Related papers: Reason first, then respond: Modular Generation for…
Recent progress in generative models has stimulated significant innovations in many fields, such as image generation and chatbots. Despite their success, these models often produce sketchy and misleading solutions for complex multi-agent…
Knowledge-based, open-domain dialogue generation aims to build chit-chat systems that talk to humans using mined support knowledge. Many types and sources of knowledge have previously been shown to be useful as support knowledge. Even in…
Reinforcement learning (RL) agents aim at learning by interacting with an environment, and are not designed for representing or reasoning with declarative knowledge. Knowledge representation and reasoning (KRR) paradigms are strong in…
Can language models (LM) ground question-answering (QA) tasks in the knowledge base via inherent relational reasoning ability? While previous models that use only LMs have seen some success on many QA tasks, more recent methods include…
Large language models have become increasingly popular and demonstrated remarkable performance in various natural language processing (NLP) tasks. However, these models are typically computationally expensive and difficult to be deployed in…
Pre-training models have been proved effective for a wide range of natural language processing tasks. Inspired by this, we propose a novel dialogue generation pre-training framework to support various kinds of conversations, including…
Multi-hop Question Answering (QA) requires the machine to answer complex questions by finding scattering clues and reasoning from multiple documents. Graph Network (GN) and Question Decomposition (QD) are two common approaches at present.…
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…
Although neural models have achieved competitive results in dialogue systems, they have shown limited ability in representing core semantics, such as ignoring important entities. To this end, we exploit Abstract Meaning Representation (AMR)…
Sequence-to-sequence models have been applied to the conversation response generation problem where the source sequence is the conversation history and the target sequence is the response. Unlike translation, conversation responding is…
End-to-end dialog systems have become very popular because they hold the promise of learning directly from human to human dialog interaction. Retrieval and Generative methods have been explored in this area with mixed results. A key element…
Question answering (QA) has become an important application in the advanced development of large language models. General pre-trained large language models for question-answering are not trained to properly understand the knowledge or…
End-to-end models for goal-orientated dialogue are challenging to train, because linguistic and strategic aspects are entangled in latent state vectors. We introduce an approach to learning representations of messages in dialogues by…
Efforts towards endowing robots with the ability to speak have benefited from recent advancements in natural language processing, in particular large language models. However, current language models are not fully incremental, as their…
Knowledge Graph(KG) grounded conversations often use large pre-trained models and usually suffer from fact hallucination. Frequently entities with no references in knowledge sources and conversation history are introduced into responses,…
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…
This paper studies joint models for selecting correct answer sentences among the top $k$ provided by answer sentence selection (AS2) modules, which are core components of retrieval-based Question Answering (QA) systems. Our work shows that…
The zero-shot chain of thought (CoT) approach is often used in question answering (QA) by language models (LMs) for tasks that require multiple reasoning steps. However, some QA tasks hinge more on accessing relevant knowledge than on…
Large Language Models (LLMs) achieve impressive performance across many tasks but remain prone to hallucination, especially in long-form generation where redundant retrieved contexts and lengthy reasoning chains amplify factual errors.…
Generative seq2seq dialogue systems are trained to predict the next word in dialogues that have already occurred. They can learn from large unlabeled conversation datasets, build a deep understanding of conversational context, and generate…