{"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":"/task/language-modeling/papers/122","list_of":"/task/language-modeling","task":"Language Modeling","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":122,"pages_in_order":142,"rows_per_page":100,"rows":[12101,12200],"of":14182,"counts":{"archive_papers_tagged":14182,"with_a_code_link":5620,"where_syntology_ran_a_sample":1894,"not_listed_spam_title":0,"listed":14182,"listed_where_code_ran":1894,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1580,"every_run_a_failure_of_syntologys_instrument":314,"listed_with_a_run_with_no_instrument_failure":1580,"listed_every_run_a_failure_of_syntologys_instrument":314,"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":"/task/language-modeling","prev":"/task/language-modeling/papers/121","next":"/task/language-modeling/papers/123","papers":[{"url":null,"slug":"one-teacher-is-enough-pre-trained-language","title":"One Teacher is Enough? Pre-trained Language Model Distillation from Multiple Teachers","date":"2021-06-02","arxiv_id":"2106.01023","repositories_listed":0,"syntology":null},{"url":"/paper/topic-driven-and-knowledge-aware-transformer","slug":"topic-driven-and-knowledge-aware-transformer","title":"Topic-Driven and Knowledge-Aware Transformer for Dialogue Emotion Detection","date":"2021-06-02","arxiv_id":"2106.01071","repositories_listed":0,"syntology":null},{"url":null,"slug":"ad-headline-generation-using-self-critical","title":"Ad Headline Generation using Self-Critical Masked Language Model","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"adversities-are-all-you-need-classification","title":"Adversities are all you need: Classification of self-reported breast cancer posts on Twitter using Adversarial Fine-tuning","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"classification-extraction-and-normalization","title":"Classification, Extraction, and Normalization : CASIA_Unisound Team at the Social Media Mining for Health 2021 Shared Tasks","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"classification-of-tweets-self-reporting","title":"Classification of Tweets Self-reporting Adverse Pregnancy Outcomes and Potential COVID-19 Cases Using RoBERTa Transformers","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"damascusteam-at-nlp4if2021-fighting-the","title":"DamascusTeam at NLP4IF2021: Fighting the Arabic COVID-19 Infodemic on Twitter Using AraBERT","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ernie-nli-analyzing-the-impact-of-domain","title":"ERNIE-NLI: Analyzing the Impact of Domain-Specific External Knowledge on Enhanced Representations for NLI","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"explainable-multi-hop-verbal-reasoning","title":"Explainable Multi-hop Verbal Reasoning Through Internal Monologue","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"flowprior-learning-expressive-priors-for","title":"FlowPrior: Learning Expressive Priors for Latent Variable Sentence Models","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-and-evaluating-a-differentially","title":"Learning and Evaluating a Differentially Private Pre-trained Language Model","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"longsumm-2021-session-based-automatic","title":"LongSumm 2021: Session based automatic summarization model for scientific document","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"low-resource-machine-translation-using-cross","title":"Low-Resource Machine Translation Using Cross-Lingual Language Model Pretraining","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mg-bert-multi-graph-augmented-bert-for-masked","title":"MG-BERT: Multi-Graph Augmented BERT for Masked Language Modeling","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"nutri-bullets-hybrid-consensual-multi","title":"Nutri-bullets Hybrid: Consensual Multi-document Summarization","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"on-randomized-classification-layers-and-their","title":"On Randomized Classification Layers and Their Implications in Natural Language Generation","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"piglet-language-grounding-through-neuro","title":"PIGLeT: Language Grounding Through Neuro-Symbolic Interaction in a 3D World","date":"2021-06-01","arxiv_id":"2106.00188","repositories_listed":0,"syntology":null},{"url":null,"slug":"predicting-numerals-in-natural-language-text","title":"Predicting Numerals in Natural Language Text Using a Language Model Considering the Quantitative Aspects of Numerals","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"script-self-critic-pretraining-of","title":"SCRIPT: Self-Critic PreTraining of Transformers","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"system-description-for-profner-smmh-optimized","title":"System description for ProfNER - SMMH: Optimized finetuning of a pretrained transformer and word vectors","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"target-aware-data-augmentation-for-stance","title":"Target-Aware Data Augmentation for Stance Detection","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"transferring-representations-of-logical","title":"Transferring Representations of Logical Connectives","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-domain-adaptation-in-cross","title":"Unsupervised Domain Adaptation in Cross-corpora Abusive Language Detection","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"language-model-evaluation-beyond-perplexity","title":"Language Model Evaluation Beyond Perplexity","date":"2021-05-31","arxiv_id":"2106.00085","repositories_listed":0,"syntology":null},{"url":null,"slug":"picking-pearl-from-seabed-extracting","title":"Picking Pearl From Seabed: Extracting Artefacts from Noisy Issue Triaging Collaborative Conversations for Hybrid Cloud Services","date":"2021-05-31","arxiv_id":"2105.15065","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-summarization-with-latent-queries","title":"Text Summarization with Latent Queries","date":"2021-05-31","arxiv_id":"2106.00104","repositories_listed":0,"syntology":null},{"url":null,"slug":"predictive-representation-learning-for","title":"Predictive Representation Learning for Language Modeling","date":"2021-05-29","arxiv_id":"2105.14214","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-code-mixed-modern-standard","title":"Investigating Code-Mixed Modern Standard Arabic-Egyptian to English Machine Translation","date":"2021-05-28","arxiv_id":"2105.13573","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-linguistic-coordination-in","title":"Leveraging Linguistic Coordination in Reranking N-Best Candidates For End-to-End Response Selection Using BERT","date":"2021-05-27","arxiv_id":"2105.13479","repositories_listed":0,"syntology":null},{"url":null,"slug":"sgpt-semantic-graphs-based-pre-training-for","title":"SGPT: Semantic Graphs based Pre-training for Aspect-based Sentiment Analysis","date":"2021-05-26","arxiv_id":"2105.12305","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-an-imu-based-pen-online-handwriting","title":"Towards an IMU-based Pen Online Handwriting Recognizer","date":"2021-05-26","arxiv_id":"2105.12434","repositories_listed":0,"syntology":null},{"url":null,"slug":"pre-trained-language-model-based-ranking-in","title":"Pre-trained Language Model based Ranking in Baidu Search","date":"2021-05-24","arxiv_id":"2105.11108","repositories_listed":0,"syntology":null},{"url":null,"slug":"lmsoc-an-approach-for-socially-sensitive-1","title":"LMSOC: An approach for socially sensitive pretraining","date":"2021-05-22","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"aligning-visual-prototypes-with-bert","title":"Aligning Visual Prototypes with BERT Embeddings for Few-Shot Learning","date":"2021-05-21","arxiv_id":"2105.10195","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-multilingual-sentence-embeddings-1","title":"Unsupervised Multilingual Sentence Embeddings for Parallel Corpus Mining","date":"2021-05-21","arxiv_id":"2105.10419","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerating-gossip-sgd-with-periodic-global","title":"Accelerating Gossip SGD with Periodic Global Averaging","date":"2021-05-19","arxiv_id":"2105.09080","repositories_listed":0,"syntology":null},{"url":null,"slug":"sentence-similarity-based-on-contexts","title":"Sentence Similarity Based on Contexts","date":"2021-05-17","arxiv_id":"2105.07623","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-based-personality-prediction-from","title":"Text based personality prediction from multiple social media data sources using pre-trained language model and model averaging","date":"2021-05-17","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-predictive-text-for-grammatical-error","title":"Neural Predictive Text for Grammatical Error Prevention","date":"2021-05-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sina-bert-a-pre-trained-language-model-for-1","title":"SINA-BERT: A Pre-Trained Language Model for Analysis of Medical Texts in Persian","date":"2021-05-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-cognitive-regularizer-for-language-modeling","title":"A Cognitive Regularizer for Language Modeling","date":"2021-05-15","arxiv_id":"2105.07144","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-human-free-automatic-quality","title":"Towards Human-Free Automatic Quality Evaluation of German Summarization","date":"2021-05-13","arxiv_id":"2105.06027","repositories_listed":0,"syntology":null},{"url":null,"slug":"slower-is-better-revisiting-the-forgetting","title":"Slower is Better: Revisiting the Forgetting Mechanism in LSTM for Slower Information Decay","date":"2021-05-12","arxiv_id":"2105.05944","repositories_listed":0,"syntology":null},{"url":null,"slug":"computer-aided-design-as-language","title":"Computer-Aided Design as Language","date":"2021-05-06","arxiv_id":"2105.02769","repositories_listed":0,"syntology":null},{"url":null,"slug":"herbert-efficiently-pretrained-transformer","title":"HerBERT: Efficiently Pretrained Transformer-based Language Model for Polish","date":"2021-05-04","arxiv_id":"2105.01735","repositories_listed":0,"syntology":null},{"url":null,"slug":"goldilocks-just-right-tuning-of-bert-for","title":"Goldilocks: Just-Right Tuning of BERT for Technology-Assisted Review","date":"2021-05-03","arxiv_id":"2105.01044","repositories_listed":0,"syntology":null},{"url":null,"slug":"impact-of-gender-debiased-word-embeddings-in","title":"Impact of Gender Debiased Word Embeddings in Language Modeling","date":"2021-05-03","arxiv_id":"2105.00908","repositories_listed":0,"syntology":null},{"url":"/paper/on-the-limit-of-english-conversational-speech","slug":"on-the-limit-of-english-conversational-speech","title":"On the limit of English conversational speech recognition","date":"2021-05-03","arxiv_id":"2105.00982","repositories_listed":0,"syntology":null},{"url":null,"slug":"larger-scale-transformers-for-multilingual","title":"Larger-Scale Transformers for Multilingual Masked Language Modeling","date":"2021-05-02","arxiv_id":"2105.00572","repositories_listed":0,"syntology":null},{"url":null,"slug":"its-basically-the-same-language-anyway-the","title":"It’s Basically the Same Language Anyway: the Case for a Nordic Language Model","date":"2021-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"measuring-translationese-across-levels-of","title":"Measuring Translationese across Levels of Expertise: Are Professionals more Surprising than Students?","date":"2021-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-interspeech-zero-resource-speech","title":"The Zero Resource Speech Challenge 2021: Spoken language modelling","date":"2021-04-29","arxiv_id":"2104.14700","repositories_listed":0,"syntology":null},{"url":null,"slug":"extractive-and-abstractive-explanations-for","title":"Extractive and Abstractive Explanations for Fact-Checking and Evaluation of News","date":"2021-04-27","arxiv_id":"2104.12918","repositories_listed":0,"syntology":null},{"url":null,"slug":"diverse-image-inpainting-with-bidirectional","title":"Diverse Image Inpainting with Bidirectional and Autoregressive Transformers","date":"2021-04-26","arxiv_id":"2104.12335","repositories_listed":0,"syntology":null},{"url":null,"slug":"teaching-a-massive-open-online-course-on","title":"Teaching a Massive Open Online Course on Natural Language Processing","date":"2021-04-26","arxiv_id":"2104.12846","repositories_listed":0,"syntology":null},{"url":null,"slug":"reranking-machine-translation-hypotheses-with","title":"Reranking Machine Translation Hypotheses with Structured and Web-based Language Models","date":"2021-04-25","arxiv_id":"2104.12277","repositories_listed":0,"syntology":null},{"url":null,"slug":"transfer-training-from-smaller-language-model","title":"Transfer training from smaller language model","date":"2021-04-23","arxiv_id":"2104.11390","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-text-only-domain-adaptation-of-rnn","title":"Fast Text-Only Domain Adaptation of RNN-Transducer Prediction Network","date":"2021-04-22","arxiv_id":"2104.11127","repositories_listed":0,"syntology":null},{"url":null,"slug":"extracting-adverse-drug-events-from-clinical","title":"Extracting Adverse Drug Events from Clinical Notes","date":"2021-04-21","arxiv_id":"2104.10791","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-sampling-based-training-criteria-for","title":"On Sampling-Based Training Criteria for Neural Language Modeling","date":"2021-04-21","arxiv_id":"2104.10507","repositories_listed":0,"syntology":null},{"url":null,"slug":"pre-training-for-spoken-language","title":"Pre-training for Spoken Language Understanding with Joint Textual and Phonetic Representation Learning","date":"2021-04-21","arxiv_id":"2104.10357","repositories_listed":0,"syntology":null},{"url":"/paper/bertic-the-transformer-language-model-for","slug":"bertic-the-transformer-language-model-for","title":"BERTić -- The Transformer Language Model for Bosnian, Croatian, Montenegrin and Serbian","date":"2021-04-19","arxiv_id":"2104.09243","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-chinese-video-and-language-via","title":"Understanding Chinese Video and Language via Contrastive Multimodal Pre-Training","date":"2021-04-19","arxiv_id":"2104.09411","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-influence-of-masking-policies-in","title":"On the Influence of Masking Policies in Intermediate Pre-training","date":"2021-04-18","arxiv_id":"2104.08840","repositories_listed":0,"syntology":null},{"url":"/paper/back-to-square-one-bias-detection-training","slug":"back-to-square-one-bias-detection-training","title":"Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema","date":"2021-04-16","arxiv_id":"2104.08161","repositories_listed":0,"syntology":null},{"url":null,"slug":"enriching-a-model-s-notion-of-belief-using-a","title":"Enriching a Model's Notion of Belief using a Persistent Memory","date":"2021-04-16","arxiv_id":"2104.08401","repositories_listed":0,"syntology":null},{"url":null,"slug":"sina-bert-a-pre-trained-language-model-for","title":"SINA-BERT: A pre-trained Language Model for Analysis of Medical Texts in Persian","date":"2021-04-15","arxiv_id":"2104.07613","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-scale-self-and-semi-supervised-learning","title":"Large-Scale Self- and Semi-Supervised Learning for Speech Translation","date":"2021-04-14","arxiv_id":"2104.06678","repositories_listed":0,"syntology":null},{"url":null,"slug":"masked-language-modeling-and-the","title":"Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little","date":"2021-04-14","arxiv_id":"2104.06644","repositories_listed":0,"syntology":null},{"url":null,"slug":"mean-squared-accuracy-of-good-turing","title":"Mean-Squared Accuracy of Good-Turing Estimator","date":"2021-04-14","arxiv_id":"2104.07029","repositories_listed":0,"syntology":null},{"url":null,"slug":"restoring-and-mining-the-records-of-the","title":"Restoring and Mining the Records of the Joseon Dynasty via Neural Language Modeling and Machine Translation","date":"2021-04-13","arxiv_id":"2104.05964","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformer-based-methods-for-recognizing","title":"Transformer-based Methods for Recognizing Ultra Fine-grained Entities (RUFES)","date":"2021-04-13","arxiv_id":"2104.06048","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-s-in-your-head-emergent-behaviour-in","title":"What's in your Head? Emergent Behaviour in Multi-Task Transformer Models","date":"2021-04-13","arxiv_id":"2104.06129","repositories_listed":0,"syntology":null},{"url":null,"slug":"estimating-subjective-crowd-evaluations-as-an","title":"Estimating Subjective Crowd-Evaluations as an Additional Objective to Improve Natural Language Generation","date":"2021-04-12","arxiv_id":"2104.05224","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-methods-to-improve-language","title":"Investigating Methods to Improve Language Model Integration for Attention-based Encoder-Decoder ASR Models","date":"2021-04-12","arxiv_id":"2104.05544","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-model-fusion-for-streaming-end-to","title":"Language model fusion for streaming end to end speech recognition","date":"2021-04-09","arxiv_id":"2104.04487","repositories_listed":0,"syntology":null},{"url":null,"slug":"lookup-table-recurrent-language-models-for","title":"Lookup-Table Recurrent Language Models for Long Tail Speech Recognition","date":"2021-04-09","arxiv_id":"2104.04552","repositories_listed":0,"syntology":null},{"url":null,"slug":"extended-parallel-corpus-for-amharic-english","title":"Extended Parallel Corpus for Amharic-English Machine Translation","date":"2021-04-08","arxiv_id":"2104.03543","repositories_listed":0,"syntology":null},{"url":null,"slug":"interpreting-a-pre-trained-model-is-a-key-for","title":"Interpreting A Pre-trained Model Is A Key For Model Architecture Optimization: A Case Study On Wav2Vec 2.0","date":"2021-04-07","arxiv_id":"2104.02851","repositories_listed":0,"syntology":null},{"url":null,"slug":"pushing-the-limits-of-non-autoregressive","title":"Pushing the Limits of Non-Autoregressive Speech Recognition","date":"2021-04-07","arxiv_id":"2104.03416","repositories_listed":0,"syntology":null},{"url":null,"slug":"communication-efficient-agnostic-federated","title":"Communication-Efficient Agnostic Federated Averaging","date":"2021-04-06","arxiv_id":"2104.02748","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextualized-streaming-end-to-end-speech","title":"Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion","date":"2021-04-05","arxiv_id":"2104.02194","repositories_listed":0,"syntology":null},{"url":null,"slug":"covid-19-sentiment-analysis-via-deep-learning","title":"COVID-19 sentiment analysis via deep learning during the rise of novel cases","date":"2021-04-05","arxiv_id":"2104.10662","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-distance-a-new-metric-for-asr","title":"Semantic Distance: A New Metric for ASR Performance Analysis Towards Spoken Language Understanding","date":"2021-04-05","arxiv_id":"2104.02138","repositories_listed":0,"syntology":null},{"url":"/paper/speechstew-simply-mix-all-available-speech","slug":"speechstew-simply-mix-all-available-speech","title":"SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network","date":"2021-04-05","arxiv_id":"2104.02133","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-automated-psychotherapy-via-language","title":"Towards Automated Psychotherapy via Language Modeling","date":"2021-04-05","arxiv_id":"2104.10661","repositories_listed":0,"syntology":null},{"url":null,"slug":"indt5-a-text-to-text-transformer-for-10","title":"IndT5: A Text-to-Text Transformer for 10 Indigenous Languages","date":"2021-04-04","arxiv_id":"2104.07483","repositories_listed":0,"syntology":null},{"url":null,"slug":"transfornn-capturing-the-sequential","title":"TransfoRNN: Capturing the Sequential Information in Self-Attention Representations for Language Modeling","date":"2021-04-04","arxiv_id":"2104.01572","repositories_listed":0,"syntology":null},{"url":null,"slug":"arabic-compact-language-modelling-for","title":"Arabic Compact Language Modelling for Resource Limited Devices","date":"2021-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bertic-the-transformer-language-model-for-1","title":"BERTić - The Transformer Language Model for Bosnian, Croatian, Montenegrin and Serbian","date":"2021-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"detecting-over-under-translation-errors-for","title":"Detecting over/under-translation errors for determining adequacy in human translations","date":"2021-04-01","arxiv_id":"2104.00267","repositories_listed":0,"syntology":null},{"url":null,"slug":"dlrg-dravidianlangtech-eacl2021-transformer","title":"DLRG@DravidianLangTech-EACL2021: Transformer based approachfor Offensive Language Identification on Code-Mixed Tamil","date":"2021-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"does-she-wink-or-does-she-nod-a-challenging","title":"Does She Wink or Does She Nod? A Challenging Benchmark for Evaluating Word Understanding of Language Models","date":"2021-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-unsupervised-nmt-for-related","title":"Efficient Unsupervised NMT for Related Languages with Cross-Lingual Language Models and Fidelity Objectives","date":"2021-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"emotional-robbert-and-insensitive-bertje","title":"Emotional RobBERT and Insensitive BERTje: Combining Transformers and Affect Lexica for Dutch Emotion Detection","date":"2021-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"expressive-text-to-speech-using-style-tag","title":"Expressive Text-to-Speech using Style Tag","date":"2021-04-01","arxiv_id":"2104.00436","repositories_listed":0,"syntology":null},{"url":null,"slug":"globalizing-bert-based-transformer","title":"Globalizing BERT-based Transformer Architectures for Long Document Summarization","date":"2021-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"introducing-a-large-tunisian-arabizi","title":"Introducing A large Tunisian Arabizi Dialectal Dataset for Sentiment Analysis","date":"2021-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"is-supervised-syntactic-parsing-beneficial-1","title":"Is Supervised Syntactic Parsing Beneficial for Language Understanding Tasks? An Empirical Investigation","date":"2021-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"maoqin-dravidianlangtech-eacl2021-the","title":"Maoqin @ DravidianLangTech-EACL2021: The Application of Transformer-Based Model","date":"2021-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"2c928022cbc492c262cee9e49d5978cab594d3d08dc93a722ea1dff7ef9a305d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}