Related papers: An End-to-End Document-Level Neural Discourse Pars…
Aiming for a better integration of data-driven and linguistically-inspired approaches, we explore whether RST Nuclearity, assigning a binary assessment of importance between text segments, can be replaced by automatically generated,…
Structured text understanding on Visually Rich Documents (VRDs) is a crucial part of Document Intelligence. Due to the complexity of content and layout in VRDs, structured text understanding has been a challenging task. Most existing…
End-to-end spoken dialogue state tracking (DST) is made difficult by the tandem of having to handle speech input and data scarcity. Combining speech foundation encoders and large language models has been proposed in recent work as to…
Long document classification presents challenges in capturing both local and global dependencies due to their extensive content and complex structure. Existing methods often struggle with token limits and fail to adequately model…
Current open-domain neural semantics parsers show impressive performance. However, closer inspection of the symbolic meaning representations they produce reveals significant weaknesses: sometimes they tend to merely copy character sequences…
Reasoning, the ability to logically draw conclusions from existing knowledge, is a hallmark of human. Together with perception, they constitute the two major themes of artificial intelligence. While deep learning has pushed the limit of…
Semantic role labeling (SRL), also known as shallow semantic parsing, is an important yet challenging task in NLP. Motivated by the close correlation between syntactic and semantic structures, traditional discrete-feature-based SRL…
In this work, we present novel approaches to exploit sentential context for neural machine translation (NMT). Specifically, we first show that a shallow sentential context extracted from the top encoder layer only, can improve translation…
We consider a new perspective on dialog state tracking (DST), the task of estimating a user's goal through the course of a dialog. By formulating DST as a semantic parsing task over hierarchical representations, we can incorporate semantic…
Recently BERT has been adopted for document encoding in state-of-the-art text summarization models. However, sentence-based extractive models often result in redundant or uninformative phrases in the extracted summaries. Also, long-range…
In automatic speech recognition (ASR) what a user says depends on the particular context she is in. Typically, this context is represented as a set of word n-grams. In this work, we present a novel, all-neural, end-to-end (E2E) ASR sys- tem…
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…
Document translation poses a challenge for Neural Machine Translation (NMT) systems. Most document-level NMT systems rely on meticulously curated sentence-level parallel data, assuming flawless extraction of text from documents along with…
Recently, neural language models (LMs) have demonstrated impressive abilities in generating high-quality discourse. While many recent papers have analyzed the syntactic aspects encoded in LMs, there has been no analysis to date of the…
End-to-end architectures have been recently proposed for spoken language understanding (SLU) and semantic parsing. Based on a large amount of data, those models learn jointly acoustic and linguistic-sequential features. Such architectures…
End-to-end speech recognition is a promising technology for enabling compact automatic speech recognition (ASR) systems since it can unify the acoustic and language model into a single neural network. However, as a drawback, training of…
Deep neural networks have achieved significant improvements in information retrieval (IR). However, most existing models are computational costly and can not efficiently scale to long documents. This paper proposes a novel End-to-End neural…
Recent breakthroughs in deep learning often rely on representation learning and knowledge transfer. In recent years, unsupervised and self-supervised techniques for learning speech representation were developed to foster automatic speech…
The addition of syntax-aware decoding in Neural Machine Translation (NMT) systems requires an effective tree-structured neural network, a syntax-aware attention model and a language generation model that is sensitive to sentence structure.…
Legal documents are unstructured, use legal jargon, and have considerable length, making them difficult to process automatically via conventional text processing techniques. A legal document processing system would benefit substantially if…