Related papers: A Comparison of Word-based and Context-based Repre…

NLP tasks differ in the semantic information they require, and at this time no single se- mantic representation fulfills all requirements. Logic-based representations characterize sentence structure, but do not capture the graded aspect of…

Human communication includes information, opinions, and reactions. Reactions are often captured by the affective-messages in written as well as verbal communications. While there has been work in affect modeling and to some extent affective…

A lot of work has been done to build text-based language models for performing different NLP tasks, but not much research has been done in the case of audio-based language models. This paper proposes a Convolutional Autoencoder based neural…

We focus on the problem of learning distributed representations for entity search queries, named entities, and their short descriptions. With our representation learning models, the entity search query, named entity and description can be…

The large size and complex decision mechanisms of state-of-the-art text classifiers make it difficult for humans to understand their predictions, leading to a potential lack of trust by the users. These issues have led to the adoption of…

Feature norm datasets of human conceptual knowledge, collected in surveys of human volunteers, yield highly interpretable models of word meaning and play an important role in neurolinguistic research on semantic cognition. However, these…

Contextualized word embeddings (CWE) such as provided by ELMo (Peters et al., 2018), Flair NLP (Akbik et al., 2018), or BERT (Devlin et al., 2019) are a major recent innovation in NLP. CWEs provide semantic vector representations of words…

In text classification, dictionaries can be used to define human-comprehensible features. We propose an improvement to dictionary features called smoothed dictionary features. These features recognize document contexts instead of n-grams.…

Efficient representation of text documents is an important building block in many NLP tasks. Research on long text categorization has shown that simple weighted averaging of word vectors for sentence representation often outperforms more…

In this work, we examine the extent to which embeddings may encode marginalized populations differently, and how this may lead to a perpetuation of biases and worsened performance on clinical tasks. We pretrain deep embedding models (BERT)…

Recent multi-modal contrastive learning models have demonstrated the ability to learn an embedding space suitable for building strong vision classifiers, by leveraging the rich information in large-scale image-caption datasets. Our work…

Language models (LMs) are used for a diverse range of tasks, from question answering to writing fantastical stories. In order to reliably accomplish these tasks, LMs must be able to discern the modal category of a sentence (i.e., whether it…

Building meaningful representations of noun compounds is not trivial since many of them scarcely appear in the corpus. To that end, composition functions approximate the distributional representation of a noun compound by combining its…

This study addresses the challenges of multi-label text classification. The difficulties arise from imbalanced data sets, varied text lengths, and numerous subjective feature labels. Existing solutions include traditional machine learning…

In comparison with document summarization on the articles from social media and newswire, argumentative zoning (AZ) is an important task in scientific paper analysis. Traditional methodology to carry on this task relies on feature…

Unsupervised methods for learning distributed representations of words are ubiquitous in today's NLP research, but far less is known about the best ways to learn distributed phrase or sentence representations from unlabelled data. This…

Learning efficient representations for concepts has been proven to be an important basis for many applications such as machine translation or document classification. Proper representations of medical concepts such as diagnosis, medication,…

Statistical language models conventionally implement representation learning based on the contextual distribution of words or other formal units, whereas any information related to the logographic features of written text are often ignored,…

Many of the existing TTS systems cannot accurately synthesize text containing a variety of numerical formats, resulting in reduced intelligibility of the synthesized speech. This research aims to develop a numerical format classifier that…

We propose a new model for learning bilingual word representations from non-parallel document-aligned data. Following the recent advances in word representation learning, our model learns dense real-valued word vectors, that is, bilingual…