Related papers: Multi-source Neural Topic Modeling in Multi-view E…

Topic models are used to identify and group similar themes in a set of documents. Recent advancements in deep learning based neural topic models has received significant research interest. In this paper, an approach is proposed that further…

Few-shot learning (FSL) is the task of learning to recognize previously unseen categories of images from a small number of training examples. This is a challenging task, as the available examples may not be enough to unambiguously determine…

Recent work has validated the importance of subword information for word representation learning. Since subwords increase parameter sharing ability in neural models, their value should be even more pronounced in low-data regimes. In this…

Topic models such as LDA, DocNADE, iDocNADEe have been popular in document analysis. However, the traditional topic models have several limitations including: (1) Bag-of-words (BoW) assumption, where they ignore word ordering, (2) Data…

Exploring the predictive capabilities of language models in material science is an ongoing interest. This study investigates the application of language model embeddings to enhance material property prediction in materials science. By…

Topic modeling is a powerful technique for uncovering hidden themes within a collection of documents. However, the effectiveness of traditional topic models often relies on sufficient word co-occurrence, which is lacking in short texts.…

This paper introduces the MERIT Dataset, a multimodal (text + image + layout) fully labeled dataset within the context of school reports. Comprising over 400 labels and 33k samples, the MERIT Dataset is a valuable resource for training…

Embeddings play an important role in end-to-end solutions for multi-modal language processing problems. Although there has been some effort to understand the properties of single-modality embedding spaces, particularly that of text, their…

Sentiment analysis benefits from large, hand-annotated resources in order to train and test machine learning models, which are often data hungry. While some languages, e.g., English, have a vast array of these resources, most…

In a multilingual neural machine translation model that fully shares parameters across all languages, an artificial language token is usually used to guide translation into the desired target language. However, recent studies show that…

One of the long-standing challenges in lexical semantics consists in learning representations of words which reflect their semantic properties. The remarkable success of word embeddings for this purpose suggests that high-quality…

Multi-source translation is an approach to exploit multiple inputs (e.g. in two different languages) to increase translation accuracy. In this paper, we examine approaches for multi-source neural machine translation (NMT) using an…

Topic segmentation is important in understanding scientific documents since it can not only provide better readability but also facilitate downstream tasks such as information retrieval and question answering by creating appropriate…

Knowledge bases (KBs) are paramount in NLP. We employ multiview learning for increasing accuracy and coverage of entity type information in KBs. We rely on two metaviews: language and representation. For language, we consider high-resource…

Topic segmentation of meetings is the task of dividing multi-person meeting transcripts into topic blocks. Supervised approaches to the problem have proven intractable due to the difficulties in collecting and accurately annotating large…

Pretrained contextual and non-contextual subword embeddings have become available in over 250 languages, allowing massively multilingual NLP. However, while there is no dearth of pretrained embeddings, the distinct lack of systematic…

Network representation learning (NRL) methods aim to map each vertex into a low dimensional space by preserving the local and global structure of a given network, and in recent years they have received a significant attention thanks to…

This paper describes a method of domain adaptive training for semantic segmentation using multiple source datasets that are not necessarily relevant to the target dataset. We propose a soft pseudo-label generation method by integrating…

Text representations using neural word embeddings have proven effective in many NLP applications. Recent researches adapt the traditional word embedding models to learn vectors of multiword expressions (concepts/entities). However, these…

We consider the supervised training setting in which we learn task-specific word embeddings. We assume that we start with initial embeddings learned from unlabelled data and update them to learn task-specific embeddings for words in the…