Heterogeneous Graph Neural Networks (HeterGNN) have been recently introduced as an emergent approach for extracting document summarization (EDS) by exploiting the cross-relations between words and sentences. However, applying HeterGNN for long documents is still an open research issue. One of the main majors is the lacking of inter-sentence connections. In this regard, this paper exploits how to apply HeterGNN for long documents by building a graph on sentence-level nodes (homogeneous graph) and combine with HeterGNN for capturing the semantic information in terms of both inter and intra-sentence connections. Experiments on two benchmark datasets of long documents such as PubMed and ArXiv show that our method is able to achieve state-of-the-art results in this research field.

Large-scale pre-trained representations such as BERT have been widely used in many natural language understanding tasks. The methods of incorporating BERT into document-level machine translation are still being explored. BERT is able to understand sentence relationships since BERT is pre-trained using the next sentence prediction task. In our work, we leverage this property to improve document-level machine translation. In our proposed model, BERT performs as a context encoder to achieve document-level contextual information, which is then integrated into both the encoder and decoder. Experiment results show that our proposed method can significantly outperform strong document-level machine translation baselines on BLEU score. Moreover, the ablation study shows our method can capture document-level context information to boost translation performance.

Text representation plays a vital role in retrieval-based question answering, especially in the legal domain where documents are usually long and complicated. The better the question and the legal documents are represented, the more accurate they are matched. In this paper, we focus on the task of answering legal questions at the article level. Given a legal question, the goal is to retrieve all the correct and valid legal articles, that can be used as the basic to answer the question. We present a retrieval-based model for the task by learning neural attentive text representation. Our text representation method first leverages convolutional neural networks to extract important information in a question and legal articles. Attention mechanisms are then used to represent the question and articles and select appropriate information to align them in a matching process. Experimental results on an annotated corpus consisting of 5,922 Vietnamese legal questions show that our model outperforms state-of-the-art retrieval-based methods for question answering by large margins in terms of both recall and NDCG.

Prior works have demonstrated that a low-resource language pair can benefit from multilingual machine translation (MT) systems, which rely on many language pairs’ joint training. This paper proposes two simple strategies to address the rare word issue in multilingual MT systems for two low-resource language pairs: French-Vietnamese and English-Vietnamese. The first strategy is about dynamical learning word similarity of tokens in the shared space among source languages while another one attempts to augment the translation ability of rare words through updating their embeddings during the training. Besides, we leverage monolingual data for multilingual MT systems to increase the amount of synthetic parallel corpora while dealing with the data sparsity problem. We have shown significant improvements of up to +1.62 and +2.54 BLEU points over the bilingual baseline systems for both language pairs and released our datasets for the research community.

While translating between East Asian languages, many works have discovered clear advantages of using characters as the translation unit. Unfortunately, traditional recurrent neural machine translation systems hinder the practical usage of those character-based systems due to their architectural limitations. They are unfavorable in handling extremely long sequences as well as highly restricted in parallelizing the computations. In this paper, we demonstrate that the new transformer architecture can perform character-based trans- lation better than the recurrent one. We conduct experiments on a low-resource language pair: Japanese-Vietnamese. Our models considerably outperform the state-of-the-art systems which employ word-based recurrent architectures.

Among the six challenges of neural machine translation (NMT) coined by (Koehn and Knowles, 2017), rare-word problem is considered the most severe one, especially in translation of low-resource languages. In this paper, we propose three solutions to address the rare words in neural machine translation systems. First, we enhance source context to predict the target words by connecting directly the source embeddings to the output of the attention component in NMT. Second, we propose an algorithm to learn morphology of unknown words for English in supervised way in order to minimize the adverse effect of rare-word problem. Finally, we exploit synonymous relation from the WordNet to overcome out-of-vocabulary (OOV) problem of NMT. We evaluate our approaches on two low-resource language pairs: English-Vietnamese and Japanese-Vietnamese. In our experiments, we have achieved significant improvements of up to roughly +1.0 BLEU points in both language pairs.

Domain Adaptation arises when we aim at learning from source domain a model that can perform acceptably well on a different target domain. It is especially crucial for Natural Language Generation (NLG) in Spoken Dialogue Systems when there are sufficient annotated data in the source domain, but there is a limited labeled data in the target domain. How to effectively utilize as much of existing abilities from source domains is a crucial issue in domain adaptation. In this paper, we propose an adversarial training procedure to train a Variational encoder-decoder based language generator via multiple adaptation steps. In this procedure, a model is first trained on a source domain data and then fine-tuned on a small set of target domain utterances under the guidance of two proposed critics. Experimental results show that the proposed method can effectively leverage the existing knowledge in the source domain to adapt to another related domain by using only a small amount of in-domain data.

Recent deep learning models have shown improving results to natural language generation (NLG) irrespective of providing sufficient annotated data. However, a modest training data may harm such models’ performance. Thus, how to build a generator that can utilize as much of knowledge from a low-resource setting data is a crucial issue in NLG. This paper presents a variational neural-based generation model to tackle the NLG problem of having limited labeled dataset, in which we integrate a variational inference into an encoder-decoder generator and introduce a novel auxiliary auto-encoding with an effective training procedure. Experiments showed that the proposed methods not only outperform the previous models when having sufficient training dataset but also demonstrate strong ability to work acceptably well when the training data is scarce.

Natural language generation (NLG) is an important component in spoken dialogue systems. This paper presents a model called Encoder-Aggregator-Decoder which is an extension of an Recurrent Neural Network based Encoder-Decoder architecture. The proposed Semantic Aggregator consists of two components: an Aligner and a Refiner. The Aligner is a conventional attention calculated over the encoded input information, while the Refiner is another attention or gating mechanism stacked over the attentive Aligner in order to further select and aggregate the semantic elements. The proposed model can be jointly trained both sentence planning and surface realization to produce natural language utterances. The model was extensively assessed on four different NLG domains, in which the experimental results showed that the proposed generator consistently outperforms the previous methods on all the NLG domains.

Natural language generation (NLG) is a critical component in a spoken dialogue system. This paper presents a Recurrent Neural Network based Encoder-Decoder architecture, in which an LSTM-based decoder is introduced to select, aggregate semantic elements produced by an attention mechanism over the input elements, and to produce the required utterances. The proposed generator can be jointly trained both sentence planning and surface realization to produce natural language sentences. The proposed model was extensively evaluated on four different NLG datasets. The experimental results showed that the proposed generators not only consistently outperform the previous methods across all the NLG domains but also show an ability to generalize from a new, unseen domain and learn from multi-domain datasets.

The use of distributional language representations have opened new paths in solving a variety of NLP problems. However, alternative approaches can take advantage of information unavailable through pure statistical means. This paper presents a method for building vector representations from meaning unit blocks called concept definitions, which are obtained by extracting information from a curated linguistic resource (Wiktionary). The representations obtained in this way can be compared through conventional cosine similarity and are also interpretable by humans. Evaluation was conducted in semantic similarity and relatedness test sets, with results indicating a performance comparable to other methods based on single linguistic resource extraction. The results also indicate noticeable performance gains when combining distributional similarity scores with the ones obtained using this approach. Additionally, a discussion on the proposed method’s shortcomings is provided in the analysis of error cases.

Tweet-level sentiment classification in Twitter social networking has many challenges: exploiting syntax, semantic, sentiment, and context in tweets. To address these problems, we propose a novel approach to sentiment analysis that uses lexicon features for building lexicon embeddings (LexW2Vs) and generates character attention vectors (CharAVs) by using a Deep Convolutional Neural Network (DeepCNN). Our approach integrates LexW2Vs and CharAVs with continuous word embeddings (ContinuousW2Vs) and dependency-based word embeddings (DependencyW2Vs) simultaneously in order to increase information for each word into a Bidirectional Contextual Gated Recurrent Neural Network (Bi-CGRNN). We evaluate our model on two Twitter sentiment classification datasets. Experimental results show that our model can improve the classification accuracy of sentence-level sentiment analysis in Twitter social networking.

Deep learning models have recently been applied successfully in natural language processing, especially sentiment analysis. Each deep learning model has a particular advantage, but it is difficult to combine these advantages into one model, especially in the area of sentiment analysis. In our approach, Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM) were utilized to learn sentiment-specific features in a freezing scheme. This scenario provides a novel and efficient way for integrating advantages of deep learning models. In addition, we also grouped documents into clusters by their similarity and applied the prediction score of Naive Bayes SVM (NBSVM) method to boost the classification accuracy of each group. The experiments show that our method achieves the state-of-the-art performance on two well-known datasets: IMDB large movie reviews for document level and Pang & Lee movie reviews for sentence level.

This paper presents VSoLSCSum, a Vietnamese linked sentence-comment dataset, which was manually created to treat the lack of standard corpora for social context summarization in Vietnamese. The dataset was collected through the keywords of 141 Web documents in 12 special events, which were mentioned on Vietnamese Web pages. Social users were asked to involve in creating standard summaries and the label of each sentence or comment. The inter-agreement calculated by Cohen’s Kappa among raters after validating is 0.685. To illustrate the potential use of our dataset, a learning to rank method was trained by using a set of local and social features. Experimental results indicate that the summary model trained on our dataset outperforms state-of-the-art baselines in both ROUGE-1 and ROUGE-2 in social context summarization.