相关论文: Unstructured Knowledge Access in Task-oriented Dia…
This work presents a novel four-stage open-domain QA pipeline R2-D2 (Rank twice, reaD twice). The pipeline is composed of a retriever, passage reranker, extractive reader, generative reader and a mechanism that aggregates the final…
Commonsense and background knowledge is required for a QA model to answer many nontrivial questions. Different from existing work on knowledge-aware QA, we focus on a more challenging task of leveraging external knowledge to generate…
Previous works on knowledge-to-text generation take as input a few RDF triples or key-value pairs conveying the knowledge of some entities to generate a natural language description. Existing datasets, such as WIKIBIO, WebNLG, and E2E,…
Many dialogue systems (DSs) lack characteristics humans have, such as emotion perception, factuality, and informativeness. Enhancing DSs with knowledge alleviates this problem, but, as many ways of doing so exist, keeping track of all…
Knowledge (including structured knowledge such as schema and ontology, and unstructured knowledge such as web corpus) is a critical part of dialog understanding, especially for unseen tasks and domains. Traditionally, such domain-specific…
Current Knowledge-Grounded Dialogue Generation (KDG) models specialize in producing rational and factual responses. However, to establish long-term relationships with users, the KDG model needs the capability to generate responses in a…
Dialog systems have achieved significant progress and have been widely used in various scenarios. The previous researches mainly focused on designing dialog generation models in a single scenario, while comprehensive abilities are required…
This paper considers the reading comprehension task in which multiple documents are given as input. Prior work has shown that a pipeline of retriever, reader, and reranker can improve the overall performance. However, the pipeline system is…
Current task-oriented dialog (TOD) systems mostly manage structured knowledge (e.g. databases and tables) to guide the goal-oriented conversations. However, they fall short of handling dialogs which also involve unstructured knowledge (e.g.…
Recent end-to-end task oriented dialog systems use memory architectures to incorporate external knowledge in their dialogs. Current work makes simplifying assumptions about the structure of the knowledge base, such as the use of triples to…
Knowledge-grounded dialogue systems are intended to convey information that is based on evidence provided in a given source text. We discuss the challenges of training a generative neural dialogue model for such systems that is controlled…
Most existing neural network based task-oriented dialogue systems follow encoder-decoder paradigm, where the decoder purely depends on the source texts to generate a sequence of words, usually suffering from instability and poor…
Performance of spoken language understanding (SLU) can be degraded with automatic speech recognition (ASR) errors. We propose a novel approach to improve SLU robustness by randomly corrupting clean training text with an ASR error simulator,…
Knowledge-grounded dialogue is a task of generating an informative response based on both discourse context and external knowledge. As we focus on better modeling the knowledge selection in the multi-turn knowledge-grounded dialogue, we…
Task-oriented dialogues often require agents to enact complex, multi-step procedures in order to meet user requests. While large language models have found success automating these dialogues in constrained environments, their widespread…
Attention-based encoder-decoder neural network models have recently shown promising results in goal-oriented dialogue systems. However, these models struggle to reason over and incorporate state-full knowledge while preserving their…
Knowledge graphs (KGs) provide structured, verifiable grounding for large language models (LLMs), but current LLM-based systems commonly use KGs as auxiliary structures for text retrieval, leaving their intrinsic quality underexplored. In…
Knowledge-grounded dialogue systems powered by large language models often generate responses that, while fluent, are not attributable to a relevant source of information. Progress towards models that do not exhibit this issue requires…
We study knowledge-grounded dialogue generation with pre-trained language models. To leverage the redundant external knowledge under capacity constraint, we propose equipping response generation defined by a pre-trained language model with…
End-to-end training of neural networks is a promising approach to automatic construction of dialog systems using a human-to-human dialog corpus. Recently, Vinyals et al. tested neural conversation models using OpenSubtitles. Lowe et al.…