Neural Chat Translation (NCT) aims to translate conversational text between speakers of different languages. Despite the promising performance of sentence-level and context-aware neural machine translation models, there still remain limitations in cu
rrent NCT models because the inherent dialogue characteristics of chat, such as dialogue coherence and speaker personality, are neglected. In this paper, we propose to promote the chat translation by introducing the modeling of dialogue characteristics into the NCT model. To this end, we design four auxiliary tasks including monolingual response generation, cross-lingual response generation, next utterance discrimination, and speaker identification. Together with the main chat translation task, we optimize the NCT model through the training objectives of all these tasks. By this means, the NCT model can be enhanced by capturing the inherent dialogue characteristics, thus generating more coherent and speaker-relevant translations. Comprehensive experiments on four language directions (English-German and English-Chinese) verify the effectiveness and superiority of the proposed approach.
Neural chat translation aims to translate bilingual conversational text, which has a broad application in international exchanges and cooperation. Despite the impressive performance of sentence-level and context-aware Neural Machine Translation (NMT)
, there still remain challenges to translate bilingual conversational text due to its inherent characteristics such as role preference, dialogue coherence, and translation consistency. In this paper, we aim to promote the translation quality of conversational text by modeling the above properties. Specifically, we design three latent variational modules to learn the distributions of bilingual conversational characteristics. Through sampling from these learned distributions, the latent variables, tailored for role preference, dialogue coherence, and translation consistency, are incorporated into the NMT model for better translation. We evaluate our approach on the benchmark dataset BConTrasT (English-German) and a self-collected bilingual dialogue corpus, named BMELD (English-Chinese). Extensive experiments show that our approach notably boosts the performance over strong baselines by a large margin and significantly surpasses some state-of-the-art context-aware NMT models in terms of BLEU and TER. Additionally, we make the BMELD dataset publicly available for the research community.
The Galactic halo is supposed to form from merging with nearby dwarf galaxies. In order to probe different components of the Galactic halo, we have applied the Gaussian Mixture Models method to a selected sample of metal poor stars with [Fe/H] $< -0.
7$ dex in the APOGEE DR16 catalogue based on four-parameters, metallicity, [Mg/Fe] ratio and spatial velocity (textit{$V_R$, $V_phi$}). Nine groups are identified with four from the halo (group 1, 3, 4 and 5), one from the thick disk (group 6), one from the thin disk (group 8) and one from dwarf galaxies (group 7) by analyzing their distributions in the ([M/H], [Mg/Fe]), ($V_R$, $V_phi$), (textit{Zmax}, textit{eccentricity}), (textit{Energy}, textit{Lz}) and ([Mg/Mn], [Al/Fe]) coordinates. The rest two groups are respectively caused by observational effect (group 9) and the cross section component (group 2) between the thin disk and the thick disk. It is found that in the extremely outer accreted halo (group 1), stars born in the Milky Way can not be distinguished from those accreted from other galaxies either chemically or kinematically. In the intermediate metallicity of $-$1.6 $<$ [Fe/H] $< -0.7$ dex, the accreted halo mainly composed of the Gaia-Enceladus-Sausage substructure (group 5), which can be easily distinguished from group 4 (the in-situ halo group) in both chemical and kinematic space. Some stars of group 4 may come from the disk and some disk stars can be scattered to high orbits by resonant effects as shown in the textit{Zmax} versus Energy coordinate. We also displayed the spatial distribution of main components of the halo and the ratio of accreted components do not show clear relation to Galactic radius.
We propose a mechanism to generate a static magnetization via {em axial magnetoelectric effect} (AMEE). Magnetization ${bf M} sim {bf E}_5(omega)times {bf E}_5^{*}(omega)$ appears as a result of the transfer of the angular momentum of the axial elect
ric field ${bf E}_5(t)$ into the magnetic moment in Dirac and Weyl semimetals. We point out similarities and differences between the proposed AMEE and a conventional inverse Faraday effect (IFE). As an example, we estimated the AMEE generated by circularly polarized acoustic waves and find it to be on the scale of microgauss for gigahertz frequency sound. In contrast to a conventional IFE, magnetization rises linearly at small frequencies and fixed sound intensity as well as demonstrates a nonmonotonic peak behavior for the AMEE. The effect provides a way to investigate unusual axial electromagnetic fields via conventional magnetometry techniques.
The success of emotional conversation systems depends on sufficient perception and appropriate expression of emotions. In a real-world conversation, we firstly instinctively perceive emotions from multi-source information, including the emotion flow
of dialogue history, facial expressions, and personalities of speakers, and then express suitable emotions according to our personalities, but these multiple types of information are insufficiently exploited in emotional conversation fields. To address this issue, we propose a heterogeneous graph-based model for emotional conversation generation. Specifically, we design a Heterogeneous Graph-Based Encoder to represent the conversation content (i.e., the dialogue history, its emotion flow, facial expressions, and speakers personalities) with a heterogeneous graph neural network, and then predict suitable emotions for feedback. After that, we employ an Emotion-Personality-Aware Decoder to generate a response not only relevant to the conversation context but also with appropriate emotions, by taking the encoded graph representations, the predicted emotions from the encoder and the personality of the current speaker as inputs. Experimental results show that our model can effectively perceive emotions from multi-source knowledge and generate a satisfactory response, which significantly outperforms previous state-of-the-art models.
For multiple aspects scenario of aspect-based sentiment analysis (ABSA), existing approaches typically ignore inter-aspect relations or rely on temporal dependencies to process aspect-aware representations of all aspects in a sentence. Although multi
ple aspects of a sentence appear in a non-adjacent sequential order, they are not in a strict temporal relationship as natural language sequence, thus the aspect-aware sentence representations should not be treated as temporal dependency processing. In this paper, we propose a novel non-temporal mechanism to enhance the ABSA task through modeling inter-aspect dependencies. Furthermore, we focus on the well-known class imbalance issue on the ABSA task and address it by down-weighting the loss assigned to well-classified instances. Experiments on two distinct domains of SemEval 2014 task 4 demonstrate the effectiveness of our proposed approach.
The aspect-based sentiment analysis (ABSA) task remains to be a long-standing challenge, which aims to extract the aspect term and then identify its sentiment orientation.In previous approaches, the explicit syntactic structure of a sentence, which r
eflects the syntax properties of natural language and hence is intuitively crucial for aspect term extraction and sentiment recognition, is typically neglected or insufficiently modeled. In this paper, we thus propose a novel dependency syntactic knowledge augmented interactive architecture with multi-task learning for end-to-end ABSA. This model is capable of fully exploiting the syntactic knowledge (dependency relations and types) by leveraging a well-designed Dependency Relation Embedded Graph Convolutional Network (DreGcn). Additionally, we design a simple yet effective message-passing mechanism to ensure that our model learns from multiple related tasks in a multi-task learning framework. Extensive experimental results on three benchmark datasets demonstrate the effectiveness of our approach, which significantly outperforms existing state-of-the-art methods. Besides, we achieve further improvements by using BERT as an additional feature extractor.
Aspect-based sentiment analysis (ABSA) mainly involves three subtasks: aspect term extraction, opinion term extraction, and aspect-level sentiment classification, which are typically handled in a separate or joint manner. However, previous approaches
do not well exploit the interactive relations among three subtasks and do not pertinently leverage the easily available document-level labeled domain/sentiment knowledge, which restricts their performances. To address these issues, we propose a novel Iterative Multi-Knowledge Transfer Network (IMKTN) for end-to-end ABSA. For one thing, through the interactive correlations between the ABSA subtasks, our IMKTN transfers the task-specific knowledge from any two of the three subtasks to another one at the token level by utilizing a well-designed routing algorithm, that is, any two of the three subtasks will help the third one. For another, our IMKTN pertinently transfers the document-level knowledge, i.e., domain-specific and sentiment-related knowledge, to the aspect-level subtasks to further enhance the corresponding performance. Experimental results on three benchmark datasets demonstrate the effectiveness and superiority of our approach.
We present a new moving group clustered in kinematics, spatial position and elemental abundances. Its spatial position is around the center of the Local Arm of the Milky Way. A convergent point method was taken to select candidate member stars.textbf
{ Among 206 candidate member stars, 74 are pre-main-sequence stars and some of them have stellar disks.} We presume those pre-main sequence stars belong to Orion nebula. We suggest this moving group is caused by density wave of the Local Arm passing by.
ReLU (rectified linear units) neural network has received significant attention since its emergence. In this paper, a univariate ReLU (UReLU) neural network is proposed to both modelling the nonlinear dynamic system and revealing insights about the s
ystem. Specifically, the neural network consists of neurons with linear and UReLU activation functions, and the UReLU functions are defined as the ReLU functions respect to each dimension. The UReLU neural network is a single hidden layer neural network, and the structure is relatively simple. The initialization of the neural network employs the decoupling method, which provides a good initialization and some insight into the nonlinear system. Compared with normal ReLU neural network, the number of parameters of UReLU network is less, but it still provide a good approximation of the nonlinear dynamic system. The performance of the UReLU neural network is shown through a Hysteretic benchmark system: the Bouc-Wen system. Simulation results verify the effectiveness of the proposed method.
