{"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/papers/255","list_of":"/method/attention","method":"Attention","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":255,"pages_in_order":316,"rows_per_page":100,"rows":[25401,25500],"of":31583,"counts":{"archive_papers_tagged":31583,"with_a_code_link":13473,"where_syntology_ran_a_sample":3998,"not_listed_spam_title":0,"listed":31583,"listed_where_code_ran":3998,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3366,"every_run_a_failure_of_syntologys_instrument":632,"listed_with_a_run_with_no_instrument_failure":3366,"listed_every_run_a_failure_of_syntologys_instrument":632,"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","prev":"/method/attention/papers/254","next":"/method/attention/papers/256","papers":[{"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":"active-dialogue-simulation-in-conversational","title":"Active Dialogue Simulation in Conversational Systems","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":"all-birds-with-one-stone-multi-task-learning","title":"All Birds with One Stone: Multi-task Learning for Inference with One Forward Pass","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"an-empirical-study-of-document-to-document","title":"An Empirical Study of Document-to-document Neural Machine Translation","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"an-information-theoretic-measurement-of","title":"An Information Theoretic Measurement of Topical Relevance in Learner Essays","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":"barcor-towards-a-unified-framework-for","title":"BARCOR: Towards A Unified Framework for Conversational Recommendation","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"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":"calbert-code-mixed-adaptive-language","title":"CalBERT - Code-mixed Adaptive Language representations using BERT","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"causal-transformers-improving-the-robustness","title":"Causal Transformers: Improving the Robustness on Spurious Correlations","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"challenges-for-open-domain-targeted-sentiment","title":"Challenges for Open-domain Targeted Sentiment Analysis","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"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":"coloring-the-blank-slate-pre-training-imparts","title":"Coloring the Blank Slate: Pre-training Imparts a Hierarchical Inductive Bias to Sequence-to-sequence Models","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"compressing-sentence-representation-via","title":"Compressing Sentence Representation via Homomorphic Projective Distillation","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"constructing-phrase-level-semantic-labels-to-1","title":"Constructing Phrase-level Semantic Labels to Form Multi-GrainedSupervision for Image-Text Retrieval","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":"create-a-benchmark-for-chinese-short-video","title":"CREATE: A Benchmark for Chinese Short Video Retrieval and Title Generation","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":null,"slug":"cst5-data-augmentation-for-code-switched","title":"CST5: Data augmentation for Code-Switched Semantic Parsing","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":"daml-st5-low-resource-style-transfer-via","title":"DAML-ST5: Low Resource Style Transfer via Domain Adaptive Meta Learning","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"data-augmentation-and-learned-layer","title":"Data Augmentation and Learned Layer Aggregation for Improved Multilingual Language Understanding in Dialogue","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"data-augmentation-for-intent-classification","title":"Data Augmentation for Intent Classification with Generic Large Language Models","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"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":"efficient-long-sequence-encoding-via","title":"Efficient Long Sequence Encoding via Synchronization","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":"empirical-analysis-of-training-strategies-of-1","title":"Empirical Analysis of Training Strategies of Transformer-based Japanese Chit-chat Systems","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"end-to-end-sign-language-translation-via","title":"End-To-End Sign Language Translation via Multitask Learning","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":"enhancing-the-nonlinear-mutual-dependencies","title":"Enhancing the Nonlinear Mutual Dependencies in Transformers with Mutual Information","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"ernie-sparse-learning-hierarchical-efficient","title":"ERNIE-SPARSE: Learning Hierarchical Efficient Transformer Through Regularized Self-Attention","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":"exploring-and-adapting-chinese-gpt-to-pinyin","title":"Exploring and Adapting Chinese GPT to Pinyin Input Method","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"extreme-multi-label-text-classification-with-1","title":"Extreme Multi-label Text Classification with Multi-layer Experts","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":"fast-and-accurate-transformer-based","title":"Fast and Accurate Transformer-based Translation with Character-Level Encoding and Subword-Level Decoding","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":"fix-bugs-with-transformer-through-a-neural","title":"Fix Bugs with Transformer through a Neural-Symbolic Edit Grammar","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"frsum-towards-faithful-abstractive","title":"FRSUM: Towards Faithful Abstractive Summarization via Enhancing Factual Robustness","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":"generating-diverse-and-high-quality","title":"Generating Diverse and High-Quality Abstractive Summaries with Variational Transformers","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"generation-of-news-articles-from-tweets-an","title":"Generation of News Articles from Tweets : An Experiment","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-pre-trained-transformer-for-design","title":"Generative Pre-Trained Transformer for Design Concept Generation: An Exploration","date":"2021-11-16","arxiv_id":"2111.08489","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-compositional-generalization-with-1","title":"Improving Compositional Generalization with Self-Training for Data-to-Text Generation","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-gpt-3-after-deployment-with-a","title":"Improving GPT-3 after deployment with a dynamic memory of feedback","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":"knowledge-graph-is-in-rescue-task-oriented","title":"Knowledge Graph is in Rescue: Task Oriented Dialogue System for Response Generation without NLU and DM","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-guided-transformer-for-joint-theme","title":"Knowledge-guided Transformer for Joint Theme and Emotion Classification of Chinese Classical Poetry","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":"learn-more-from-less-improving-conversational","title":"Learn More from Less: Improving Conversational Recommender Systems via Contextual and Time-Aware Modeling","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-methods-for-solving-astronomy-course","title":"Learning Methods for Solving Astronomy Course Problems","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-non-autoregressive-models-from","title":"Learning Non-Autoregressive Models from Search for Unsupervised Sentence Summarization","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":"listen-to-both-sides-and-be-enlightened","title":"Listen to Both Sides and be Enlightened! -- Hierarchical Modality Fusion Network for Entity and Relation Extraction","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":"making-transformers-solve-compositional-tasks-1","title":"Making Transformers Solve Compositional Tasks","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":"/paper/meeting-summarization-with-pre-training-and","slug":"meeting-summarization-with-pre-training-and","title":"Meeting Summarization with Pre-training and Clustering Methods","date":"2021-11-16","arxiv_id":"2111.08210","n_code_links":1,"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":"/paper/modeling-hierarchical-syntax-structure-with","slug":"modeling-hierarchical-syntax-structure-with","title":"Modeling Hierarchical Syntax Structure with Triplet Position for Source Code Summarization","date":"2021-11-16","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"moving-the-eiffel-tower-to-rome-tracing-and","title":"Moving the Eiffel Tower to ROME: Tracing and Editing Facts in GPT","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-head-or-single-head-an-empirical-1","title":"Multi-head or Single-head? An Empirical Comparison for Transformer Training","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"n-grammer-augmenting-transformers-with-latent","title":"N-grammer: Augmenting Transformers with latent n-grams","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-keyphrase-generation-analysis-and","title":"Neural Keyphrase Generation: Analysis and Evaluation","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-multilingual-capabilities-of-very-1","title":"On the Multilingual Capabilities of Very Large-Scale English Language Models","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null}],"record_sha256":"2b5c285b615f5f4dc3384cb9d008a65e14d1e71db8d21cff8b8ab5fc2798369f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}