相关论文: WEBDial, a Multi-domain, Multitask Statistical Dia…

Large language models for vertical domains are bottlenecked by the scarcity of complex, domain-specific task-oriented dialogues. Existing data acquisition pipelines face a persistent trilemma: expert annotation is expensive, real-world…

Tool-Augmented Language Models (TALMs) leverage external APIs to answer user queries across various domains. However, existing benchmark datasets for TALM research often feature simplistic dialogues that do not reflect real-world scenarios,…

The basic unit of meaning on the Semantic Web is the RDF statement, or triple, which combines a distinct subject, predicate and object to make a definite assertion about the world. A set of triples constitutes a graph, to which they give a…

The interdisciplinary nature of the Semantic Web and the many projects put forward by the community led to a large number of widely accepted serialization formats for RDF. Most of these RDF syntaxes have been developed out of a necessity to…

In this paper a Set Theoretic approach has been reported for analyzing inter-relationship between any numbers of RDF Graphs. An RDF Graph represents triples in Resource Description Format of semantic web. So the identification and…

We present FlipDial, a generative model for visual dialogue that simultaneously plays the role of both participants in a visually-grounded dialogue. Given context in the form of an image and an associated caption summarising the contents of…

We propose MultiDoc2Dial, a new task and dataset on modeling goal-oriented dialogues grounded in multiple documents. Most previous works treat document-grounded dialogue modeling as a machine reading comprehension task based on a single…

Many systems can be described in terms of networks of discrete elements and their various relationships to one another. A semantic network, or multi-relational network, is a directed labeled graph consisting of a heterogeneous set of…

The search for a standardized optimum way to communicate using natural language dialog has involved a lot of research. However, due to the diversity of communication domains, we think that this is extremely difficult to achieve and…

Earnings calls represent a uniquely rich and semi-structured source of financial communication, blending scripted managerial commentary with unscripted analyst dialogue. Although recent advances in financial sentiment analysis have…

Dialogue systems have been widely applied in many scenarios and are now more powerful and ubiquitous than ever before. With large neural models and massive available data, current dialogue systems have access to more knowledge than any…

Process-driven dialogue systems, which operate under strict predefined process constraints, are essential in customer service and equipment maintenance scenarios. Although Large Language Models (LLMs) have shown remarkable progress in…

The Semantic Web, an extension of the current web, provides a common framework that makes data machine understandable and also allows data to be shared and reused across various applications. Resource Description Framework (RDF), a…

In this paper, we present a novel approach -- called WaterFowl -- for the storage of RDF triples that addresses some key issues in the contexts of big data and the Semantic Web. The architecture of our prototype, largely based on the use of…

We propose a novel model to address the task of Visual Dialog which exhibits complex dialog structures. To obtain a reasonable answer based on the current question and the dialog history, the underlying semantic dependencies between dialog…

For task-oriented dialog systems to be maximally useful, it must be able to process conversations in a way that is (1) generalizable with a small number of training examples for new task domains, and (2) robust to user input in various…

Human conversation is inherently complex, often spanning many different topics/domains. This makes policy learning for dialogue systems very challenging. Standard flat reinforcement learning methods do not provide an efficient framework for…

Reinforcement learning (RL) is a promising approach to solve dialogue policy optimisation. Traditional RL algorithms, however, fail to scale to large domains due to the curse of dimensionality. We propose a novel Dialogue Management…

We investigate the problem of multi-domain Dialogue State Tracking (DST) with open vocabulary, which aims to extract the state from the dialogue. Existing approaches usually concatenate previous dialogue state with dialogue history as the…

Goal oriented dialogue systems were originally designed as a natural language interface to a fixed data-set of entities that users might inquire about, further described by domain, slots, and values. As we move towards adaptable dialogue…