Related papers: Context Aware Document Embedding
Dense retrieval calls for discriminative embeddings to represent the semantic relationship between query and document. It may benefit from the using of large language models (LLMs), given LLMs' strong capability on semantic understanding.…
We present path2vec, a new approach for learning graph embeddings that relies on structural measures of pairwise node similarities. The model learns representations for nodes in a dense space that approximate a given user-defined graph…
Due to the availability of references of research papers and the rich information contained in papers, various citation analysis approaches have been proposed to identify similar documents for scholar recommendation. Despite of the success…
This study proposes a Neural Attentive Bag-of-Entities model, which is a neural network model that performs text classification using entities in a knowledge base. Entities provide unambiguous and relevant semantic signals that are…
Although contextualized embeddings generated from large-scale pre-trained models perform well in many tasks, traditional static embeddings (e.g., Skip-gram, Word2Vec) still play an important role in low-resource and lightweight settings due…
Sentiments of words differ from one corpus to another. Inducing general sentiment lexicons for languages and using them cannot, in general, produce meaningful results for different domains. In this paper, we combine contextual and…
While the celebrated Word2Vec technique yields semantically rich representations for individual words, there has been relatively less success in extending to generate unsupervised sentences or documents embeddings. Recent work has…
Recent work in neural machine translation has demonstrated both the necessity and feasibility of using inter-sentential context -- context from sentences other than those currently being translated. However, while many current methods…
Motivations like domain adaptation, transfer learning, and feature learning have fueled interest in inducing embeddings for rare or unseen words, n-grams, synsets, and other textual features. This paper introduces a la carte embedding, a…
Using deep learning for different machine learning tasks such as image classification and word embedding has recently gained many attentions. Its appealing performance reported across specific Natural Language Processing (NLP) tasks in…
Recent studies on knowledge graph embedding focus on mapping entities and relations into low-dimensional vector spaces. While most existing models primarily exploit structural information, knowledge graphs also contain rich contextual and…
Recently, many researches employ middle-layer output of convolutional neural network models (CNN) as features for different visual recognition tasks. Although promising results have been achieved in some empirical studies, such type of…
The goal of sentence and document modeling is to accurately represent the meaning of sentences and documents for various Natural Language Processing tasks. In this work, we present Dependency Sensitive Convolutional Neural Networks (DSCNN)…
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…
With the recent advancements in information technology there has been a huge surge in amount of data available. But information retrieval technology has not been able to keep up with this pace of information generation resulting in over…
This paper proposes a way to improve the performance of existing algorithms for text classification in domains with strong language semantics. We propose a domain adaptation layer learns weights to combine a generic and a domain specific…
Document-level machine translation manages to outperform sentence level models by a small margin, but have failed to be widely adopted. We argue that previous research did not make a clear use of the global context, and propose a new…
Recent advances in deep learning have achieved impressive gains in classification accuracy on a variety of types of data, including images and text. Despite these gains, however, concerns have been raised about the calibration, robustness,…
Learning to rank has been intensively studied and widely applied in information retrieval. Typically, a global ranking function is learned from a set of labeled data, which can achieve good performance on average but may be suboptimal for…
End-to-end acoustic-to-word speech recognition models have recently gained popularity because they are easy to train, scale well to large amounts of training data, and do not require a lexicon. In addition, word models may also be easier to…