{"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-modelling/papers/135","list_of":"/task/language-modelling","task":"Language Modelling","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":135,"pages_in_order":177,"rows_per_page":100,"rows":[13401,13500],"of":17610,"counts":{"archive_papers_tagged":17610,"with_a_code_link":7012,"where_syntology_ran_a_sample":2428,"not_listed_spam_title":0,"listed":17610,"listed_where_code_ran":2428,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2027,"every_run_a_failure_of_syntologys_instrument":401,"listed_with_a_run_with_no_instrument_failure":2027,"listed_every_run_a_failure_of_syntologys_instrument":401,"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-modelling","prev":"/task/language-modelling/papers/134","next":"/task/language-modelling/papers/136","papers":[{"url":null,"slug":"a-semi-supervised-approach-for-a-better","title":"A Semi-supervised Approach for a Better Translation of Sentiment in Dialectical Arabic UGT","date":"2022-10-21","arxiv_id":"2210.11899","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-lstm-spoken-term-detection-using-wav2vec","title":"Deep LSTM Spoken Term Detection using Wav2Vec 2.0 Recognizer","date":"2022-10-21","arxiv_id":"2210.11885","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-encoder-decoder-redundant-for-neural","title":"Is Encoder-Decoder Redundant for Neural Machine Translation?","date":"2022-10-21","arxiv_id":"2210.11807","repositories_listed":0,"syntology":null},{"url":null,"slug":"litevl-efficient-video-language-learning-with","title":"LiteVL: Efficient Video-Language Learning with Enhanced Spatial-Temporal Modeling","date":"2022-10-21","arxiv_id":"2210.11929","repositories_listed":0,"syntology":null},{"url":null,"slug":"littlebird-efficient-faster-longer","title":"LittleBird: Efficient Faster & Longer Transformer for Question Answering","date":"2022-10-21","arxiv_id":"2210.11870","repositories_listed":0,"syntology":null},{"url":null,"slug":"spabert-a-pretrained-language-model-from","title":"SpaBERT: A Pretrained Language Model from Geographic Data for Geo-Entity Representation","date":"2022-10-21","arxiv_id":"2210.12213","repositories_listed":0,"syntology":null},{"url":"/paper/transcending-scaling-laws-with-0-1-extra","slug":"transcending-scaling-laws-with-0-1-extra","title":"Transcending Scaling Laws with 0.1% Extra Compute","date":"2022-10-20","arxiv_id":"2210.11399","repositories_listed":0,"syntology":null},{"url":null,"slug":"separating-grains-from-the-chaff-using-data","title":"Separating Grains from the Chaff: Using Data Filtering to Improve Multilingual Translation for Low-Resourced African Languages","date":"2022-10-19","arxiv_id":"2210.10692","repositories_listed":0,"syntology":null},{"url":null,"slug":"two-turn-debate-doesn-t-help-humans-answer","title":"Two-Turn Debate Doesn't Help Humans Answer Hard Reading Comprehension Questions","date":"2022-10-19","arxiv_id":"2210.10860","repositories_listed":0,"syntology":null},{"url":null,"slug":"aligning-magma-by-few-shot-learning-and","title":"Aligning MAGMA by Few-Shot Learning and Finetuning","date":"2022-10-18","arxiv_id":"2210.14161","repositories_listed":0,"syntology":null},{"url":null,"slug":"hidden-state-variability-of-pretrained","title":"Hidden State Variability of Pretrained Language Models Can Guide Computation Reduction for Transfer Learning","date":"2022-10-18","arxiv_id":"2210.10041","repositories_listed":0,"syntology":null},{"url":"/paper/swinv2-imagen-hierarchical-vision-transformer","slug":"swinv2-imagen-hierarchical-vision-transformer","title":"Swinv2-Imagen: Hierarchical Vision Transformer Diffusion Models for Text-to-Image Generation","date":"2022-10-18","arxiv_id":"2210.09549","repositories_listed":0,"syntology":null},{"url":null,"slug":"systematicity-in-gpt-3-s-interpretation-of","title":"Systematicity in GPT-3's Interpretation of Novel English Noun Compounds","date":"2022-10-18","arxiv_id":"2210.09492","repositories_listed":0,"syntology":null},{"url":null,"slug":"tiny-attention-adapter-contexts-are-more","title":"Tiny-Attention Adapter: Contexts Are More Important Than the Number of Parameters","date":"2022-10-18","arxiv_id":"2211.01979","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-bert-do-it-controller-area-network","title":"CAN-BERT do it? Controller Area Network Intrusion Detection System based on BERT Language Model","date":"2022-10-17","arxiv_id":"2210.09439","repositories_listed":0,"syntology":null},{"url":null,"slug":"continuous-pseudo-labeling-from-the-start","title":"Continuous Pseudo-Labeling from the Start","date":"2022-10-17","arxiv_id":"2210.08711","repositories_listed":0,"syntology":null},{"url":null,"slug":"sgram-improving-scene-graph-parsing-via","title":"SGRAM: Improving Scene Graph Parsing via Abstract Meaning Representation","date":"2022-10-17","arxiv_id":"2210.08675","repositories_listed":0,"syntology":null},{"url":null,"slug":"acoustic-aware-non-autoregressive-spell","title":"Acoustic-aware Non-autoregressive Spell Correction with Mask Sample Decoding","date":"2022-10-16","arxiv_id":"2210.08665","repositories_listed":0,"syntology":null},{"url":null,"slug":"aralegal-bert-a-pretrained-language-model-for","title":"AraLegal-BERT: A pretrained language model for Arabic Legal text","date":"2022-10-15","arxiv_id":"2210.08284","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-generation-models-can-cause-harm-so","title":"Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey","date":"2022-10-14","arxiv_id":"2210.07700","repositories_listed":0,"syntology":null},{"url":null,"slug":"levoice-asr-systems-for-the-iscslp-2022","title":"LeVoice ASR Systems for the ISCSLP 2022 Intelligent Cockpit Speech Recognition Challenge","date":"2022-10-14","arxiv_id":"2210.07749","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-preference-learning-for-storytelling","title":"Robust Preference Learning for Storytelling via Contrastive Reinforcement Learning","date":"2022-10-14","arxiv_id":"2210.07792","repositories_listed":0,"syntology":null},{"url":null,"slug":"assessing-out-of-domain-language-model","title":"Assessing Out-of-Domain Language Model Performance from Few Examples","date":"2022-10-13","arxiv_id":"2210.06725","repositories_listed":0,"syntology":null},{"url":null,"slug":"dungeons-and-dragons-as-a-dialog-challenge","title":"Dungeons and Dragons as a Dialog Challenge for Artificial Intelligence","date":"2022-10-13","arxiv_id":"2210.07109","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-zero-resource-speech-recognition","title":"Multilingual Zero Resource Speech Recognition Base on Self-Supervise Pre-Trained Acoustic Models","date":"2022-10-13","arxiv_id":"2210.06936","repositories_listed":0,"syntology":null},{"url":null,"slug":"neuro-symbolic-explainable-artificial","title":"Neuro-symbolic Explainable Artificial Intelligence Twin for Zero-touch IoE in Wireless Network","date":"2022-10-13","arxiv_id":"2210.06649","repositories_listed":0,"syntology":null},{"url":null,"slug":"query-expansion-using-contextual-clue","title":"Query Expansion Using Contextual Clue Sampling with Language Models","date":"2022-10-13","arxiv_id":"2210.07093","repositories_listed":0,"syntology":null},{"url":null,"slug":"spontaneous-emerging-preference-in-two-tower","title":"Spontaneous Emerging Preference in Two-tower Language Model","date":"2022-10-13","arxiv_id":"2210.07041","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-covid-that-wasn-t-counterfactual","title":"The COVID That Wasn't: Counterfactual Journalism Using GPT","date":"2022-10-13","arxiv_id":"2210.06644","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-generation-improves-open-domain","title":"Context Generation Improves Open Domain Question Answering","date":"2022-10-12","arxiv_id":"2210.06349","repositories_listed":0,"syntology":null},{"url":null,"slug":"datscore-evaluating-translation-with-data","title":"DATScore: Evaluating Translation with Data Augmented Translations","date":"2022-10-12","arxiv_id":"2210.06576","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-text-style-transfer-via-style-masked","title":"On Text Style Transfer via Style Masked Language Models","date":"2022-10-12","arxiv_id":"2210.06394","repositories_listed":0,"syntology":null},{"url":null,"slug":"decoupled-context-processing-for-context","title":"Decoupled Context Processing for Context Augmented Language Modeling","date":"2022-10-11","arxiv_id":"2210.05758","repositories_listed":0,"syntology":null},{"url":null,"slug":"legal-element-oriented-modeling-with-multi","title":"Legal Element-oriented Modeling with Multi-view Contrastive Learning for Legal Case Retrieval","date":"2022-10-11","arxiv_id":"2210.05188","repositories_listed":0,"syntology":null},{"url":null,"slug":"like-a-bilingual-baby-the-advantage-of","title":"Like a bilingual baby: The advantage of visually grounding a bilingual language model","date":"2022-10-11","arxiv_id":"2210.05487","repositories_listed":0,"syntology":null},{"url":null,"slug":"mind-s-eye-grounded-language-model-reasoning","title":"Mind's Eye: Grounded Language Model Reasoning through Simulation","date":"2022-10-11","arxiv_id":"2210.05359","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-bert-has-an-accent-evaluating","title":"Multilingual BERT has an accent: Evaluating English influences on fluency in multilingual models","date":"2022-10-11","arxiv_id":"2210.05619","repositories_listed":0,"syntology":null},{"url":null,"slug":"retrieval-augmentation-for-t5-re-ranker-using","title":"Retrieval Augmentation for T5 Re-ranker using External Sources","date":"2022-10-11","arxiv_id":"2210.05145","repositories_listed":0,"syntology":null},{"url":null,"slug":"robustify-transformers-with-robust-kernel","title":"Designing Robust Transformers using Robust Kernel Density Estimation","date":"2022-10-11","arxiv_id":"2210.05794","repositories_listed":0,"syntology":null},{"url":null,"slug":"word-sense-induction-with-hierarchical","title":"Word Sense Induction with Hierarchical Clustering and Mutual Information Maximization","date":"2022-10-11","arxiv_id":"2210.05422","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-clip-and-stylegan-through-latent","title":"Bridging CLIP and StyleGAN through Latent Alignment for Image Editing","date":"2022-10-10","arxiv_id":"2210.04506","repositories_listed":0,"syntology":null},{"url":"/paper/do-children-texts-hold-the-key-to-commonsense","slug":"do-children-texts-hold-the-key-to-commonsense","title":"Do Children Texts Hold The Key To Commonsense Knowledge?","date":"2022-10-10","arxiv_id":"2210.04530","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-key-information-modeling-to","title":"Leveraging Key Information Modeling to Improve Less-Data Constrained News Headline Generation via Duality Fine-Tuning","date":"2022-10-10","arxiv_id":"2210.04473","repositories_listed":0,"syntology":null},{"url":null,"slug":"readability-controllable-biomedical-document","title":"Readability Controllable Biomedical Document Summarization","date":"2022-10-10","arxiv_id":"2210.04705","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-up-probabilistic-circuits-by-latent","title":"Scaling Up Probabilistic Circuits by Latent Variable Distillation","date":"2022-10-10","arxiv_id":"2210.04398","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-minimum-wage-as-an-anchor-effects-on","title":"The Minimum Wage as an Anchor: Effects on Determinations of Fairness by Humans and AI","date":"2022-10-10","arxiv_id":"2210.10585","repositories_listed":0,"syntology":null},{"url":null,"slug":"improve-transformer-pre-training-with","title":"Better Pre-Training by Reducing Representation Confusion","date":"2022-10-09","arxiv_id":"2210.04246","repositories_listed":0,"syntology":null},{"url":null,"slug":"qascore-an-unsupervised-unreferenced-metric","title":"QAScore -- An Unsupervised Unreferenced Metric for the Question Generation Evaluation","date":"2022-10-09","arxiv_id":"2210.04320","repositories_listed":0,"syntology":null},{"url":null,"slug":"alphatuning-quantization-aware-parameter","title":"AlphaTuning: Quantization-Aware Parameter-Efficient Adaptation of Large-Scale Pre-Trained Language Models","date":"2022-10-08","arxiv_id":"2210.03858","repositories_listed":0,"syntology":null},{"url":null,"slug":"in-context-policy-iteration","title":"Large Language Models can Implement Policy Iteration","date":"2022-10-07","arxiv_id":"2210.03821","repositories_listed":0,"syntology":null},{"url":null,"slug":"novice-type-error-diagnosis-with-natural","title":"Novice Type Error Diagnosis with Natural Language Models","date":"2022-10-07","arxiv_id":"2210.03682","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-interventions-to-improve-out-of","title":"Using Interventions to Improve Out-of-Distribution Generalization of Text-Matching Recommendation Systems","date":"2022-10-07","arxiv_id":"2210.10636","repositories_listed":0,"syntology":null},{"url":null,"slug":"conversational-semantic-role-labeling-with","title":"Conversational Semantic Role Labeling with Predicate-Oriented Latent Graph","date":"2022-10-06","arxiv_id":"2210.03037","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-large-scale-paraphrase-acquisition","title":"Improving Large-scale Paraphrase Acquisition and Generation","date":"2022-10-06","arxiv_id":"2210.03235","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompt-compression-and-contrastive","title":"Prompt Compression and Contrastive Conditioning for Controllability and Toxicity Reduction in Language Models","date":"2022-10-06","arxiv_id":"2210.03162","repositories_listed":0,"syntology":null},{"url":null,"slug":"q-lstm-language-model-decentralized-quantum","title":"PQLM -- Multilingual Decentralized Portable Quantum Language Model for Privacy Protection","date":"2022-10-06","arxiv_id":"2210.03221","repositories_listed":0,"syntology":null},{"url":"/paper/vision-transformer-based-model-for-describing","slug":"vision-transformer-based-model-for-describing","title":"Vision Transformer Based Model for Describing a Set of Images as a Story","date":"2022-10-06","arxiv_id":"2210.02762","repositories_listed":0,"syntology":null},{"url":null,"slug":"antibody-representation-learning-for-drug","title":"Antibody Representation Learning for Drug Discovery","date":"2022-10-05","arxiv_id":"2210.02881","repositories_listed":0,"syntology":null},{"url":null,"slug":"honest-students-from-untrusted-teachers","title":"Honest Students from Untrusted Teachers: Learning an Interpretable Question-Answering Pipeline from a Pretrained Language Model","date":"2022-10-05","arxiv_id":"2210.02498","repositories_listed":0,"syntology":null},{"url":null,"slug":"revisiting-syllables-in-language-modelling","title":"Revisiting Syllables in Language Modelling and their Application on Low-Resource Machine Translation","date":"2022-10-05","arxiv_id":"2210.02509","repositories_listed":0,"syntology":null},{"url":null,"slug":"enriching-vulnerability-reports-through","title":"Enriching Vulnerability Reports Through Automated and Augmented Description Summarization","date":"2022-10-03","arxiv_id":"2210.01260","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-boundaries-of-meaning-a-case-study-in","title":"The boundaries of meaning: a case study in neural machine translation","date":"2022-10-02","arxiv_id":"2210.00613","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-closer-look-at-parameter-contributions-when","title":"A Closer Look at Parameter Contributions When Training Neural Language and Translation Models","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-simple-model-for-distantly-supervised","title":"A Simple Model for Distantly Supervised Relation Extraction","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-tip-attribute-aware-text-infilling-via-pre","title":"A-TIP: Attribute-aware Text Infilling via Pre-trained Language Model","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"an-exploration-of-prompt-based-zero-shot-1","title":"An Exploration of Prompt-Based Zero-Shot Relation Extraction Method","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"arguably-smm4h22-classification-of-health","title":"ARGUABLY@SMM4H’22: Classification of Health Related Tweets using Ensemble, Zero-Shot and Fine-Tuned Language Model","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"asymmetric-mutual-learning-for-multi-source","title":"Asymmetric Mutual Learning for Multi-source Unsupervised Sentiment Adaptation with Dynamic Feature Network","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-detection-of-borrowings-in-low","title":"Automatic Detection of Borrowings in Low-Resource Languages of the Caucasus: Andic branch","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-nominalization-of-clauses","title":"Automatic Nominalization of Clauses","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"can-data-diversity-enhance-learning","title":"Can Data Diversity Enhance Learning Generalization?","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"can-we-train-a-language-model-inside-an-end","title":"Can We Train a Language Model Inside an End-to-End ASR Model? - Investigating Effective Implicit Language Modeling","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"complx-smm4h22-in-domain-pretrained-language","title":"CompLx@SMM4H’22: In-domain pretrained language models for detection of adverse drug reaction mentions in English tweets","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"data-synthesis-and-iterative-refinement-for","title":"Data Synthesis and Iterative Refinement for Neural Semantic Parsing without Annotated Logical Forms","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deciphering-and-characterizing-out-of","title":"Deciphering and Characterizing Out-of-Vocabulary Words for Morphologically Rich Languages","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"does-meta-learning-help-mbert-for-few-shot","title":"Does Meta-learning Help mBERT for Few-shot Question Generation in a Cross-lingual Transfer Setting for Indic Languages?","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-code-switched-asr-with-linguistic","title":"Improving Code-switched ASR with Linguistic Information","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-event-temporal-relation","title":"Improving Event Temporal Relation Classification via Auxiliary Label-Aware Contrastive Learning","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"kul-smm4h22-template-augmented-adaptive-pre","title":"KUL@SMM4H’22: Template Augmented Adaptive Pre-training for Tweet Classification","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learnable-dependency-based-double-graph","title":"Learnable Dependency-based Double Graph Structure for Aspect-based Sentiment Analysis","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"malm-mixing-augmented-language-modeling-for","title":"MALM: Mixing Augmented Language Modeling for Zero-Shot Machine Translation","date":"2022-10-01","arxiv_id":"2210.00320","repositories_listed":0,"syntology":null},{"url":null,"slug":"mattica-smm4h22-leveraging-sentiment-for","title":"mattica@SMM4H’22: Leveraging sentiment for stance & premise joint learning","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-guided-program-synthesis-of","title":"Neural-Guided Program Synthesis of Information Extraction Rules Using Self-Supervision","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"pingantech-at-smm4h-task1-multiple-pre","title":"PingAnTech at SMM4H task1: Multiple pre-trained model approaches for Adverse Drug Reactions","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"pln-cmm-at-socialdisner-improving-detection","title":"PLN CMM at SocialDisNER: Improving Detection of Disease Mentions in Tweets by Using Document-Level Features","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"predictive-text-for-agglutinative-and-1","title":"Predictive Text for Agglutinative and Polysynthetic Languages","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"speaker-clustering-in-textual-dialogue-with-1","title":"Speaker Clustering in Textual Dialogue with Pairwise Utterance Relation and Cross-corpus Dialogue Act Supervision","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"taking-actions-separately-a-bidirectionally","title":"Taking Actions Separately: A Bidirectionally-Adaptive Transfer Learning Method for Low-Resource Neural Machine Translation","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"team-ainlpml-mup-in-sdp-2021-scientific","title":"Team AINLPML @ MuP in SDP 2021: Scientific Document Summarization by End-to-End Extractive and Abstractive Approach","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-covid-that-wasnt-counterfactual","title":"The COVID That Wasn’t: Counterfactual Journalism Using GPT","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-only-chance-to-understand-machine","title":"The Only Chance to Understand: Machine Translation of the Severely Endangered Low-resource Languages of Eurasia","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-role-of-context-in-detecting-the-target","title":"The Role of Context in Detecting the Target of Hate Speech","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-making-the-most-of-pre-trained","title":"Towards Making the Most of Pre-trained Translation Model for Quality Estimation","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"transfer-learning-improves-french-cross","title":"Transfer Learning Improves French Cross-Domain Dialect Identification: NRC @ VarDial 2022","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"transferring-knowledge-from-structure-aware-1","title":"Transferring Knowledge from Structure-aware Self-attention Language Model to Sequence-to-Sequence Semantic Parsing","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-data-augmentation-for-aspect","title":"Unsupervised Data Augmentation for Aspect Based Sentiment Analysis","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"using-structured-content-plans-for-fine-1","title":"Using Structured Content Plans for Fine-grained Syntactic Control in Pretrained Language Model Generation","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-by-distilling-context","title":"Learning by Distilling Context","date":"2022-09-30","arxiv_id":"2209.15189","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-robustness-of-self-supervised-1","title":"Augmentation Invariant Discrete Representation for Generative Spoken Language Modeling","date":"2022-09-30","arxiv_id":"2209.15483","repositories_listed":0,"syntology":null},{"url":null,"slug":"bidirectional-language-models-are-also-few","title":"Bidirectional Language Models Are Also Few-shot Learners","date":"2022-09-29","arxiv_id":"2209.14500","repositories_listed":0,"syntology":null}],"record_sha256":"d46a9e381ab2ad39808f95d52c1a469e6c29890abb077485816605acb9d0498e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}