Related papers: Task-Specific Dependency-based Word Embedding Meth…
Sentence embedding is an effective feature representation for most deep learning-based NLP tasks. One prevailing line of methods is using recursive latent tree-structured networks to embed sentences with task-specific structures. However,…
In this work, we present an effective method for semantic specialization of word vector representations. To this end, we use traditional word embeddings and apply specialization methods to better capture semantic relations between words. In…
Fully data-driven, deep learning-based models are usually designed as language-independent and have been shown to be successful for many natural language processing tasks. However, when the studied language is low-resourced and the amount…
We propose a novel generative model to explore both local and global context for joint learning topics and topic-specific word embeddings. In particular, we assume that global latent topics are shared across documents, a word is generated…
Meta-embedding (ME) learning is an emerging approach that attempts to learn more accurate word embeddings given existing (source) word embeddings as the sole input. Due to their ability to incorporate semantics from multiple source…
In this paper, we present a kernel-based learning approach for the 2018 Complex Word Identification (CWI) Shared Task. Our approach is based on combining multiple low-level features, such as character n-grams, with high-level semantic…
Pretrained contextualized embeddings are powerful word representations for structured prediction tasks. Recent work found that better word representations can be obtained by concatenating different types of embeddings. However, the…
Word2vec is one of the most used algorithms to generate word embeddings because of a good mix of efficiency, quality of the generated representations and cognitive grounding. However, word meaning is not static and depends on the context in…
Deep learning models such as convolutional neural networks and recurrent networks are widely applied in text classification. In spite of their great success, most deep learning models neglect the importance of modeling context information,…
Topic modeling analyzes documents to learn meaningful patterns of words. However, existing topic models fail to learn interpretable topics when working with large and heavy-tailed vocabularies. To this end, we develop the Embedded Topic…
Recent work suggests that interpolating between the weights of two specialized language models can transfer knowledge between tasks in a way that multi-task learning cannot. However, very few have explored interpolation between more than…
Learning sentence vectors that generalise well is a challenging task. In this paper we compare three methods of learning phrase embeddings: 1) Using LSTMs, 2) using recursive nets, 3) A variant of the method 2 using the POS information of…
In this paper, we propose a novel approach for text classification based on clustering word embeddings, inspired by the bag of visual words model, which is widely used in computer vision. After each word in a collection of documents is…
Cross-Lingual Word Embeddings (CLWEs) encode words from two or more languages in a shared high-dimensional space in which vectors representing words with similar meaning (regardless of language) are closely located. Existing methods for…
Probing has become an important tool for analyzing representations in Natural Language Processing (NLP). For graphical NLP tasks such as dependency parsing, linear probes are currently limited to extracting undirected or unlabeled parse…
Word embeddings capture semantic relationships based on contextual information and are the basis for a wide variety of natural language processing applications. Notably these relationships are solely learned from the data and subsequently…
Many deep learning architectures have been proposed to model the compositionality in text sequences, requiring a substantial number of parameters and expensive computations. However, there has not been a rigorous evaluation regarding the…
We present an unsupervised explainable word embedding technique, called EVE, which is built upon the structure of Wikipedia. The proposed model defines the dimensions of a semantic vector representing a word using human-readable labels,…
Target-oriented opinion words extraction (TOWE) (Fan et al., 2019b) is a new subtask of target-oriented sentiment analysis that aims to extract opinion words for a given aspect in text. Current state-of-the-art methods leverage position…
Text embedding representing natural language documents in a semantic vector space can be used for document retrieval using nearest neighbor lookup. In order to study the feasibility of neural models specialized for retrieval in a…