_links":0,"syntology":null},{"paper":null,"slug":"conversational-speech-recognition-leveraging","title":"Effective Cross-Utterance Language Modeling for Conversational Speech Recognition","date":"2021-11-05","arxiv_id":"2111.03333","n_code_links":0,"syntology":null},{"paper":null,"slug":"ibert-idiom-cloze-style-reading-comprehension","title":"IBERT: Idiom Cloze-style reading comprehension with Attention","date":"2021-11-05","arxiv_id":"2112.02994","n_code_links":0,"syntology":null},{"paper":null,"slug":"sexism-identification-in-tweets-and-gabs","title":"Sexism Identification in Tweets and Gabs using Deep Neural Networks","date":"2021-11-05","arxiv_id":"2111.03612","n_code_links":0,"syntology":null}],"record_sha256":"d900e1624d5d4f76b4a23da133a669d71cff4dd9b8a3738da19aa9da56922a00","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}