{"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/pgtask-introducing-the-task-of-profile","title":"PGTask: Introducing the Task of Profile Generation from Dialogues","arxiv_id":"2304.06634","date":"2023-04-13","proceeding":null,"authors":["Rui Ribeiro","Joao P. Carvalho","Luísa Coheur"],"abstract":"Recent approaches have attempted to personalize dialogue systems by leveraging profile information into models. However, this knowledge is scarce and difficult to obtain, which makes the extraction/generation of profile information from dialogues a fundamental asset. To surpass this limitation, we introduce the Profile Generation Task (PGTask). We contribute with a new dataset for this problem, comprising profile sentences aligned with related utterances, extracted from a corpus of dialogues. Furthermore, using state-of-the-art methods, we provide a benchmark for profile generation on this novel dataset. Our experiments disclose the challenges of profile generation, and we hope that this introduces a new research direction.","url_abs":"https://arxiv.org/abs/2304.06634v2","url_pdf":"https://arxiv.org/pdf/2304.06634v2.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":"pgtask-introducing-the-task-of-profile","repo_url":"https://github.com/ruinunca/PGTask","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"pgtask","task_name":"Profile Generation"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"discriminative-fine-tuning","method_name":"Discriminative Fine-Tuning"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-2","method_name":"GPT-2"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[{"slug":"pgdataset","name":"PGDataset","full_name":"Profile Generation Dataset"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/pgtask-on-pgdataset","task":"Profile Generation","dataset":"PGDataset","model":"gpt2-small","rank_in_archive_order":1,"of":2,"metrics":{"BLEU-1":"61.30","BLEU-2":"32.3","BLEU-3":"20.62","BLEU-4":"9.44","BertScore":"94.39","ROUGE-1":"50.07","ROUGE-2":"28.31","ROUGE-L":"50.00"},"uses_additional_data":false},{"leaderboard":"/sota/pgtask-on-pgdataset","task":"Profile Generation","dataset":"PGDataset","model":"gpt2-medium","rank_in_archive_order":2,"of":2,"metrics":{"BLEU-1":"59.31","BLEU-2":"25.94","BLEU-3":"15.3","BLEU-4":"9.17","BertScore":"94.76","ROUGE-1":"46.32","ROUGE-2":"24.14","ROUGE-L":"45.88"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2304.06634","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}