{"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/tricy-trigger-guided-data-to-text-generation-1","title":"TrICy: Trigger-guided Data-to-text Generation with Intent aware Attention-Copy","arxiv_id":"2402.01714","date":"2024-01-25","proceeding":"IEEE/ACM Transactions on Audio, Speech, and Language Processing 2024 1","authors":["Vibhav Agarwal","Sourav Ghosh","Harichandana BSS","Himanshu Arora","Barath Raj Kandur Raja"],"abstract":"Data-to-text (D2T) generation is a crucial task in many natural language understanding (NLU) applications and forms the foundation of task-oriented dialog systems. In the context of conversational AI solutions that can work directly with local data on the user's device, architectures utilizing large pre-trained language models (PLMs) are impractical for on-device deployment due to a high memory footprint. To this end, we propose TrICy, a novel lightweight framework for an enhanced D2T task that generates text sequences based on the intent in context and may further be guided by user-provided triggers. We leverage an attention-copy mechanism to predict out-of-vocabulary (OOV) words accurately. Performance analyses on E2E NLG dataset (BLEU: 66.43%, ROUGE-L: 70.14%), WebNLG dataset (BLEU: Seen 64.08%, Unseen 52.35%), and our Custom dataset related to text messaging applications, showcase our architecture's effectiveness. Moreover, we show that by leveraging an optional trigger input, data-to-text generation quality increases significantly and achieves the new SOTA score of 69.29% BLEU for E2E NLG. Furthermore, our analyses show that TrICy achieves at least 24% and 3% improvement in BLEU and METEOR respectively over LLMs like GPT-3, ChatGPT, and Llama 2. We also demonstrate that in some scenarios, performance improvement due to triggers is observed even when they are absent in training.","url_abs":"https://arxiv.org/abs/2402.01714v1","url_pdf":"https://arxiv.org/pdf/2402.01714v1.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":[],"tasks":[{"task_slug":"data-to-text-generation","task_name":"Data-to-Text Generation"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"text-generation","task_name":"Text 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":"dropout","method_name":"Dropout"},{"method_slug":"gpt-3","method_name":"GPT-3"},{"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":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/data-to-text-generation-on-e2e-nlg-challenge","task":"Data-to-Text Generation","dataset":"E2E NLG Challenge","model":"TrICy (trK = 0)","rank_in_archive_order":3,"of":11,"metrics":{"BLEU":"66.43","Number of parameters (M)":"4.7","ROUGE-L":"70.14"},"uses_additional_data":false},{"leaderboard":"/sota/data-to-text-generation-on-webnlg","task":"Data-to-Text Generation","dataset":"WebNLG","model":"TrICy (trK = trk* = 0.24)","rank_in_archive_order":10,"of":20,"metrics":{"BLEU":"64.73","METEOR":"45.53","Number of parameters (M)":"6.2"},"uses_additional_data":false},{"leaderboard":"/sota/data-to-text-generation-on-webnlg","task":"Data-to-Text Generation","dataset":"WebNLG","model":"TrICy (trK = 0)","rank_in_archive_order":12,"of":20,"metrics":{"BLEU":"64.08","METEOR":"45.23","Number of parameters (M)":"6.2"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}