arXiv subjects

Hongshen Chen

Publications and source records attributed to Hongshen Chen.

25 records · Page 2Linked to original sources

arXiv2020

Learning from Easy to Complex: Adaptive Multi-curricula Learning for Neural Dialogue Generation

Current state-of-the-art neural dialogue systems are mainly data-driven and are trained on human-generated responses. However, due to the subjectivity and open-ended nature of human conversations, the complexity of training dialogues varies greatly. The noise and uneven complexity of query-response pairs impede the learning efficiency and effects of the neural dialogue generation models. What is more, so far, there are no unified dialogue complexity measurements, and the dialogue complexity embodies multiple aspects of attributes---specificity, repetitiveness, relevance, etc. Inspired by human behaviors of learning to converse, where children learn from easy dialogues to complex ones and dynamically adjust their learning progress, in this paper, we first analyze five dialogue attributes to measure the dialogue complexity in multiple perspectives on three publicly available corpora. Then, we propose an adaptive multi-curricula learning framework to schedule a committee of the organized curricula. The framework is established upon the reinforcement learning paradigm, which automatically chooses different curricula at the evolving learning process according to the learning status of the neural dialogue generation model. Extensive experiments conducted on five state-of-the-art models demonstrate its learning efficiency and effectiveness with respect to 13 automatic evaluation metrics and human judgments.

cs.CL↗

arXiv2020

Posterior-GAN: Towards Informative and Coherent Response Generation with Posterior Generative Adversarial Network

Neural conversational models learn to generate responses by taking into account the dialog history. These models are typically optimized over the query-response pairs with a maximum likelihood estimation objective. However, the query-response tuples are naturally loosely coupled, and there exist multiple responses that can respond to a given query, which leads the conversational model learning burdensome. Besides, the general dull response problem is even worsened when the model is confronted with meaningless response training instances. Intuitively, a high-quality response not only responds to the given query but also links up to the future conversations, in this paper, we leverage the query-response-future turn triples to induce the generated responses that consider both the given context and the future conversations. To facilitate the modeling of these triples, we further propose a novel encoder-decoder based generative adversarial learning framework, Posterior Generative Adversarial Network (Posterior-GAN), which consists of a forward and a backward generative discriminator to cooperatively encourage the generated response to be informative and coherent by two complementary assessment perspectives. Experimental results demonstrate that our method effectively boosts the informativeness and coherence of the generated response on both automatic and human evaluation, which verifies the advantages of considering two assessment perspectives.

cs.CL↗

arXiv2020

Adaptive Parameterization for Neural Dialogue Generation

Neural conversation systems generate responses based on the sequence-to-sequence (SEQ2SEQ) paradigm. Typically, the model is equipped with a single set of learned parameters to generate responses for given input contexts. When confronting diverse conversations, its adaptability is rather limited and the model is hence prone to generate generic responses. In this work, we propose an {\bf Ada}ptive {\bf N}eural {\bf D}ialogue generation model, \textsc{AdaND}, which manages various conversations with conversation-specific parameterization. For each conversation, the model generates parameters of the encoder-decoder by referring to the input context. In particular, we propose two adaptive parameterization mechanisms: a context-aware and a topic-aware parameterization mechanism. The context-aware parameterization directly generates the parameters by capturing local semantics of the given context. The topic-aware parameterization enables parameter sharing among conversations with similar topics by first inferring the latent topics of the given context and then generating the parameters with respect to the distributional topics. Extensive experiments conducted on a large-scale real-world conversational dataset show that our model achieves superior performance in terms of both quantitative metrics and human evaluations.

cs.CL↗

arXiv2018

Explicit State Tracking with Semi-Supervision for Neural Dialogue Generation

The task of dialogue generation aims to automatically provide responses given previous utterances. Tracking dialogue states is an important ingredient in dialogue generation for estimating users' intention. However, the \emph{expensive nature of state labeling} and the \emph{weak interpretability} make the dialogue state tracking a challenging problem for both task-oriented and non-task-oriented dialogue generation: For generating responses in task-oriented dialogues, state tracking is usually learned from manually annotated corpora, where the human annotation is expensive for training; for generating responses in non-task-oriented dialogues, most of existing work neglects the explicit state tracking due to the unlimited number of dialogue states. In this paper, we propose the \emph{semi-supervised explicit dialogue state tracker} (SEDST) for neural dialogue generation. To this end, our approach has two core ingredients: \emph{CopyFlowNet} and \emph{posterior regularization}. Specifically, we propose an encoder-decoder architecture, named \emph{CopyFlowNet}, to represent an explicit dialogue state with a probabilistic distribution over the vocabulary space. To optimize the training procedure, we apply a posterior regularization strategy to integrate indirect supervision. Extensive experiments conducted on both task-oriented and non-task-oriented dialogue corpora demonstrate the effectiveness of our proposed model. Moreover, we find that our proposed semi-supervised dialogue state tracker achieves a comparable performance as state-of-the-art supervised learning baselines in state tracking procedure.

cs.CL↗

arXiv2018

A Survey on Dialogue Systems: Recent Advances and New Frontiers

Dialogue systems have attracted more and more attention. Recent advances on dialogue systems are overwhelmingly contributed by deep learning techniques, which have been employed to enhance a wide range of big data applications such as computer vision, natural language processing, and recommender systems. For dialogue systems, deep learning can leverage a massive amount of data to learn meaningful feature representations and response generation strategies, while requiring a minimum amount of hand-crafting. In this article, we give an overview to these recent advances on dialogue systems from various perspectives and discuss some possible research directions. In particular, we generally divide existing dialogue systems into task-oriented and non-task-oriented models, then detail how deep learning techniques help them with representative algorithms and finally discuss some appealing research directions that can bring the dialogue system research into a new frontier.

cs.CL↗

arXiv2015

High performance solar cells based on graphene-GaAs heterostructures

The honeycomb connection of carbon atoms by covalent bonds in a macroscopic two-dimensional scale leads to fascinating graphene and solar cell based on graphene/silicon Schottky diode has been widely studied. For solar cell applications, GaAs is superior to silicon as it has a direct band gap of 1.42 eV and its electron mobility is six times of that of silicon. However, graphene/GaAs solar cell has been rarely explored. Herein, we report graphene/GaAs solar cells with conversion efficiency (Eta) of 10.4% and 15.5% without and with anti-reflection layer on graphene, respectively. The Eta of 15.5% is higher than the state of art efficiency for graphene/Si system (14.5%). Furthermore, our calculation points out Eta of 25.8% can be reached by reasonably optimizing the open circuit voltage, junction ideality factor, resistance of graphene and metal/graphene contact. This research strongly support graphene/GaAs hetero-structure solar cell have great potential for practical applications.

cond-mat.mes-hall↗

arXiv2011

Electronic Transport in Monolayer Graphene with Extreme Physical Deformation: ab Initio Density Functional Calculation

Electronic transport properties of monolayer graphene with extreme physical bending up to 90o angle are studied using ab Initio first-principle calculations. The importance of key structural parameters including step height, curvature radius and bending angle are discussed how they modify the transport properties of the deformed graphene sheet comparing to the corresponding flat ones. The local density of state reveals that energy state modification caused by the physical bending is highly localized. It is observed that the transport properties of bent graphene with a wide range of geometrical configurations are insensitive to the structural deformation in the low-energy transmission spectra, even in the extreme case of bending. The results support that graphene, with its superb electromechanical robustness, could serve as a viable material platform in a spectrum of applications such as photovoltaics, flexible electronics, OLED, and 3D electronic chips.

quant-ph↗