Related papers: Document-aware Positional Encoding and Linguistic-…

We propose a Cross-lingual Encoder-Decoder model that simultaneously translates and generates sentences with Semantic Role Labeling annotations in a resource-poor target language. Unlike annotation projection techniques, our model does not…

Writing style is a combination of consistent decisions associated with a specific author at different levels of language production, including lexical, syntactic, and structural. In this paper, we introduce a style-aware neural model to…

This paper proposes a structure-aware decoding method based on large language models to address the difficulty of traditional approaches in maintaining both semantic integrity and structural consistency in nested and overlapping entity…

Multi-Source Domain Adaptation (MSDA) aims to mitigate changes in data distribution when transferring knowledge from multiple labeled source domains to an unlabeled target domain. However, existing MSDA techniques assume target domain…

Deep language models learning a hierarchical representation proved to be a powerful tool for natural language processing, text mining and information retrieval. However, representations that perform well for retrieval must capture semantic…

Most of existing extractive multi-document summarization (MDS) methods score each sentence individually and extract salient sentences one by one to compose a summary, which have two main drawbacks: (1) neglecting both the intra and…

Automatic summarisation is a popular approach to reduce a document to its main arguments. Recent research in the area has focused on neural approaches to summarisation, which can be very data-hungry. However, few large datasets exist and…

Document-level machine translation incorporates inter-sentential dependencies into the translation of a source sentence. In this paper, we propose a new framework to model cross-sentence dependencies by training neural machine translation…

Self-supervised representation learning of Multivariate Time Series (MTS) is a challenging task and attracts increasing research interests in recent years. Many previous works focus on the pretext task of self-supervised learning and…

Understanding images without explicit supervision has become an important problem in computer vision. In this paper, we address image captioning by generating language descriptions of scenes without learning from annotated pairs of images…

Abstractive multi-document summarization (MDS) is the task of automatically summarizing information in multiple documents, from news articles to conversations with multiple speakers. The training approaches for current MDS models can be…

Although many context-aware neural machine translation models have been proposed to incorporate contexts in translation, most of those models are trained end-to-end on parallel documents aligned in sentence-level. Because only a few domains…

Prior works have demonstrated that implicit representations trained only for reconstruction tasks typically generate encodings that are not useful for semantic tasks. In this work, we propose a method that contextualises the encodings of…

Many useful tasks on scientific documents, such as topic classification and citation prediction, involve corpora that span multiple scientific domains. Typically, such tasks are accomplished by representing the text with a vector embedding…

Gestures are integral components of face-to-face communication. They unfold over time, often following predictable movement phases of preparation, stroke, and retraction. Yet, the prevalent approach to automatic gesture detection treats the…

Recently, document-level neural machine translation (NMT) has become a hot topic in the community of machine translation. Despite its success, most of existing studies ignored the discourse structure information of the input document to be…

Language models based on the Transformer architecture achieve excellent results in many language-related tasks, such as text classification or sentiment analysis. However, despite the architecture of these models being well-defined, little…

Transformer architecture has enabled recent progress in speech enhancement. Since Transformers are position-agostic, positional encoding is the de facto standard component used to enable Transformers to distinguish the order of elements in…

Writing a survey paper on one research topic usually needs to cover the salient content from numerous related papers, which can be modeled as a multi-document summarization (MDS) task. Existing MDS datasets usually focus on producing the…

Some Transformer-based models can perform cross-lingual transfer learning: those models can be trained on a specific task in one language and give relatively good results on the same task in another language, despite having been pre-trained…