{"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/softmax/papers/316","list_of":"/method/softmax","method":"Softmax","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":316,"pages_in_order":375,"rows_per_page":100,"rows":[31501,31600],"of":37443,"counts":{"archive_papers_tagged":37443,"with_a_code_link":15869,"where_syntology_ran_a_sample":4578,"not_listed_spam_title":0,"listed":37443,"listed_where_code_ran":4578,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3835,"every_run_a_failure_of_syntologys_instrument":743,"listed_with_a_run_with_no_instrument_failure":3835,"listed_every_run_a_failure_of_syntologys_instrument":743,"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/softmax","prev":"/method/softmax/papers/315","next":"/method/softmax/papers/317","papers":[{"paper":null,"slug":"pre-trained-language-models-as-knowledge","title":"Pre-trained language models as knowledge bases for Automotive Complaint Analysis","date":"2020-12-04","arxiv_id":"2012.02558","n_code_links":0,"syntology":null},{"paper":null,"slug":"relational-pretrained-transformers-towards","title":"RPT: Relational Pre-trained Transformer Is Almost All You Need towards Democratizing Data Preparation","date":"2020-12-04","arxiv_id":"2012.02469","n_code_links":0,"syntology":null},{"paper":null,"slug":"spread-mechanism-and-influence-measurement-of","title":"Spread Mechanism and Influence Measurement of Online Rumors in China During the COVID-19 Pandemic","date":"2020-12-04","arxiv_id":"2012.02446","n_code_links":0,"syntology":null},{"paper":null,"slug":"adapt-and-adjust-overcoming-the-long-tail-1","title":"Adapt-and-Adjust: Overcoming the Long-Tail Problem of Multilingual Speech Recognition","date":"2020-12-03","arxiv_id":"2012.01687","n_code_links":0,"syntology":null},{"paper":"/paper/bert-hlstms-bert-and-hierarchical-lstms-for","slug":"bert-hlstms-bert-and-hierarchical-lstms-for","title":"BERT-hLSTMs: BERT and Hierarchical LSTMs for Visual Storytelling","date":"2020-12-03","arxiv_id":"2012.02128","n_code_links":0,"syntology":null},{"paper":null,"slug":"circles-are-like-ellipses-or-ellipses-are","title":"Circles are like Ellipses, or Ellipses are like Circles? Measuring the Degree of Asymmetry of Static and Contextual Embeddings and the Implications to Representation Learning","date":"2020-12-03","arxiv_id":"2012.01631","n_code_links":0,"syntology":null},{"paper":"/paper/dialogbert-discourse-aware-response","slug":"dialogbert-discourse-aware-response","title":"DialogBERT: Discourse-Aware Response Generation via Learning to Recover and Rank Utterances","date":"2020-12-03","arxiv_id":"2012.01775","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"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":null}},{"paper":null,"slug":"evolving-character-level-densenet","title":"Evolving Character-Level DenseNet Architectures using Genetic Programming","date":"2020-12-03","arxiv_id":"2012.02327","n_code_links":0,"syntology":null},{"paper":null,"slug":"federated-learning-with-diversified","title":"Federated Learning for Personalized Humor Recognition","date":"2020-12-03","arxiv_id":"2012.01675","n_code_links":0,"syntology":null},{"paper":null,"slug":"gottbert-a-pure-german-language-model","title":"GottBERT: a pure German Language Model","date":"2020-12-03","arxiv_id":"2012.02110","n_code_links":0,"syntology":null},{"paper":"/paper/make-one-shot-video-object-segmentation-1","slug":"make-one-shot-video-object-segmentation-1","title":"Make One-Shot Video Object Segmentation Efficient Again","date":"2020-12-03","arxiv_id":"2012.01866","n_code_links":4,"syntology":null},{"paper":"/paper/self-explaining-structures-improve-nlp-models","slug":"self-explaining-structures-improve-nlp-models","title":"Self-Explaining Structures Improve NLP Models","date":"2020-12-03","arxiv_id":"2012.01786","n_code_links":1,"syntology":null},{"paper":"/paper/sentiment-analysis-in-bengali-via-transfer","slug":"sentiment-analysis-in-bengali-via-transfer","title":"Sentiment analysis in Bengali via transfer learning using multi-lingual BERT","date":"2020-12-03","arxiv_id":"2012.07538","n_code_links":1,"syntology":null},{"paper":null,"slug":"trace-early-detection-of-chronic-kidney","title":"TRACE: Early Detection of Chronic Kidney Disease Onset with Transformer-Enhanced Feature Embedding","date":"2020-12-03","arxiv_id":"2012.03729","n_code_links":0,"syntology":null},{"paper":null,"slug":"traffic-surveillance-using-vehicle-license","title":"Traffic Surveillance using Vehicle License Plate Detection and Recognition in Bangladesh","date":"2020-12-03","arxiv_id":"2012.02218","n_code_links":0,"syntology":null},{"paper":"/paper/triplet-entropy-loss-improving-the","slug":"triplet-entropy-loss-improving-the","title":"Triplet Entropy Loss: Improving The Generalisation of Short Speech Language Identification Systems","date":"2020-12-03","arxiv_id":"2012.03775","n_code_links":1,"syntology":null},{"paper":null,"slug":"what-makes-a-star-teacher-a-hierarchical-bert","title":"What Makes a Star Teacher? A Hierarchical BERT Model for Evaluating Teacher's Performance in Online Education","date":"2020-12-03","arxiv_id":"2012.01633","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-framework-and-dataset-for-abstract-art","title":"A Framework and Dataset for Abstract Art Generation via CalligraphyGAN","date":"2020-12-02","arxiv_id":"2012.00744","n_code_links":0,"syntology":null},{"paper":"/paper/contour-transformer-network-for-one-shot","slug":"contour-transformer-network-for-one-shot","title":"Contour Transformer Network for One-shot Segmentation of Anatomical Structures","date":"2020-12-02","arxiv_id":"2012.01480","n_code_links":1,"syntology":null},{"paper":"/paper/exploiting-bert-to-improve-aspect-based","slug":"exploiting-bert-to-improve-aspect-based","title":"Exploiting BERT to improve aspect-based sentiment analysis performance on Persian language","date":"2020-12-02","arxiv_id":"2012.07510","n_code_links":1,"syntology":null},{"paper":"/paper/how-can-we-know-when-language-models-know","slug":"how-can-we-know-when-language-models-know","title":"How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering","date":"2020-12-02","arxiv_id":"2012.00955","n_code_links":1,"syntology":null},{"paper":"/paper/learning-universal-shape-dictionary-for","slug":"learning-universal-shape-dictionary-for","title":"Learning Universal Shape Dictionary for Realtime Instance Segmentation","date":"2020-12-02","arxiv_id":"2012.01050","n_code_links":1,"syntology":null},{"paper":null,"slug":"regularization-via-adaptive-pairwise-label","title":"Regularization via Adaptive Pairwise Label Smoothing","date":"2020-12-02","arxiv_id":"2012.01559","n_code_links":0,"syntology":null},{"paper":"/paper/single-shot-lightweight-model-for-the","slug":"single-shot-lightweight-model-for-the","title":"Single-Shot Lightweight Model For The Detection of Lesions And The Prediction of COVID-19 From Chest CT Scans","date":"2020-12-02","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/two-stage-single-image-reflection-removal","slug":"two-stage-single-image-reflection-removal","title":"Two-Stage Single Image Reflection Removal with Reflection-Aware Guidance","date":"2020-12-02","arxiv_id":"2012.00945","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-deep-generative-approach-to-native-language","title":"A Deep Generative Approach to Native Language Identification","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-large-scale-corpus-of-e-mail-conversations","title":"A Large-Scale Corpus of E-mail Conversations with Standard and Two-Level Dialogue Act Annotations","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-neural-local-coherence-analysis-model-for","title":"A Neural Local Coherence Analysis Model for Clarity Text Scoring","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/adversarial-sparse-transformer-for-time","slug":"adversarial-sparse-transformer-for-time","title":"Adversarial Sparse Transformer for Time Series Forecasting","date":"2020-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/affective-and-contextual-embedding-for","slug":"affective-and-contextual-embedding-for","title":"Affective and Contextual Embedding for Sarcasm Detection","date":"2020-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"alexu-aux-bert-at-semeval-2020-task-3","title":"AlexU-AUX-BERT at SemEval-2020 Task 3: Improving BERT Contextual Similarity Using Multiple Auxiliary Contexts","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"alexu-backtranslation-tl-at-semeval-2020-task","title":"AlexU-BackTranslation-TL at SemEval-2020 Task 12: Improving Offensive Language Detection Using Data Augmentation and Transfer Learning","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"alt-at-semeval-2020-task-12-arabic-and","title":"ALT at SemEval-2020 Task 12: Arabic and English Offensive Language Identification in Social Media","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/analogy-models-for-neural-word-inflection","slug":"analogy-models-for-neural-word-inflection","title":"Analogy Models for Neural Word Inflection","date":"2020-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"arabizi-language-models-for-sentiment","title":"Arabizi Language Models for Sentiment Analysis","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"assessing-polyseme-sense-similarity-through","title":"Assessing Polyseme Sense Similarity through Co-predication Acceptability and Contextualised Embedding Distance","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/attentively-embracing-noise-for-robust-latent","slug":"attentively-embracing-noise-for-robust-latent","title":"Attentively Embracing Noise for Robust Latent Representation in BERT","date":"2020-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"bert-at-semeval-2020-task-8-using-bert-to","title":"BERT at SemEval-2020 Task 8: Using BERT to Analyse Meme Emotions","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/bert-based-cohesion-analysis-of-japanese","slug":"bert-based-cohesion-analysis-of-japanese","title":"BERT-based Cohesion Analysis of Japanese Texts","date":"2020-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"bert-based-neural-collaborative-filtering-and","title":"BERT-Based Neural Collaborative Filtering and Fixed-Length Contiguous Tokens Explanation","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"bertatde-at-semeval-2020-task-6-extracting","title":"BERTatDE at SemEval-2020 Task 6: Extracting Term-definition Pairs in Free Text Using Pre-trained Model","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"bilingual-subword-segmentation-for-neural","title":"Bilingual Subword Segmentation for Neural Machine Translation","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"blcu-nlp-at-semeval-2020-task-5-data","title":"BLCU-NLP at SemEval-2020 Task 5: Data Augmentation for Efficient Counterfactual Detecting","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"bridge-the-gap-high-level-semantic-planning","title":"Bridge the Gap: High-level Semantic Planning for Image Captioning","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"byteam-at-semeval-2020-task-5-detecting","title":"BYteam at SemEval-2020 Task 5: Detecting Counterfactual Statements with BERT and Ensembles","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cardiff-university-at-semeval-2020-task-6","title":"Cardiff University at SemEval-2020 Task 6: Fine-tuning BERT for Domain-Specific Definition Classification","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"citiusnlp-at-semeval-2020-task-3-comparing","title":"CitiusNLP at SemEval-2020 Task 3: Comparing Two Approaches for Word Vector Contextualization","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/classifier-probes-may-just-learn-from-linear","slug":"classifier-probes-may-just-learn-from-linear","title":"Classifier Probes May Just Learn from Linear Context Features","date":"2020-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"climatext-a-dataset-for-climate-change-topic","title":"ClimaText: A Dataset for Climate Change Topic Detection","date":"2020-12-01","arxiv_id":"2012.00483","n_code_links":0,"syntology":null},{"paper":null,"slug":"cn-hit-mi-t-at-semeval-2020-task-8-memotion","title":"CN-HIT-MI.T at SemEval-2020 Task 8: Memotion Analysis Based on BERT","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/cogltx-applying-bert-to-long-texts","slug":"cogltx-applying-bert-to-long-texts","title":"CogLTX: Applying BERT to Long Texts","date":"2020-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"comparing-probabilistic-distributional-and","title":"Comparing Probabilistic, Distributional and Transformer-Based Models on Logical Metonymy Interpretation","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/confluence-a-robust-non-iou-alternative-to","slug":"confluence-a-robust-non-iou-alternative-to","title":"Confluence: A Robust Non-IoU Alternative to Non-Maxima Suppression in Object Detection","date":"2020-12-01","arxiv_id":"2012.00257","n_code_links":3,"syntology":null},{"paper":"/paper/constituency-lattice-encoding-for-aspect-term","slug":"constituency-lattice-encoding-for-aspect-term","title":"Constituency Lattice Encoding for Aspect Term Extraction","date":"2020-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"contextualized-embeddings-for-enriching","title":"Contextualized Embeddings for Enriching Linguistic Analyses on Politeness","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/cpm-a-large-scale-generative-chinese-pre","slug":"cpm-a-large-scale-generative-chinese-pre","title":"CPM: A Large-scale Generative Chinese Pre-trained Language Model","date":"2020-12-01","arxiv_id":"2012.00413","n_code_links":10,"syntology":null},{"paper":null,"slug":"data-selection-for-bilingual-lexicon","title":"Data Selection for Bilingual Lexicon Induction from Specialized Comparable Corpora","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-brasil-nlp-at-semeval-2020-task-1","title":"Deep Learning Brasil - NLP at SemEval-2020 Task 9: Sentiment Analysis of Code-Mixed Tweets Using Ensemble of Language Models","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"deepyang-at-semeval-2020-task-4-using-the","title":"DEEPYANG at SemEval-2020 Task 4: Using the Hidden Layer State of BERT Model for Differentiating Common Sense","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"deftpunk-at-semeval-2020-task-6-using-rnn","title":"DeftPunk at SemEval-2020 Task 6: Using RNN-ensemble for the Sentence Classification.","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"denoising-pre-training-and-data-augmentation","title":"Denoising Pre-Training and Data Augmentation Strategies for Enhanced RDF Verbalization with Transformers","date":"2020-12-01","arxiv_id":"2012.00571","n_code_links":0,"syntology":null},{"paper":"/paper/detecting-urgency-status-of-crisis-tweets-a","slug":"detecting-urgency-status-of-crisis-tweets-a","title":"Detecting Urgency Status of Crisis Tweets: A Transfer Learning Approach for Low Resource Languages","date":"2020-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"differentiable-meta-learning-of-bandit","title":"Differentiable Meta-Learning of Bandit Policies","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"discovery-team-at-semeval-2020-task-1-context","title":"Discovery Team at SemEval-2020 Task 1: Context-sensitive Embeddings Not Always Better than Static for Semantic Change Detection","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/disentangling-label-distribution-for-long","slug":"disentangling-label-distribution-for-long","title":"Disentangling Label Distribution for Long-tailed Visual Recognition","date":"2020-12-01","arxiv_id":"2012.00321","n_code_links":2,"syntology":null},{"paper":null,"slug":"diverse-dialogue-generation-with-context","title":"Diverse dialogue generation with context dependent dynamic loss function","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"document-level-neural-machine-translation-3","title":"Document-Level Neural Machine Translation Using BERT as Context Encoder","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"domain-transfer-based-data-augmentation-for","title":"Domain Transfer based Data Augmentation for Neural Query Translation","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"don-t-invite-bert-to-drink-a-bottle-modeling","title":"Don't Invite BERT to Drink a Bottle: Modeling the Interpretation of Metonymies Using BERT and Distributional Representations","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/dual-dynamic-memory-network-for-end-to-end","slug":"dual-dynamic-memory-network-for-end-to-end","title":"Dual Dynamic Memory Network for End-to-End Multi-turn Task-oriented Dialog Systems","date":"2020-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/dynamic-feature-pyramid-networks-for-object","slug":"dynamic-feature-pyramid-networks-for-object","title":"Dynamic Feature Pyramid Networks for Object Detection","date":"2020-12-01","arxiv_id":"2012.00779","n_code_links":1,"syntology":null},{"paper":null,"slug":"embeddings-in-natural-language-processing","title":"Embeddings in Natural Language Processing","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"emotion-classification-by-jointly-learning-to","title":"Emotion Classification by Jointly Learning to Lexiconize and Classify","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"escaping-the-gravitational-pull-of-softmax","title":"Escaping the Gravitational Pull of Softmax","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-pretrained-transformer-based","title":"Evaluating Pretrained Transformer-based Models on the Task of Fine-Grained Named Entity Recognition","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-unsupervised-representation","title":"Evaluating Unsupervised Representation Learning for Detecting Stances of Fake News","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-statistical-and-neural-models-for","title":"Exploring Statistical and Neural Models for Noun Ellipsis Detection and Resolution in English","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"fastmatch-accelerating-the-inference-of-bert","title":"FASTMATCH: Accelerating the Inference of BERT-based Text Matching","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/fbk-dh-at-semeval-2020-task-12-using-multi","slug":"fbk-dh-at-semeval-2020-task-12-using-multi","title":"FBK-DH at SemEval-2020 Task 12: Using Multi-channel BERT for Multilingual Offensive Language Detection","date":"2020-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"federated-learning-for-spoken-language","title":"Federated Learning for Spoken Language Understanding","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"ferryman-at-semeval-2020-task-12-bert-based","title":"Ferryman at SemEval-2020 Task 12: BERT-Based Model with Advanced Improvement Methods for Multilingual Offensive Language Identification","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"ferryman-at-semeval-2020-task-7-ensemble","title":"Ferryman at SemEval-2020 Task 7: Ensemble Model for Assessing Humor in Edited News Headlines","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-tuning-bert-with-focus-words-for","title":"Fine-tuning BERT with Focus Words for Explanation Regeneration","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/flight-of-the-pegasus-comparing-transformers","slug":"flight-of-the-pegasus-comparing-transformers","title":"Flight of the PEGASUS? Comparing Transformers on Few-shot and Zero-shot Multi-document Abstractive Summarization","date":"2020-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"forcereader-a-bert-based-interactive-machine","title":"ForceReader: a BERT-based Interactive Machine Reading Comprehension Model with Attention Separation","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/formality-style-transfer-with-shared-latent","slug":"formality-style-transfer-with-shared-latent","title":"Formality Style Transfer with Shared Latent Space","date":"2020-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/from-hero-to-z-eroe-a-benchmark-of-low-level","slug":"from-hero-to-z-eroe-a-benchmark-of-low-level","title":"From Hero to Z\\'eroe: A Benchmark of Low-Level Adversarial Attacks","date":"2020-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"generalized-shortest-paths-encoders-for-amr","title":"Generalized Shortest-Paths Encoders for AMR-to-Text Generation","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/global-context-enhanced-graph-convolutional","slug":"global-context-enhanced-graph-convolutional","title":"Global Context-enhanced Graph Convolutional Networks for Document-level Relation Extraction","date":"2020-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"go-simple-and-pre-train-on-domain-specific","title":"Go Simple and Pre-Train on Domain-Specific Corpora: On the Role of Training Data for Text Classification","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/grubert-a-gru-based-method-to-fuse-bert","slug":"grubert-a-gru-based-method-to-fuse-bert","title":"GRUBERT: A GRU-Based Method to Fuse BERT Hidden Layers for Twitter Sentiment Analysis","date":"2020-12-01","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":"/paper/hinglishnlp-at-semeval-2020-task-9-fine-tuned","slug":"hinglishnlp-at-semeval-2020-task-9-fine-tuned","title":"HinglishNLP at SemEval-2020 Task 9: Fine-tuned Language Models for Hinglish Sentiment Detection","date":"2020-12-01","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":null,"slug":"hitachi-at-semeval-2020-task-11-an-empirical","title":"Hitachi at SemEval-2020 Task 11: An Empirical Study of Pre-Trained Transformer Family for Propaganda Detection","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"hitachi-at-semeval-2020-task-7-stacking-at","title":"Hitachi at SemEval-2020 Task 7: Stacking at Scale with Heterogeneous Language Models for Humor Recognition","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"hitachi-at-semeval-2020-task-8-simple-but","title":"Hitachi at SemEval-2020 Task 8: Simple but Effective Modality Ensemble for Meme Emotion Recognition","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/hitrans-a-transformer-based-context-and","slug":"hitrans-a-transformer-based-context-and","title":"HiTrans: A Transformer-Based Context- and Speaker-Sensitive Model for Emotion Detection in Conversations","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"how-far-does-bert-look-at-distance-based-1","title":"How Far Does BERT Look At: Distance-based Clustering and Analysis of BERT's Attention","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/how-relevant-are-selectional-preferences-for","slug":"how-relevant-are-selectional-preferences-for","title":"How Relevant Are Selectional Preferences for Transformer-based Language Models?","date":"2020-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"hr-just-team-at-semeval-2020-task-4-the","title":"HR@JUST Team at SemEval-2020 Task 4: The Impact of RoBERTa Transformer for Evaluation Common Sense Understanding","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/hy-nli-a-hybrid-system-for-natural-language","slug":"hy-nli-a-hybrid-system-for-natural-language","title":"Hy-NLI: a Hybrid system for Natural Language Inference","date":"2020-12-01","arxiv_id":null,"n_code_links":2,"syntology":null}],"record_sha256":"4d3c36eb37809ff43ecbbf1495184f6579e0d7f373b67536f3768a60c4111069","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}