Related papers: Cross-Lingual Task-Specific Representation Learnin…
This work focuses on the rapid development of linguistic annotation tools for resource-poor languages. We experiment several cross-lingual annotation projection methods using Recurrent Neural Networks (RNN) models. The distinctive feature…
In this work, we apply word embeddings and neural networks with Long Short-Term Memory (LSTM) to text classification problems, where the classification criteria are decided by the context of the application. We examine two applications in…
Bilingual word embeddings have been widely used to capture the similarity of lexical semantics in different human languages. However, many applications, such as cross-lingual semantic search and question answering, can be largely benefited…
Scaling multilingual representation learning beyond the hundred most frequent languages is challenging, in particular to cover the long tail of low-resource languages. A promising approach has been to train one-for-all multilingual models…
In this paper, we propose to boost low-resource cross-lingual document retrieval performance with deep bilingual query-document representations. We match queries and documents in both source and target languages with four components, each…
We propose an LSTM-based model with hierarchical architecture on named entity recognition from code-switching Twitter data. Our model uses bilingual character representation and transfer learning to address out-of-vocabulary words. In order…
Class-based language models (LMs) have been long devised to address context sparsity in $n$-gram LMs. In this study, we revisit this approach in the context of neural LMs. We hypothesize that class-based prediction leads to an implicit…
Named entity recognition (NER) models are typically based on the architecture of Bi-directional LSTM (BiLSTM). The constraints of sequential nature and the modeling of single input prevent the full utilization of global information from…
This work presents an end-to-end trainable deep bidirectional LSTM (Long-Short Term Memory) model for image captioning. Our model builds on a deep convolutional neural network (CNN) and two separate LSTM networks. It is capable of learning…
Sentence-level classification and sequential labeling are two fundamental tasks in language understanding. While these two tasks are usually modeled separately, in reality, they are often correlated, for example in intent classification and…
In recent years, text classification methods based on neural networks and pre-trained models have gained increasing attention and demonstrated excellent performance. However, these methods still have some limitations in practical…
Target-dependent sentiment classification remains a challenge: modeling the semantic relatedness of a target with its context words in a sentence. Different context words have different influences on determining the sentiment polarity of a…
We propose a novel language-independent approach for improving machine translation for resource-poor languages by exploiting their similarity to resource-rich ones. More precisely, we improve the translation from a resource-poor source…
We propose a new approach for learning contextualised cross-lingual word embeddings based on a small parallel corpus (e.g. a few hundred sentence pairs). Our method obtains word embeddings via an LSTM encoder-decoder model that…
The recent surge of complex attention-based deep learning architectures has led to extraordinary results in various downstream NLP tasks in the English language. However, such research for resource-constrained and morphologically rich…
Long Short-Term Memory (LSTM) networks, a type of recurrent neural network with a more complex computational unit, have been successfully applied to a variety of sequence modeling tasks. In this paper we develop Tree Long Short-Term Memory…
Recent work on speech representation models jointly pre-trained with text has demonstrated the potential of improving speech representations by encoding speech and text in a shared space. In this paper, we leverage such shared…
To effectively perform the task of next-word prediction, long short-term memory networks (LSTMs) must keep track of many types of information. Some information is directly related to the next word's identity, but some is more secondary…
Due to recent technical and scientific advances, we have a wealth of information hidden in unstructured text data such as offline/online narratives, research articles, and clinical reports. To mine these data properly, attributable to their…
Language models are generally employed to estimate the probability distribution of various linguistic units, making them one of the fundamental parts of natural language processing. Applications of language models include a wide spectrum of…