Related papers: PLATO-K: Internal and External Knowledge Enhanced …
Task-oriented dialogue systems have been plagued by the difficulties of obtaining large-scale and high-quality annotated conversations. Furthermore, most of the publicly available datasets only include written conversations, which are…
Document-grounded dialogue (DGD) uses documents as external knowledge for dialogue generation. Correctly understanding the dialogue context is crucial for selecting knowledge from the document and generating proper responses. In this paper,…
Existing dialog systems are all monolingual, where features shared among different languages are rarely explored. In this paper, we introduce a novel multilingual dialogue system. Specifically, we augment the sequence to sequence framework…
Hitherto statistical type inference systems rely thoroughly on supervised learning approaches, which require laborious manual effort to collect and label large amounts of data. Most Turing-complete imperative languages share similar…
In this paper, we present a system to showcase the capabilities of the latest state-of-the-art retrieval augmented generation models trained on knowledge-intensive language tasks, such as slot filling, open domain question answering,…
Recently, large language models (LLMs) have gained much attention for the emergence of human-comparable capabilities and huge potential. However, for open-domain implicit question-answering problems, LLMs may not be the ultimate solution…
Knowledge graph-based dialogue systems can narrow down knowledge candidates for generating informative and diverse responses with the use of prior information, e.g., triple attributes or graph paths. However, most current knowledge graph…
Achieving true human-like ability to conduct a conversation remains an elusive goal for open-ended dialogue systems. We posit this is because extant approaches towards natural language generation (NLG) are typically construed as end-to-end…
Recent works have attempted to integrate external knowledge into LLMs to address the limitations and potential factual errors in LLM-generated content. However, how to retrieve the correct knowledge from the large amount of external…
We study knowledge-grounded dialogue generation with pre-trained language models. Instead of pursuing new state-of-the-art on benchmarks, we try to understand if the knowledge stored in parameters of the pre-trained models is already enough…
Grounding dialogue on external knowledge and interpreting linguistic patterns in dialogue history context, such as ellipsis, anaphora, and co-references is critical for dialogue comprehension and generation. In this paper, we present a…
Self-learning paradigms in large-scale conversational AI agents tend to leverage user feedback in bridging between what they say and what they mean. However, such learning, particularly in Markov-based query rewriting systems have far from…
Recent advances in pre-trained language models have significantly improved neural response generation. However, existing methods usually view the dialogue context as a linear sequence of tokens and learn to generate the next word through…
Conversational interfaces that allow for intuitive and comprehensive access to digitally stored information remain an ambitious goal. In this thesis, we lay foundations for designing conversational search systems by analyzing the…
Knowledge augmentation has significantly enhanced the performance of Large Language Models (LLMs) in knowledge-intensive tasks. However, existing methods typically operate on the simplistic premise that model performance equates with…
Goal-oriented dialogue systems are now being widely adopted in industry where it is of key importance to maintain a rapid prototyping cycle for new products and domains. Data-driven dialogue system development has to be adapted to meet this…
Knowledge-grounded conversation (KGC) shows excellent potential to deliver an engaging and informative response. However, existing approaches emphasize selecting one golden knowledge given a particular dialogue context, overlooking the…
The ability to build and reason about models of the world is essential for situated language understanding. But evaluating world modeling capabilities in modern AI systems -- especially those based on language models -- has proven…
Existing conversational models are handled by a database(DB) and API based systems. However, very often users' questions require information that cannot be handled by such systems. Nonetheless, answers to these questions are available in…
Task-oriented dialogue systems are either modularized with separate dialogue state tracking (DST) and management steps or end-to-end trainable. In either case, the knowledge base (KB) plays an essential role in fulfilling user requests.…