Related papers: Lexicon-injected Semantic Parsing for Task-Oriente…

The dominant paradigm for semantic parsing in recent years is to formulate parsing as a sequence-to-sequence task, generating predictions with auto-regressive sequence decoders. In this work, we explore an alternative paradigm. We formulate…

Syntactic structure of a sentence text is correlated with the prosodic structure of the speech that is crucial for improving the prosody and naturalness of a text-to-speech (TTS) system. Nowadays TTS systems usually try to incorporate…

Deep learning methods have enabled task-oriented semantic parsing of increasingly complex utterances. However, a single model is still typically trained and deployed for each task separately, requiring labeled training data for each, which…

Task-oriented semantic parsing is a critical component of virtual assistants, which is responsible for understanding the user's intents (set reminder, play music, etc.). Recent advances in deep learning have enabled several approaches to…

Text classification, a core component of task-oriented dialogue systems, attracts continuous research from both the research and industry community, and has resulted in tremendous progress. However, existing method does not consider the use…

Representing structured text from complex documents typically calls for different machine learning techniques, such as language models for paragraphs and convolutional neural networks (CNNs) for table extraction, which prohibits drawing…

Task-oriented dialogue focuses on conversational agents that participate in user-initiated dialogues on domain-specific topics. In contrast to chatbots, which simply seek to sustain open-ended meaningful discourse, existing task-oriented…

Transformer has demonstrated its great power to learn contextual word representations for multiple languages in a single model. To process multilingual sentences in the model, a learnable vector is usually assigned to each language, which…

Parsing accuracy using efficient greedy transition systems has improved dramatically in recent years thanks to neural networks. Despite striking results in dependency parsing, however, neural models have not surpassed state-of-the-art…

Virtual assistants such as Amazon Alexa, Apple Siri, and Google Assistant often rely on a semantic parsing component to understand which action(s) to execute for an utterance spoken by its users. Traditionally, rule-based or statistical…

Semantic communication is an emerging paradigm that focuses on understanding and delivering semantics, or meaning of messages. Most existing semantic communication solutions define semantic meaning as the meaning of object labels recognized…

Over the last few years, machine learning over graph structures has manifested a significant enhancement in text mining applications such as event detection, opinion mining, and news recommendation. One of the primary challenges in this…

Generating fluent natural language responses from structured semantic representations is a critical step in task-oriented conversational systems. Avenues like the E2E NLG Challenge have encouraged the development of neural approaches,…

Robust state tracking for task-oriented dialogue systems currently remains restricted to a few popular languages. This paper shows that given a large-scale dialogue data set in one language, we can automatically produce an effective…

Discourse structure is integral to understanding a text and is helpful in many NLP tasks. Learning latent representations of discourse is an attractive alternative to acquiring expensive labeled discourse data. Liu and Lapata (2018) propose…

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…

Recurrent neural network (RNN) based joint intent classification and slot tagging models have achieved tremendous success in recent years for building spoken language understanding and dialog systems. However, these models suffer from poor…

Finding an optimal word representation algorithm is particularly important in terms of domain specific data, as the same word can have different meanings and hence, different representations depending on the domain and context. While…

We describe a transfer method based on annotation projection to develop a dependency-based semantic role labeling system for languages for which no supervised linguistic information other than parallel data is available. Unlike previous…

Semantic role labeling (SRL) is a fundamental yet challenging task in the NLP community. Recent works of SRL mainly fall into two lines: 1) BIO-based; 2) span-based. Despite ubiquity, they share some intrinsic drawbacks of not considering…