Related papers: MultiWOZ-DF -- A Dataflow implementation of the Mu…
Multimodal Large Language Models (MLLMs) have achieved remarkable advances by integrating text, image, and audio understanding within a unified architecture. However, existing distributed training frameworks remain fundamentally data-blind:…
Proposal of large-scale datasets has facilitated research on deep neural models for news summarization. Deep learning can also be potentially useful for spoken dialogue summarization, which can benefit a range of real-life scenarios…
Synthetic data has become an important tool in the fine-tuning of language models to follow instructions and solve complex problems. Nevertheless, the majority of open data to date is often lacking multi-turn data and collected on closed…
Memes are widely used in online social interactions, providing vivid, intuitive, and often humorous means to express intentions and emotions. Existing dialogue datasets are predominantly limited to either manually annotated or pure-text…
We introduce doc2dial, a new dataset of goal-oriented dialogues that are grounded in the associated documents. Inspired by how the authors compose documents for guiding end users, we first construct dialogue flows based on the content…
Designing task-oriented dialogue systems is a challenging research topic, since it needs not only to generate utterances fulfilling user requests but also to guarantee the comprehensibility. Many previous works trained end-to-end (E2E)…
Neural models of dialog rely on generalized latent representations of language. This paper introduces a novel training procedure which explicitly learns multiple representations of language at several levels of granularity. The…
Understanding and characterizing how people interact in information-seeking conversations is crucial in developing conversational search systems. In this paper, we introduce a new dataset designed for this purpose and use it to analyze…
ML-based systems are software systems that incorporates machine learning components such as Deep Neural Networks (DNNs) or Large Language Models (LLMs). While such systems enable advanced features such as high performance computer vision,…
Driven by the recent advances in smart, miniaturized, and mass produced sensors, networked systems, and high-speed data communication and computing, the ability to collect and process larger volumes of higher veracity real-time data from a…
State-of-the-art Datalog engines include expressive features such as ADTs (structured heap values), stratified aggregation and negation, various primitive operations, and the opportunity for further extension using FFIs. Current…
Unlocking the full potential of Knowledge Graphs (KGs) to enable or enhance various semantic and other applications requires Data Management Systems (DMSs) to efficiently store and process the content of KGs. However, the increases in the…
Semantic communication can significantly improve bandwidth utilization in wireless systems by exploiting the meaning behind raw data. However, the advancements achieved through semantic communication are closely dependent on the development…
Task oriented dialog agents provide a natural language interface for users to complete their goal. Dialog State Tracking (DST), which is often a core component of these systems, tracks the system's understanding of the user's goal…
Scaling semantic parsing models for task-oriented dialog systems to new languages is often expensive and time-consuming due to the lack of available datasets. Available datasets suffer from several shortcomings: a) they contain few…
Conversations are always related to certain topics. However, it is challenging to fuse dialogue history and topic information from various sources at the same time in current dialogue generation models because of the input length limit of…
Recent advances in deep learning, and especially the invention of encoder-decoder architectures, has significantly improved the performance of abstractive summarization systems. The majority of research has focused on written documents,…
Non-task oriented dialogue systems have achieved great success in recent years due to largely accessible conversation data and the development of deep learning techniques. Given a context, current systems are able to yield a relevant and…
Dialogue state tracking (DST) is a component of the task-oriented dialogue system. It is responsible for extracting and managing slot values according to dialogue utterances, where each slot represents an essential part of the information…
Building dialogue generation systems in a zero-shot scenario remains a huge challenge, since the typical zero-shot approaches in dialogue generation rely heavily on large-scale pre-trained language generation models such as GPT-3 and T5.…