metadata
tags:
- bertopic
library_name: bertopic
pipeline_tag: text-classification
topic_model_general_normal_april8
This is a BERTopic model. BERTopic is a flexible and modular topic modeling framework that allows for the generation of easily interpretable topics from large datasets.
Usage
To use this model, please install BERTopic:
pip install -U bertopic
You can use the model as follows:
from bertopic import BERTopic
topic_model = BERTopic.load("Thang203/topic_model_general_normal_april8")
topic_model.get_topic_info()
Topic overview
- Number of topics: 80
- Number of training documents: 6795
Click here for an overview of all topics.
| Topic ID | Topic Keywords | Topic Frequency | Label |
|---|---|---|---|
| -1 | models - language - llms - language models - chatgpt | 11 | -1_models_language_llms_language models |
| 0 | translation - language - models - data - generation | 2010 | 0_translation_language_models_data |
| 1 | visual - multimodal - image - images - video | 510 | 1_visual_multimodal_image_images |
| 2 | reasoning - math - cot - mathematical - problems | 432 | 2_reasoning_math_cot_mathematical |
| 3 | attacks - attack - adversarial - safety - jailbreak | 340 | 3_attacks_attack_adversarial_safety |
| 4 | medical - clinical - biomedical - health - healthcare | 318 | 4_medical_clinical_biomedical_health |
| 5 | code - code generation - generation - programming - software | 303 | 5_code_code generation_generation_programming |
| 6 | students - education - ai - chatgpt - student | 153 | 6_students_education_ai_chatgpt |
| 7 | robot - planning - robots - navigation - robotic | 110 | 7_robot_planning_robots_navigation |
| 8 | dialogue - taskoriented - dialog - dialogue systems - systems | 107 | 8_dialogue_taskoriented_dialog_dialogue systems |
| 9 | knowledge - question - answering - question answering - kgs | 97 | 9_knowledge_question_answering_question answering |
| 10 | financial - sentiment - stock - market - investment | 78 | 10_financial_sentiment_stock_market |
| 11 | bias - gender - biases - gender bias - fairness | 78 | 11_bias_gender_biases_gender bias |
| 12 | emotion - emotional - empathetic - mental health - affective | 77 | 12_emotion_emotional_empathetic_mental health |
| 13 | privacy - private - federated - data - attack | 76 | 13_privacy_private_federated_data |
| 14 | text - detection - texts - aigenerated - machinegenerated | 75 | 14_text_detection_texts_aigenerated |
| 15 | radiology - medical - reports - image - radiology reports | 75 | 15_radiology_medical_reports_image |
| 16 | training - parallelism - gpu - memory - hardware | 71 | 16_training_parallelism_gpu_memory |
| 17 | summarization - summaries - abstractive - summary - text summarization | 70 | 17_summarization_summaries_abstractive_summary |
| 18 | game - games - agents - social - llm agents | 69 | 18_game_games_agents_social |
| 19 | quantization - quantized - weights - memory - compression | 66 | 19_quantization_quantized_weights_memory |
| 20 | sql - texttosql - table - database - tabular | 62 | 20_sql_texttosql_table_database |
| 21 | retrieval - ranking - rag - reranking - retrievalaugmented | 61 | 21_retrieval_ranking_rag_reranking |
| 22 | lora - attention - lowrank - finetuning - memory | 59 | 22_lora_attention_lowrank_finetuning |
| 23 | legal - patent - claim - court - law | 58 | 23_legal_patent_claim_court |
| 24 | alignment - preference - reward - rlhf - preferences | 58 | 24_alignment_preference_reward_rlhf |
| 25 | recommendation - recommender - recommendations - recommender systems - user | 56 | 25_recommendation_recommender_recommendations_recommender systems |
| 26 | transformer - transformers - attention - layers - layer | 55 | 26_transformer_transformers_attention_layers |
| 27 | tom - cognitive - analogical - analogies - human | 52 | 27_tom_cognitive_analogical_analogies |
| 28 | vulnerability - vulnerabilities - code - security - smart | 48 | 28_vulnerability_vulnerabilities_code_security |
| 29 | materials - chemistry - materials science - chemical - molecular | 48 | 29_materials_chemistry_materials science_chemical |
| 30 | agent - agents - rl - environments - language agents | 47 | 30_agent_agents_rl_environments |
| 31 | repair - bugs - bug - program repair - apr | 43 | 31_repair_bugs_bug_program repair |
| 32 | graph - graphs - graph reasoning - graph neural - graph data | 43 | 32_graph_graphs_graph reasoning_graph neural |
| 33 | speech - asr - audio - speech recognition - recognition | 42 | 33_speech_asr_audio_speech recognition |
| 34 | ai - ethical - regulation - risks - risk | 41 | 34_ai_ethical_regulation_risks |
| 35 | personality - traits - personality traits - personas - personalities | 41 | 35_personality_traits_personality traits_personas |
| 36 | context - context window - window - length - long | 36 | 36_context_context window_window_length |
| 37 | chatgpt - research - writing - ai - academic | 34 | 37_chatgpt_research_writing_ai |
| 38 | incontext - demonstrations - icl - incontext learning - learning | 33 | 38_incontext_demonstrations_icl_incontext learning |
| 39 | sentiment - sentiment analysis - analysis - aspectbased - polarity | 32 | 39_sentiment_sentiment analysis_analysis_aspectbased |
| 40 | cultural - opinions - political - survey - values | 30 | 40_cultural_opinions_political_survey |
| 41 | tool - tools - apis - api - llms | 29 | 41_tool_tools_apis_api |
| 42 | hallucinations - hallucination - hallucination detection - detection - llms | 29 | 42_hallucinations_hallucination_hallucination detection_detection |
| 43 | creative - ideas - ai - creativity - storytelling | 28 | 43_creative_ideas_ai_creativity |
| 44 | music - musical - audio - lyrics - song | 28 | 44_music_musical_audio_lyrics |
| 45 | scaling - scaling laws - laws - training - model | 27 | 45_scaling_scaling laws_laws_training |
| 46 | physics - students - chatgpt - education - responses | 26 | 46_physics_students_chatgpt_education |
| 47 | correction - grammatical - gec - error - error correction | 26 | 47_correction_grammatical_gec_error |
| 48 | test - unit - tests - test generation - test cases | 23 | 48_test_unit_tests_test generation |
| 49 | pruning - sparsity - structured pruning - structured - weights | 23 | 49_pruning_sparsity_structured pruning_structured |
| 50 | commonsense - commonsense knowledge - knowledge - commonsense question answering - commonsense question | 21 | 50_commonsense_commonsense knowledge_knowledge_commonsense question answering |
| 51 | distillation - teacher - student - kd - knowledge distillation | 20 | 51_distillation_teacher_student_kd |
| 52 | visualization - visualizations - data visualization - natural - natural language | 20 | 52_visualization_visualizations_data visualization_natural |
| 53 | hallucination - hallucinations - lvlms - mllms - visual | 20 | 53_hallucination_hallucinations_lvlms_mllms |
| 54 | adversarial - vlms - attacks - attack - adversarial examples | 20 | 54_adversarial_vlms_attacks_attack |
| 55 | verilog - design - hardware - hardware design - rtl | 18 | 55_verilog_design_hardware_hardware design |
| 56 | spatial - geospatial - geographic - location - populations | 18 | 56_spatial_geospatial_geographic_location |
| 57 | intent - intent detection - slot - detection - slot filling | 18 | 57_intent_intent detection_slot_detection |
| 58 | prompts - prompt - performance - negated - pseudocode | 18 | 58_prompts_prompt_performance_negated |
| 59 | brain - fmri - neural - activity - eeg | 17 | 59_brain_fmri_neural_activity |
| 60 | watermarking - copyright - protection - text - model | 16 | 60_watermarking_copyright_protection_text |
| 61 | public - social - media - early - ai | 16 | 61_public_social_media_early |
| 62 | ai - productivity - chatbots - chatgpt - economy | 15 | 62_ai_productivity_chatbots_chatgpt |
| 63 | poetry - poems - poetry generation - lyrics - poem | 15 | 63_poetry_poems_poetry generation_lyrics |
| 64 | geoscience - astronomy - scientific - astronomical - galactica | 15 | 64_geoscience_astronomy_scientific_astronomical |
| 65 | editing - knowledge editing - knowledge - model editing - editing methods | 14 | 65_editing_knowledge editing_knowledge_model editing |
| 66 | argument - arguments - argumentation - fallacy - fallacies | 14 | 66_argument_arguments_argumentation_fallacy |
| 67 | mobile - wireless - devices - aigc - network | 14 | 67_mobile_wireless_devices_aigc |
| 68 | design - bid - 3d - designs - generative | 14 | 68_design_bid_3d_designs |
| 69 | simplification - text simplification - text - sentence - readability | 14 | 69_simplification_text simplification_text_sentence |
| 70 | urban - traffic - transportation - foundation models - foundation | 13 | 70_urban_traffic_transportation_foundation models |
| 71 | log - anomaly - root - anomaly detection - cloud | 13 | 71_log_anomaly_root_anomaly detection |
| 72 | forgetting - catastrophic forgetting - catastrophic - continual - finetuning | 13 | 72_forgetting_catastrophic forgetting_catastrophic_continual |
| 73 | scientific - papers - review - gpt4 - feedback | 13 | 73_scientific_papers_review_gpt4 |
| 74 | causal - causality - causal discovery - causal inference - causal reasoning | 13 | 74_causal_causality_causal discovery_causal inference |
| 75 | product - ecommerce - attribute - extraction - product descriptions | 13 | 75_product_ecommerce_attribute_extraction |
| 76 | optimizers - adam - deep - training - networks | 12 | 76_optimizers_adam_deep_training |
| 77 | chinese - questions - subjects - school - ceval | 12 | 77_chinese_questions_subjects_school |
| 78 | speculative - decoding - draft - speculative decoding - draft model | 12 | 78_speculative_decoding_draft_speculative decoding |
Training hyperparameters
- calculate_probabilities: False
- language: english
- low_memory: False
- min_topic_size: 10
- n_gram_range: (1, 1)
- nr_topics: auto
- seed_topic_list: None
- top_n_words: 10
- verbose: True
- zeroshot_min_similarity: 0.7
- zeroshot_topic_list: None
Framework versions
- Numpy: 1.25.2
- HDBSCAN: 0.8.33
- UMAP: 0.5.6
- Pandas: 2.0.3
- Scikit-Learn: 1.2.2
- Sentence-transformers: 2.6.1
- Transformers: 4.38.2
- Numba: 0.58.1
- Plotly: 5.15.0
- Python: 3.10.12