Improving the generation of personalised descriptions
Referring expression generation (REG) models that use speaker-dependent information require a considerable amount of training data produced by every individual speaker, or may otherwise perform poorly. In this work we propose a simple personalised method for this task, in which speakers are grouped into profiles according to their referential behaviour. Intrinsic evaluation shows that the use of speaker{'}s profiles generally outperforms the personalised method found in previous work.
Code (0)
등록된 구현이 없습니다.
Tasks
Referring ExpressionReferring expression generationText GenerationSimilar Papers 제목 키워드 기반
Towards Music Captioning: Generating Music Playlist Descriptions
Descriptions are often provided along with recommendations to help users' discovery. Recommending automatically generated music playlists (e.g. personalised playlists) introduces the problem of generating descriptions. I…
Music CaptioningListener's Social Identity Matters in Personalised Response Generation
Personalised response generation enables generating human-like responses by means of assigning the generator a social identity. However, pragmatics theory suggests that human beings adjust the way of speaking based on no…
Response GenerationListener’s Social Identity Matters in Personalised Response Generation
Personalised response generation enables generating human-like responses by means of assigning the generator a social identity. However, pragmatics theory suggests that human beings adjust the way of speaking based on no…
Response GenerationPersonalised Distillation: Empowering Open-Sourced LLMs with Adaptive Learning for Code Generation
With the rise of powerful closed-sourced LLMs (ChatGPT, GPT-4), there are increasing interests in distilling the capabilies of close-sourced LLMs to smaller open-sourced LLMs. Previous distillation methods usually prompt…
Code GenerationHumanEvalPREF: Reference-Free Evaluation of Personalised Text Generation in LLMs
Personalised text generation is essential for user-centric information systems, yet most evaluation methods overlook the individuality of users. We introduce \textbf{PREF}, a \textbf{P}ersonalised \textbf{R}eference-free…
Text Generation