相关论文: Beyond Goldfish Memory: Long-Term Open-Domain Conv…

Recent work in open-domain conversational agents has demonstrated that significant improvements in model engagingness and humanness metrics can be achieved via massive scaling in both pre-training data and model size (Adiwardana et al.,…

Existing speech recognition systems are typically built at the sentence level, although it is known that dialog context, e.g. higher-level knowledge that spans across sentences or speakers, can help the processing of long conversations. The…

With the availability of massive general-domain dialogue data, pre-trained dialogue generation appears to be super appealing to transfer knowledge from the general domain to downstream applications. In most existing work, such transferable…

Ever since the successful application of sequence to sequence learning for neural machine translation systems, interest has surged in its applicability towards language generation in other problem domains. Recent work has investigated the…

Autoregressive models used to generate responses in open-domain dialogue systems often struggle to take long-term context into account and to maintain consistency over a dialogue. Previous research in open-domain dialogue generation has…

In many real-world scenarios, the absence of external knowledge source like Wikipedia restricts question answering systems to rely on latent internal knowledge in limited dialogue data. In addition, humans often seek answers by asking…

Building a dialogue system that can communicate naturally with humans is a challenging yet interesting problem of agent-based computing. The rapid growth in this area is usually hindered by the long-standing problem of data scarcity as…

In order for large language models to achieve true conversational continuity and benefit from experiential learning, they need memory. While research has focused on the development of complex memory systems, it remains unclear which types…

The ability of a machine to communicate with humans has long been associated with the general success of AI. This dates back to Alan Turing's epoch-making work in the early 1950s, which proposes that a machine's intelligence can be tested…

Large language models (LLMs) have demonstrated remarkable performance in zero-shot dialogue state tracking (DST), reducing the need for task-specific training. However, conventional DST benchmarks primarily focus on structured user-agent…

Open-domain multi-turn conversations mainly have three features, which are hierarchical semantic structure, redundant information, and long-term dependency. Grounded on these, selecting relevant context becomes a challenge step for…

Long-term, open-domain dialogue capabilities are essential for chatbots aiming to recall past interactions and demonstrate emotional intelligence (EI). Yet, most existing research relies on synthetic, LLM-generated data, leaving open…

Understanding the dynamics of counseling conversations is an important task, yet it is a challenging NLP problem regardless of the recent advance of Transformer-based pre-trained language models. This paper proposes a systematic approach to…

This paper analyzes some speed and performance improvement methods of Transformer architecture in recent years, mainly its application in dedicated model training. The dedicated model studied here refers to the open domain persona-aware…

We investigate the task of modeling open-domain, multi-turn, unstructured, multi-participant, conversational dialogue. We specifically study the effect of incorporating different elements of the conversation. Unlike previous efforts, which…

One challenge for dialogue agents is recognizing feelings in the conversation partner and replying accordingly, a key communicative skill. While it is straightforward for humans to recognize and acknowledge others' feelings in a…

Maintaining engagement and consistency is particularly important in dialogue systems. Existing works have improved the performance of dialogue systems by intentionally learning interlocutor personas with sophisticated network structures.…

Frozen models trained to mimic static datasets can never improve their performance. Models that can employ internet-retrieval for up-to-date information and obtain feedback from humans during deployment provide the promise of both adapting…

Existing dialog datasets contain a sequence of utterances and responses without any explicit background knowledge associated with them. This has resulted in the development of models which treat conversation as a sequence-to-sequence…

Longitudinal Dialogues (LD) are the most challenging type of conversation for human-machine dialogue systems. LDs include the recollections of events, personal thoughts, and emotions specific to each individual in a sparse sequence of…