{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/topic-conversation-relevance-tcr-dataset-and","title":"Topic-Conversation Relevance (TCR) Dataset and Benchmarks","arxiv_id":"2411.00038","date":"2024-10-29","proceeding":null,"authors":["Yaran Fan","Jamie Pool","Senja Filipi","Ross Cutler"],"abstract":"Workplace meetings are vital to organizational collaboration, yet a large percentage of meetings are rated as ineffective. To help improve meeting effectiveness by understanding if the conversation is on topic, we create a comprehensive Topic-Conversation Relevance (TCR) dataset that covers a variety of domains and meeting styles. The TCR dataset includes 1,500 unique meetings, 22 million words in transcripts, and over 15,000 meeting topics, sourced from both newly collected Speech Interruption Meeting (SIM) data and existing public datasets. Along with the text data, we also open source scripts to generate synthetic meetings or create augmented meetings from the TCR dataset to enhance data diversity. For each data source, benchmarks are created using GPT-4 to evaluate the model accuracy in understanding transcription-topic relevance.","url_abs":"https://arxiv.org/abs/2411.00038v2","url_pdf":"https://arxiv.org/pdf/2411.00038v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"topic-conversation-relevance-tcr-dataset-and","repo_url":"https://github.com/microsoft/topic_conversation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-4","method_name":"GPT-4"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2411.00038","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00038"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/microsoft/topic_conversation","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":10},"by_repo_kind":{"official":{"samples":10,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"3971a3926467307b","entry":"adjust_time","repo":"microsoft/topic_conversation","repo_kind":"official","path":"utils/create_synthetic_SIM.py","file_url":"https://github.com/microsoft/topic_conversation/blob/HEAD/utils/create_synthetic_SIM.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3971a3926467307b"}},{"code_sha256_prefix":"f8b67f983fdf5aa8","entry":"create_data_addTopics","repo":"microsoft/topic_conversation","repo_kind":"official","path":"utils/create_variations.py","file_url":"https://github.com/microsoft/topic_conversation/blob/HEAD/utils/create_variations.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f8b67f983fdf5aa8"}},{"code_sha256_prefix":"6c4670df5b502c3b","entry":"create_data_removeTopics","repo":"microsoft/topic_conversation","repo_kind":"official","path":"utils/create_variations.py","file_url":"https://github.com/microsoft/topic_conversation/blob/HEAD/utils/create_variations.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6c4670df5b502c3b"}},{"code_sha256_prefix":"231e1a4c4cbb05fc","entry":"create_variation_dist","repo":"microsoft/topic_conversation","repo_kind":"official","path":"utils/create_variations.py","file_url":"https://github.com/microsoft/topic_conversation/blob/HEAD/utils/create_variations.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"231e1a4c4cbb05fc"}},{"code_sha256_prefix":"011957a2786945c5","entry":"format_topics","repo":"microsoft/topic_conversation","repo_kind":"official","path":"utils/create_synthetic_SIM.py","file_url":"https://github.com/microsoft/topic_conversation/blob/HEAD/utils/create_synthetic_SIM.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"011957a2786945c5"}},{"code_sha256_prefix":"02a8fa83309f558c","entry":"locate_suffix_files","repo":"microsoft/topic_conversation","repo_kind":"official","path":"utils/benchmark_utils.py","file_url":"https://github.com/microsoft/topic_conversation/blob/HEAD/utils/benchmark_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"02a8fa83309f558c"}},{"code_sha256_prefix":"9066def57157b199","entry":"prompt_topic_relevance","repo":"microsoft/topic_conversation","repo_kind":"official","path":"utils/benchmark_utils.py","file_url":"https://github.com/microsoft/topic_conversation/blob/HEAD/utils/benchmark_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9066def57157b199"}},{"code_sha256_prefix":"c429c845650185a1","entry":"set_parameters","repo":"microsoft/topic_conversation","repo_kind":"official","path":"script_create_synthetic_meetings_SIM.py","file_url":"https://github.com/microsoft/topic_conversation/blob/HEAD/script_create_synthetic_meetings_SIM.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c429c845650185a1"}},{"code_sha256_prefix":"2df7542c36a58a73","entry":"syn_prepare","repo":"microsoft/topic_conversation","repo_kind":"official","path":"utils/create_synthetic_SIM.py","file_url":"https://github.com/microsoft/topic_conversation/blob/HEAD/utils/create_synthetic_SIM.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2df7542c36a58a73"}},{"code_sha256_prefix":"8732e2792a3c0074","entry":"unify_quotes","repo":"microsoft/topic_conversation","repo_kind":"official","path":"utils/benchmark_utils.py","file_url":"https://github.com/microsoft/topic_conversation/blob/HEAD/utils/benchmark_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8732e2792a3c0074"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}