000 03982nas a2200385 a 4500
005 20260818085045.0
008 240229s20239999th u m tt 000 a eng d
035 _a.b12421820
099 _aAIT Thesis no.DSAI-23-11
100 0 _aWorachot Nakduk
245 1 0 _aContrastive learning with template{u2019}s prompt in multiple aspect dialogue summarization
260 _aPathum Thani, Thailand :
_bAsian Institute of Technology,
_c2023
300 _a39 leaves :
_bill.
490 1 _aThesis ;
_vno. DSAI-23-11
500 _aA thesis submitted in partial fulfillment of the requirements for the degree of Master of Engineering in Data Science and Artificial Intelligence, School of Engineering and Technology
502 _aThesis (M. Eng.) - Asian Institute of Technology, 2023
520 _aDialogue summarizing compresses the essential information from a conversation into a concise paragraph, enabling individuals to efficiently understand the main ideas without needing to look into the surrounding context. Recently, pre-trained language models have the potential to be helpful for dialogue summaries. Due to the engagement of sev eral participants, topic deviations, frequent references to previous statements, diverse interaction messages, and specific vocabulary, these variables contribute to increased complexity for summarizers. It can generate misinformation and generate misleading content that only covers partial facts of a conversation. Furthermore, a single discourse has the ability to incorporate multiple topics without a clearly defined boundary between them. The realistic importance of the dialogue summarization model can be better char acterized by assessing numerous aspects, such as the speaker{u2019}s goal or the specific topic under discussion. However, current summarization systems produce generic summaries that lack personalization and fail to align with customer preferences and expectations. To address this limitation, create customized different aspects of the produced summaries by engaging with the summarization process through textual submission in a format of descriptive prompts. In this paper, we present Contrastive Learning with a Topic Length Template Prompt for Dialogue Summarization. We select a topic either from the goal summary or attractive topics. These topics serve as a control signal, guided by a template{u2019}s prompt. We utilize contrastive learning methods to enhance the diversity of prompts in the template by using synonym replacement and random topics. These methods enable us to generate both positive and negative topics, thereby increasing the quantity of meaningful information available for training. Additionally, we use special tokens to highlight words and prompts to focus on important keywords. Experimentally, we show that our model can increase the ROUGE score in the DialogSum testing dataset. Our models are available at https://github.com/worachot-n/topic-length.git
650 0 _aNatural language processing (Computer science)
700 0 _aChaklam Silpasuwanchai,
_eChairperson
700 0 _aMongkol Ekpanyapong,
_eExamination Committee
700 1 _aDailey, Matthew N.,
_eExamination Committee
710 2 _aHis Majesty the King{u2019}s Scholarships (Thailand),
_eScholarship Donor
810 2 _aAsian Institute of Technology.
_tThesis ;
_vno. DSAI-23-11
856 4 0 _3Full-Text
_uhttp://203.159.5.9/ait-thesis/detail.php?q=B20439
907 _a.b12421820
_bmnait
_ca
902 _a250307
998 _b0
_c240319
_dm
_ea
_fa
_g0
945 _lmnarc
945 _lmnarc
942 _c67
942 _c40
909 _aBarcode : -
_bCREATED : 2024-02-29
_cRECORD # : i1348803x
_dLPATRON : 0
_eLCHKIN : -
_f# RENEWALS : 0
_g# OVERDUE : 0
_hIUSE3 : 0
_iTOT CHKOUT : 0
_jTOT RENEW : 0
909 _aBarcode : 30050120898811
_bCREATED : 2025-07-03
_cRECORD # : i13537544
_dLPATRON : 0
_eLCHKIN : -
_f# RENEWALS : 0
_g# OVERDUE : 0
_hIUSE3 : 0
_iTOT CHKOUT : 0
_jTOT RENEW : 0
999 _c22947
_d22947