{"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/fasttext/papers/2","list_of":"/method/fasttext","method":"fastText","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":2,"pages_in_order":3,"rows_per_page":100,"rows":[101,200],"of":240,"counts":{"archive_papers_tagged":240,"with_a_code_link":76,"where_syntology_ran_a_sample":10,"not_listed_spam_title":0,"listed":240,"listed_where_code_ran":10,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":8,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":8,"listed_every_run_a_failure_of_syntologys_instrument":2,"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/fasttext","prev":"/method/fasttext","next":"/method/fasttext/papers/3","papers":[{"paper":"/paper/evaluating-document-representations-for","slug":"evaluating-document-representations-for","title":"Evaluating Document Representations for Content-based Legal Literature Recommendations","date":"2021-04-28","arxiv_id":"2104.13841","n_code_links":1,"syntology":null},{"paper":null,"slug":"are-word-embedding-methods-stable-and-should","title":"Are Word Embedding Methods Stable and Should We Care About It?","date":"2021-04-17","arxiv_id":"2104.08433","n_code_links":0,"syntology":null},{"paper":null,"slug":"supersim-a-test-set-for-word-similarity-and","title":"SuperSim: a test set for word similarity and relatedness in Swedish","date":"2021-04-12","arxiv_id":"2104.05228","n_code_links":0,"syntology":null},{"paper":"/paper/text2chart-a-multi-staged-chart-generator","slug":"text2chart-a-multi-staged-chart-generator","title":"Text2Chart: A Multi-Staged Chart Generator from Natural Language Text","date":"2021-04-09","arxiv_id":"2104.04584","n_code_links":1,"syntology":null},{"paper":null,"slug":"semi-supervised-classification-of-social","title":"Semi-Supervised Classification of Social Media Posts: Identifying Sex-Industry Posts to Enable Better Support for Those Experiencing Sex-Trafficking","date":"2021-04-07","arxiv_id":"2104.03233","n_code_links":0,"syntology":null},{"paper":null,"slug":"sentiment-analysis-of-code-mixed-social-media","title":"Sentiment Analysis of Code-Mixed Social Media Text (Hinglish)","date":"2021-02-24","arxiv_id":"2102.12149","n_code_links":0,"syntology":null},{"paper":"/paper/co-occurrences-using-fasttext-embeddings-for","slug":"co-occurrences-using-fasttext-embeddings-for","title":"Co-occurrences using Fasttext embeddings for word similarity tasks in Urdu","date":"2021-02-22","arxiv_id":"2102.10957","n_code_links":1,"syntology":null},{"paper":"/paper/towards-emotion-recognition-in-hindi-english","slug":"towards-emotion-recognition-in-hindi-english","title":"Towards Emotion Recognition in Hindi-English Code-Mixed Data: A Transformer Based Approach","date":"2021-02-19","arxiv_id":"2102.09943","n_code_links":1,"syntology":null},{"paper":"/paper/an-automl-based-approach-to-multimodal-image","slug":"an-automl-based-approach-to-multimodal-image","title":"An AutoML-based Approach to Multimodal Image Sentiment Analysis","date":"2021-02-16","arxiv_id":"2102.08092","n_code_links":0,"syntology":null},{"paper":null,"slug":"one-size-does-not-fit-all-finding-the-optimal","title":"One Size Does Not Fit All: Finding the Optimal Subword Sizes for FastText Models across Languages","date":"2021-02-04","arxiv_id":"2102.02585","n_code_links":0,"syntology":null},{"paper":null,"slug":"does-a-hybrid-neural-network-based-feature","title":"Does a Hybrid Neural Network based Feature Selection Model Improve Text Classification?","date":"2021-01-22","arxiv_id":"2101.09009","n_code_links":0,"syntology":null},{"paper":null,"slug":"hinflair-pre-trained-contextual-string","title":"HinFlair: pre-trained contextual string embeddings for pos tagging and text classification in the Hindi language","date":"2021-01-18","arxiv_id":"2101.06949","n_code_links":0,"syntology":null},{"paper":null,"slug":"hostility-detection-and-covid-19-fake-news","title":"Hostility Detection and Covid-19 Fake News Detection in Social Media","date":"2021-01-15","arxiv_id":"2101.05953","n_code_links":0,"syntology":null},{"paper":null,"slug":"experimental-evaluation-of-deep-learning","title":"Experimental Evaluation of Deep Learning models for Marathi Text Classification","date":"2021-01-13","arxiv_id":"2101.04899","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluation-of-deep-learning-models-for","title":"Evaluation of Deep Learning Models for Hostility Detection in Hindi Text","date":"2021-01-11","arxiv_id":"2101.04144","n_code_links":0,"syntology":null},{"paper":"/paper/graph-of-tweets-a-graph-merging-approach-to","slug":"graph-of-tweets-a-graph-merging-approach-to","title":"Graph-of-Tweets: A Graph Merging Approach to Sub-event Identification","date":"2021-01-08","arxiv_id":"2101.03208","n_code_links":1,"syntology":null},{"paper":null,"slug":"language-detection-engine-for-multilingual","title":"Language Detection Engine for Multilingual Texting on Mobile Devices","date":"2021-01-07","arxiv_id":"2101.03963","n_code_links":0,"syntology":null},{"paper":null,"slug":"faster-training-of-word-embeddings","title":"Faster Training of Word Embeddings","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"hate-speech-detection-in-the-bengali-language","title":"Hate Speech detection in the Bengali language: A dataset and its baseline evaluation","date":"2020-12-17","arxiv_id":"2012.09686","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":"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":null,"slug":"iiitg-adbu-at-semeval-2020-task-8-a","title":"IIITG-ADBU at SemEval-2020 Task 8: A Multimodal Approach to Detect Offensive, Sarcastic and Humorous Memes","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"nlp-passau-at-semeval-2020-task-12","title":"NLP\\_Passau at SemEval-2020 Task 12: Multilingual Neural Network for Offensive Language Detection in English, Danish and Turkish","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"word-embedding-binarization-with-semantic","title":"Word Embedding Binarization with Semantic Information Preservation","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"blind-signal-decomposition-of-various-word","title":"Blind signal decomposition of various word embeddings based on join and individual variance explained","date":"2020-11-30","arxiv_id":"2011.14496","n_code_links":0,"syntology":null},{"paper":"/paper/improving-clinical-outcome-predictions-using","slug":"improving-clinical-outcome-predictions-using","title":"Improving Clinical Outcome Predictions Using Convolution over Medical Entities with Multimodal Learning","date":"2020-11-24","arxiv_id":"2011.12349","n_code_links":1,"syntology":null},{"paper":null,"slug":"steps-rl-speech-text-entanglement-for","title":"STEPs-RL: Speech-Text Entanglement for Phonetically Sound Representation Learning","date":"2020-11-23","arxiv_id":"2011.11387","n_code_links":0,"syntology":null},{"paper":"/paper/debatesum-a-large-scale-argument-mining-and","slug":"debatesum-a-large-scale-argument-mining-and","title":"DebateSum: A large-scale argument mining and summarization dataset","date":"2020-11-14","arxiv_id":"2011.07251","n_code_links":3,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["Hellisotherpeople/DebateSum","Hellisotherpeople/debate2vec","arvind-balaji/debate-cards"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/hypertext-endowing-fasttext-with-hyperbolic","slug":"hypertext-endowing-fasttext-with-hyperbolic","title":"HyperText: Endowing FastText with Hyperbolic Geometry","date":"2020-10-30","arxiv_id":"2010.16143","n_code_links":3,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/gender-prediction-based-on-vietnamese-names","slug":"gender-prediction-based-on-vietnamese-names","title":"Gender Prediction Based on Vietnamese Names with Machine Learning Techniques","date":"2020-10-21","arxiv_id":"2010.10852","n_code_links":0,"syntology":null},{"paper":null,"slug":"lt3-at-semeval-2020-task-9-cross-lingual","title":"LT3 at SemEval-2020 Task 9: Cross-lingual Embeddings for Sentiment Analysis of Hinglish Social Media Text","date":"2020-10-21","arxiv_id":"2010.11019","n_code_links":0,"syntology":null},{"paper":"/paper/wnut-2020-task-2-identification-of","slug":"wnut-2020-task-2-identification-of","title":"WNUT-2020 Task 2: Identification of Informative COVID-19 English Tweets","date":"2020-10-16","arxiv_id":"2010.08232","n_code_links":1,"syntology":null},{"paper":null,"slug":"geometry-matters-exploring-language-examples-1","title":"Geometry matters: Exploring language examples at the decision boundary","date":"2020-10-14","arxiv_id":"2010.07212","n_code_links":0,"syntology":null},{"paper":null,"slug":"gundapusunil-at-semeval-2020-task-9-syntactic","title":"gundapusunil at SemEval-2020 Task 9: Syntactic Semantic LSTM Architecture for SENTIment Analysis of Code-MIXed Data","date":"2020-10-09","arxiv_id":"2010.04395","n_code_links":0,"syntology":null},{"paper":"/paper/intrinsic-probing-through-dimension-selection","slug":"intrinsic-probing-through-dimension-selection","title":"Intrinsic Probing through Dimension Selection","date":"2020-10-06","arxiv_id":"2010.02812","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["rycolab/intrinsic-probing"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/pareto-probing-trading-off-accuracy-for","slug":"pareto-probing-trading-off-accuracy-for","title":"Pareto Probing: Trading Off Accuracy for Complexity","date":"2020-10-05","arxiv_id":"2010.02180","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["rycolab/pareto-probing"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/did-you-really-mean-what-you-said-sarcasm","slug":"did-you-really-mean-what-you-said-sarcasm","title":"\"Did you really mean what you said?\" : Sarcasm Detection in Hindi-English Code-Mixed Data using Bilingual Word Embeddings","date":"2020-10-01","arxiv_id":"2010.00310","n_code_links":1,"syntology":null},{"paper":null,"slug":"development-of-word-embeddings-for-uzbek","title":"Development of Word Embeddings for Uzbek Language","date":"2020-09-30","arxiv_id":"2009.14384","n_code_links":0,"syntology":null},{"paper":"/paper/farstail-a-persian-natural-language-inference","slug":"farstail-a-persian-natural-language-inference","title":"FarsTail: A Persian Natural Language Inference Dataset","date":"2020-09-18","arxiv_id":"2009.08820","n_code_links":1,"syntology":null},{"paper":null,"slug":"edinburghnlp-at-wnut-2020-task-2-leveraging","title":"EdinburghNLP at WNUT-2020 Task 2: Leveraging Transformers with Generalized Augmentation for Identifying Informativeness in COVID-19 Tweets","date":"2020-09-06","arxiv_id":"2009.06375","n_code_links":0,"syntology":null},{"paper":"/paper/going-beyond-t-sne-exposing-texttt-whatlies","slug":"going-beyond-t-sne-exposing-texttt-whatlies","title":"Going Beyond T-SNE: Exposing \\texttt{whatlies} in Text Embeddings","date":"2020-09-04","arxiv_id":"2009.02113","n_code_links":1,"syntology":null},{"paper":null,"slug":"beyond-next-item-recommendation-recommending","title":"Beyond Next Item Recommendation: Recommending and Evaluating List of Sequences","date":"2020-08-30","arxiv_id":"2008.13281","n_code_links":0,"syntology":null},{"paper":"/paper/a-study-of-fasttext-word-embedding-effects-in","slug":"a-study-of-fasttext-word-embedding-effects-in","title":"A Study of fastText Word Embedding Effects in Document Classification in Bangla Language","date":"2020-07-30","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"covid-19-therapy-target-discovery-with","title":"COVID-19 therapy target discovery with context-aware literature mining","date":"2020-07-30","arxiv_id":"2007.15681","n_code_links":0,"syntology":null},{"paper":null,"slug":"word-embeddings-stability-and-semantic-change","title":"Word Embeddings: Stability and Semantic Change","date":"2020-07-23","arxiv_id":"2007.16006","n_code_links":0,"syntology":null},{"paper":null,"slug":"morphological-skip-gram-using-morphological","title":"Morphological Skip-Gram: Using morphological knowledge to improve word representation","date":"2020-07-20","arxiv_id":"2007.10055","n_code_links":0,"syntology":null},{"paper":null,"slug":"estimating-the-effect-of-covid-19-on-mental","title":"Estimating the effect of COVID-19 on mental health: Linguistic indicators of depression during a global pandemic","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-learnability-of-concepts-with","title":"On the Learnability of Concepts: With Applications to Comparing Word Embedding Algorithms","date":"2020-06-17","arxiv_id":"2006.09896","n_code_links":0,"syntology":null},{"paper":null,"slug":"qdkt-question-centric-deep-knowledge-tracing","title":"qDKT: Question-centric Deep Knowledge Tracing","date":"2020-05-25","arxiv_id":"2005.12442","n_code_links":0,"syntology":null},{"paper":"/paper/adversarial-alignment-of-multilingual-models","slug":"adversarial-alignment-of-multilingual-models","title":"Adversarial Alignment of Multilingual Models for Extracting Temporal Expressions from Text","date":"2020-05-19","arxiv_id":"2005.09392","n_code_links":0,"syntology":null},{"paper":null,"slug":"categorical-vector-space-semantics-for-lambek","title":"Categorical Vector Space Semantics for Lambek Calculus with a Relevant Modality","date":"2020-05-06","arxiv_id":"2005.03074","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-first-dataset-for-film-age-appropriateness","title":"A First Dataset for Film Age Appropriateness Investigation","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"ai-ml-nit-patna-trac-2-deep-learning-approach","title":"AI\\_ML\\_NIT\\_Patna @ TRAC - 2: Deep Learning Approach for Multi-lingual Aggression Identification","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cbow-tag-a-modified-cbow-algorithm-for","title":"CBOW-tag: a Modified CBOW Algorithm for Generating Embedding Models from Annotated Corpora","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"czech-historical-named-entity-corpus-v-1-0","title":"Czech Historical Named Entity Corpus v 1.0","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-the-impact-of-sub-word-information","title":"Evaluating the Impact of Sub-word Information and Cross-lingual Word Embeddings on Mi'kmaq Language Modelling","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"facilitating-corpus-usage-making-icelandic","title":"Facilitating Corpus Usage: Making Icelandic Corpora More Accessible for Researchers and Language Users","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"high-quality-elmo-embeddings-for-seven-less-1","title":"High Quality ELMo Embeddings for Seven Less-Resourced Languages","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"identifying-cognates-in-english-dutch-and","title":"Identifying Cognates in English-Dutch and French-Dutch by means of Orthographic Information and Cross-lingual Word Embeddings","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/klej-comprehensive-benchmark-for-polish","slug":"klej-comprehensive-benchmark-for-polish","title":"KLEJ: Comprehensive Benchmark for Polish Language Understanding","date":"2020-05-01","arxiv_id":"2005.00630","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["allegro/klejbenchmark-baselines"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"taln-ls2n-participation-at-the-bucc-shared","title":"TALN/LS2N Participation at the BUCC Shared Task: Bilingual Dictionary Induction from Comparable Corpora","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"unior-nlp-at-mwsa-task-globalex-2020-siamese","title":"UNIOR NLP at MWSA Task - GlobaLex 2020: Siamese LSTM with Attention for Word Sense Alignment","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"word-embedding-evaluation-for-sinhala","title":"Word Embedding Evaluation for Sinhala","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"standardizing-and-benchmarking-crisis-related","title":"CrisisBench: Benchmarking Crisis-related Social Media Datasets for Humanitarian Information Processing","date":"2020-04-14","arxiv_id":"2004.06774","n_code_links":0,"syntology":null},{"paper":"/paper/deepsentipers-novel-deep-learning-models","slug":"deepsentipers-novel-deep-learning-models","title":"DeepSentiPers: Novel Deep Learning Models Trained Over Proposed Augmented Persian Sentiment Corpus","date":"2020-04-11","arxiv_id":"2004.05328","n_code_links":1,"syntology":null},{"paper":null,"slug":"word-sense-disambiguation-for-158-languages","title":"Word Sense Disambiguation for 158 Languages using Word Embeddings Only","date":"2020-03-14","arxiv_id":"2003.06651","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-simlex-a-large-scale-evaluation-of","title":"Multi-SimLex: A Large-Scale Evaluation of Multilingual and Cross-Lingual Lexical Semantic Similarity","date":"2020-03-10","arxiv_id":"2003.04866","n_code_links":0,"syntology":null},{"paper":null,"slug":"discovering-linguistic-irregularities-in-word","title":"Discovering linguistic (ir)regularities in word embeddings through max-margin separating hyperplanes","date":"2020-03-07","arxiv_id":"2003.03654","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparison-of-turkish-word-representations","title":"Comparison of Turkish Word Representations Trained on Different Morphological Forms","date":"2020-02-13","arxiv_id":"2002.05417","n_code_links":0,"syntology":null},{"paper":"/paper/generating-sense-embeddings-for-syntactic-and","slug":"generating-sense-embeddings-for-syntactic-and","title":"Generating Sense Embeddings for Syntactic and Semantic Analogy for Portuguese","date":"2020-01-21","arxiv_id":"2001.07574","n_code_links":1,"syntology":null},{"paper":"/paper/exem-expert-embedding-using-dominating-set","slug":"exem-expert-embedding-using-dominating-set","title":"ExEm: Expert Embedding using dominating set theory with deep learning approaches","date":"2020-01-16","arxiv_id":"2001.08503","n_code_links":2,"syntology":null},{"paper":"/paper/aggressionnet-generalised-multi-modal-deep","slug":"aggressionnet-generalised-multi-modal-deep","title":"A Unified System for Aggression Identification in English Code-Mixed and Uni-Lingual Texts","date":"2020-01-15","arxiv_id":"2001.05493","n_code_links":0,"syntology":null},{"paper":null,"slug":"character-3-gram-movers-distance-an-effective","title":"Character 3-gram Mover's Distance: An Effective Method for Detecting Near-duplicate Japanese-language Recipes","date":"2019-12-11","arxiv_id":"1912.05171","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-new-corpus-for-low-resourced-sindhi","title":"Word Embedding based New Corpus for Low-resourced Language: Sindhi","date":"2019-11-28","arxiv_id":"1911.12579","n_code_links":0,"syntology":null},{"paper":null,"slug":"hauwe-hausa-words-embedding-for-natural","title":"hauWE: Hausa Words Embedding for Natural Language Processing","date":"2019-11-25","arxiv_id":"1911.10708","n_code_links":0,"syntology":null},{"paper":null,"slug":"high-quality-elmo-embeddings-for-seven-less","title":"High Quality ELMo Embeddings for Seven Less-Resourced Languages","date":"2019-11-22","arxiv_id":"1911.10049","n_code_links":0,"syntology":null},{"paper":null,"slug":"multilingual-culture-independent-word-analogy","title":"Multilingual Culture-Independent Word Analogy Datasets","date":"2019-11-22","arxiv_id":"1911.10038","n_code_links":0,"syntology":null},{"paper":null,"slug":"event-detection-in-colombian-security-twitter","title":"Event detection in Colombian security Twitter news using fine-grained latent topic analysis","date":"2019-11-19","arxiv_id":"1911.08370","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-non-toxic-landscapes-automatic-toxic","title":"Towards non-toxic landscapes: Automatic toxic comment detection using DNN","date":"2019-11-19","arxiv_id":"1911.08395","n_code_links":0,"syntology":null},{"paper":"/paper/ccnet-extracting-high-quality-monolingual","slug":"ccnet-extracting-high-quality-monolingual","title":"CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Data","date":"2019-11-01","arxiv_id":"1911.00359","n_code_links":2,"syntology":null},{"paper":"/paper/191013291","slug":"191013291","title":"Sentence Embeddings for Russian NLU","date":"2019-10-29","arxiv_id":"1910.13291","n_code_links":1,"syntology":null},{"paper":null,"slug":"using-machine-learning-and-information","title":"Using machine learning and information visualisation for discovering latent topics in Twitter news","date":"2019-10-21","arxiv_id":"1910.09114","n_code_links":0,"syntology":null},{"paper":"/paper/privacy-and-utility-preserving-textual","slug":"privacy-and-utility-preserving-textual","title":"Privacy- and Utility-Preserving Textual Analysis via Calibrated Multivariate Perturbations","date":"2019-10-20","arxiv_id":"1910.08902","n_code_links":1,"syntology":null},{"paper":null,"slug":"uncovering-flaming-events-on-news-media-in","title":"Uncovering Flaming Events on News Media in Social Media","date":"2019-09-16","arxiv_id":"1909.07181","n_code_links":0,"syntology":null},{"paper":null,"slug":"dialogue-act-classification-in-team","title":"Dialogue Act Classification in Team Communication for Robot Assisted Disaster Response","date":"2019-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluation-of-stacked-embeddings-for","title":"Evaluation of Stacked Embeddings for Bulgarian on the Downstream Tasks POS and NERC","date":"2019-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluation-of-vector-embedding-models-in","title":"Evaluation of vector embedding models in clustering of text documents","date":"2019-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/question-similarity-in-community-question","slug":"question-similarity-in-community-question","title":"Question Similarity in Community Question Answering: A Systematic Exploration of Preprocessing Methods and Models","date":"2019-09-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/sparse-victory-a-large-scale-systematic","slug":"sparse-victory-a-large-scale-systematic","title":"Sparse Victory -- A Large Scale Systematic Comparison of count-based and prediction-based vectorizers for text classification","date":"2019-09-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"tagger-for-polish-computer-mediated","title":"Tagger for Polish Computer Mediated Communication Texts","date":"2019-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-word-embeddings-using-kernel-pca","title":"Improving Word Embeddings Using Kernel PCA","date":"2019-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-word-embeddings-without-context","title":"Learning Word Embeddings without Context Vectors","date":"2019-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/rnn-embeddings-for-identifying-difficult-to","slug":"rnn-embeddings-for-identifying-difficult-to","title":"RNN Embeddings for Identifying Difficult to Understand Medical Words","date":"2019-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/robust-to-noise-models-in-natural-language","slug":"robust-to-noise-models-in-natural-language","title":"Robust to Noise Models in Natural Language Processing Tasks","date":"2019-07-01","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":null,"slug":"gated-embeddings-in-end-to-end-speech","title":"Gated Embeddings in End-to-End Speech Recognition for Conversational-Context Fusion","date":"2019-06-27","arxiv_id":"1906.11604","n_code_links":0,"syntology":null},{"paper":"/paper/word-embeddings-for-the-armenian-language","slug":"word-embeddings-for-the-armenian-language","title":"Word Embeddings for the Armenian Language: Intrinsic and Extrinsic Evaluation","date":"2019-06-07","arxiv_id":"1906.03134","n_code_links":1,"syntology":null},{"paper":"/paper/sequence-tagging-with-contextual-and-non","slug":"sequence-tagging-with-contextual-and-non","title":"Sequence Tagging with Contextual and Non-Contextual Subword Representations: A Multilingual Evaluation","date":"2019-06-04","arxiv_id":"1906.01569","n_code_links":1,"syntology":null},{"paper":null,"slug":"beyond-context-a-new-perspective-for-word","title":"Beyond Context: A New Perspective for Word Embeddings","date":"2019-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-techniques-for-humor-detection","title":"Deep Learning Techniques for Humor Detection in Hindi-English Code-Mixed Tweets","date":"2019-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"how-well-do-embedding-models-capture-non","title":"How Well Do Embedding Models Capture Non-compositionality? A View from Multiword Expressions","date":"2019-06-01","arxiv_id":null,"n_code_links":0,"syntology":null}],"record_sha256":"1ea355c5f6a2db8315aac10008be954f5439e9dc1f740089f70bc2a9d63b140b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}