Related papers: KwaiChat: A Large-Scale Video-Driven Multilingual …
This paper introduces QCaption, a novel video captioning and Q&A pipeline that enhances video analytics by fusing three models: key frame extraction, a Large Multimodal Model (LMM) for image-text analysis, and a Large Language Model (LLM)…
We present a new large-scale multilingual video description dataset, VATEX, which contains over 41,250 videos and 825,000 captions in both English and Chinese. Among the captions, there are over 206,000 English-Chinese parallel translation…
Existing studies in dialogue system research mostly treat task-oriented dialogue and chit-chat as separate domains. Towards building a human-like assistant that can converse naturally and seamlessly with users, it is important to build a…
Existing datasets for audio understanding primarily focus on single-turn interactions (i.e. audio captioning, audio question answering) for describing audio in natural language, thus limiting understanding audio via interactive dialogue. To…
The uptake of deep learning in natural language generation (NLG) led to the release of both small and relatively large parallel corpora for training neural models. The existing data-to-text datasets are, however, aimed at task-oriented…
This study focuses on emotion-sensitive spoken dialogue in human-machine speech interaction. With the advancement of Large Language Models (LLMs), dialogue systems can handle multimodal data, including audio. Recent models have enhanced the…
Large Language Models (LLMs) have attained the impressive capability to resolve a wide range of NLP tasks by fine-tuning high-quality instruction data. However, collecting human-written data of high quality, especially multi-turn dialogues,…
Aligning large language models (LLMs) with human preferences has proven to drastically improve usability and has driven rapid adoption as demonstrated by ChatGPT. Alignment techniques such as supervised fine-tuning (SFT) and reinforcement…
This paper introduces the Ubuntu Dialogue Corpus, a dataset containing almost 1 million multi-turn dialogues, with a total of over 7 million utterances and 100 million words. This provides a unique resource for research into building…
Recent advancements in reference-free learned metrics for open-domain dialogue evaluation have been driven by the progress in pre-trained language models and the availability of dialogue data with high-quality human annotations. However,…
Existing dialogue corpora and models are typically designed under two disjoint motives: while task-oriented systems focus on achieving functional goals (e.g., booking hotels), open-domain chatbots aim at making socially engaging…
The development of chatbots requires collecting a large number of human-chatbot dialogues to reflect the breadth of users' sociodemographic backgrounds and conversational goals. However, the resource requirements to conduct the respective…
We present MeetDot, a videoconferencing system with live translation captions overlaid on screen. The system aims to facilitate conversation between people who speak different languages, thereby reducing communication barriers between…
Large language models (LLMs), such as ChatGPT, have demonstrated outstanding performance in various fields, particularly in natural language understanding and generation tasks. In complex application scenarios, users tend to engage in…
Collecting human-chatbot dialogues typically demands substantial manual effort and is time-consuming, which limits and poses challenges for research on conversational AI. In this work, we propose DialogueForge - a framework for generating…
While conversing with chatbots, humans typically tend to ask many questions, a significant portion of which can be answered by referring to large-scale knowledge graphs (KG). While Question Answering (QA) and dialog systems have been…
Large language models (LLMs) increasingly serve as educational tools, yet evaluating their teaching capabilities remains challenging due to the resource-intensive, context-dependent, and methodologically complex nature of teacher-student…
Code-switching is a widespread practice among the world's multilingual majority, yet few benchmarks accurately reflect its complexity in everyday communication. We present PingPong, a benchmark for natural multi-party code-switching…
Large Language Models (LLMs) have revolutionized various industries by harnessing their power to improve productivity and facilitate learning across different fields. One intriguing application involves combining LLMs with visual models to…
Mental health care poses an increasingly serious challenge to modern societies. In this context, there has been a surge in research that utilizes information technologies to address mental health problems, including those aiming to develop…