Related papers: Conversational Semantic Parsing
This paper gives an overview of the Schema-Guided Dialogue State Tracking task of the 8th Dialogue System Technology Challenge. The goal of this task is to develop dialogue state tracking models suitable for large-scale virtual assistants,…
These lecture notes cover basic automata-theoretic concepts and logical formalisms for the modeling and verification of concurrent and distributed systems. Many of these concepts naturally extend the classical automata and logics over…
In spoken Task-Oriented Dialogue (TOD) systems, the choice of the semantic representation describing the users' requests is key to a smooth interaction. Indeed, the system uses this representation to reason over a database and its domain…
This paper describes a neural semantic parser that maps natural language utterances onto logical forms which can be executed against a task-specific environment, such as a knowledge base or a database, to produce a response. The parser…
Recent work in semantic parsing for question answering has focused on long and complicated questions, many of which would seem unnatural if asked in a normal conversation between two humans. In an effort to explore a conversational QA…
Conversational search has been regarded as the next-generation search paradigm. Constrained by data scarcity, most existing methods distill the well-trained ad-hoc retriever to the conversational retriever. However, these methods, which…
Text-based dialogues are now widely used to solve real-world problems. In cases where solution strategies are already known, they can sometimes be codified into workflows and used to guide humans or artificial agents through the task of…
Learning high-quality dialogue representations is essential for solving a variety of dialogue-oriented tasks, especially considering that dialogue systems often suffer from data scarcity. In this paper, we introduce Dialogue Sentence…
Conversational assistants are increasingly popular across diverse real-world applications, highlighting the need for advanced multimodal speech modeling. Speech, as a natural mode of communication, encodes rich user-specific characteristics…
We combine character-level and contextual language model representations to improve performance on Discourse Representation Structure parsing. Character representations can easily be added in a sequence-to-sequence model in either one…
Conversational modeling is an important task in natural language understanding and machine intelligence. Although previous approaches exist, they are often restricted to specific domains (e.g., booking an airline ticket) and require…
Discrete speech representation learning has recently attracted increasing interest in both acoustic and semantic modeling. Existing approaches typically encode 16 kHz waveforms into discrete tokens at a rate of 25 or 50 tokens per second.…
Emotions play a central role in human communication, shaping trust, engagement, and social interaction. As artificial intelligence systems powered by large language models become increasingly integrated into everyday life, enabling them to…
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…
Building machines that can understand text like humans is an AI-complete problem. A great deal of research has already gone into this, with astounding results, allowing everyday people to discuss with their telephones, or have their reading…
Learning effective representations of sentences is one of the core missions of natural language understanding. Existing models either train on a vast amount of text, or require costly, manually curated sentence relation datasets. We show…
Implicit discourse relation classification is one of the most difficult steps in discourse parsing. The difficulty stems from the fact that the coherence relation must be inferred based on the content of the discourse relational arguments.…
The task of Semantic Parsing can be approximated as a transformation of an utterance into a logical form graph where edges represent semantic roles and nodes represent word senses. The resulting representation should be capture the meaning…
Neural network models are capable of generating extremely natural sounding conversational interactions. Nevertheless, these models have yet to demonstrate that they can incorporate content in the form of factual information or…
Although self-attention networks (SANs) have advanced the state-of-the-art on various NLP tasks, one criticism of SANs is their ability of encoding positions of input words (Shaw et al., 2018). In this work, we propose to augment SANs with…