arXiv subjects

Quan Liu

Publications and source records attributed to Quan Liu.

At least 127 records · Page 7Linked to original sources

arXiv2020

GAN based Unsupervised Segmentation: Should We Match the Exact Number of Objects

The unsupervised segmentation is an increasingly popular topic in biomedical image analysis. The basic idea is to approach the supervised segmentation task as an unsupervised synthesis problem, where the intensity images can be transferred to the annotation domain using cycle-consistent adversarial learning. The previous studies have shown that the macro-level (global distribution level) matching on the number of the objects (e.g., cells, tissues, protrusions etc.) between two domains resulted in better segmentation performance. However, no prior studies have exploited whether the unsupervised segmentation performance would be further improved when matching the exact number of objects at micro-level (mini-batch level). In this paper, we propose a deep learning based unsupervised segmentation method for segmenting highly overlapped and dynamic sub-cellular microvilli. With this challenging task, both micro-level and macro-level matching strategies were evaluated. To match the number of objects at the micro-level, the novel fluorescence-based micro-level matching approach was presented. From the experimental results, the micro-level matching did not improve the segmentation performance, compared with the simpler macro-level matching.

cs.CV↗

arXiv2020

Filtering before Iteratively Referring for Knowledge-Grounded Response Selection in Retrieval-Based Chatbots

The challenges of building knowledge-grounded retrieval-based chatbots lie in how to ground a conversation on its background knowledge and how to match response candidates with both context and knowledge simultaneously. This paper proposes a method named Filtering before Iteratively REferring (FIRE) for this task. In this method, a context filter and a knowledge filter are first built, which derive knowledge-aware context representations and context-aware knowledge representations respectively by global and bidirectional attention. Besides, the entries irrelevant to the conversation are discarded by the knowledge filter. After that, iteratively referring is performed between context and response representations as well as between knowledge and response representations, in order to collect deep matching features for scoring response candidates. Experimental results show that FIRE outperforms previous methods by margins larger than 2.8% and 4.1% on the PERSONA-CHAT dataset with original and revised personas respectively, and margins larger than 3.1% on the CMU_DoG dataset in terms of top-1 accuracy. We also show that FIRE is more interpretable by visualizing the knowledge grounding process.

cs.CL↗

arXiv2020

Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based Chatbots

In this paper, we study the problem of employing pre-trained language models for multi-turn response selection in retrieval-based chatbots. A new model, named Speaker-Aware BERT (SA-BERT), is proposed in order to make the model aware of the speaker change information, which is an important and intrinsic property of multi-turn dialogues. Furthermore, a speaker-aware disentanglement strategy is proposed to tackle the entangled dialogues. This strategy selects a small number of most important utterances as the filtered context according to the speakers' information in them. Finally, domain adaptation is performed to incorporate the in-domain knowledge into pre-trained language models. Experiments on five public datasets show that our proposed model outperforms the present models on all metrics by large margins and achieves new state-of-the-art performances for multi-turn response selection.

cs.CL↗

arXiv2020

Periodic Fluorescence Variations of CdSe Quantum Dots Coupled to Aryleneethynylenes with Aggregation Induced Emission

CdSe nanocrystals and aggregates of an aryleneethynylene derivative are assembled into a hybrid thin film with dual fluorescence from both fluorophores. Under continuous excitation, the nanocrystals and the molecules exhibit anti-correlated fluorescence intensity variations, which become periodic at low temperature. We attribute this to a structure-dependent aggregation induced emission of the aryleneethynylene derivative, which impacts the rate of excitation energy transfer between the molecules and nanocrystals. Energy transfer also affects the electric transport properties of the hybrid material under optical excitation. This work highlights that combining semiconductor nanocrystals with molecular aggregates, which exhibit aggregation induced emission, can result in unprecedented emerging optical properties.

physics.app-ph↗

arXiv2020

Pre-Trained and Attention-Based Neural Networks for Building Noetic Task-Oriented Dialogue Systems

The NOESIS II challenge, as the Track 2 of the 8th Dialogue System Technology Challenges (DSTC 8), is the extension of DSTC 7. This track incorporates new elements that are vital for the creation of a deployed task-oriented dialogue system. This paper describes our systems that are evaluated on all subtasks under this challenge. We study the problem of employing pre-trained attention-based network for multi-turn dialogue systems. Meanwhile, several adaptation methods are proposed to adapt the pre-trained language models for multi-turn dialogue systems, in order to keep the intrinsic property of dialogue systems. In the released evaluation results of Track 2 of DSTC 8, our proposed models ranked fourth in subtask 1, third in subtask 2, and first in subtask 3 and subtask 4 respectively.

cs.CL↗

arXiv2020

Dually Interactive Matching Network for Personalized Response Selection in Retrieval-Based Chatbots

This paper proposes a dually interactive matching network (DIM) for presenting the personalities of dialogue agents in retrieval-based chatbots. This model develops from the interactive matching network (IMN) which models the matching degree between a context composed of multiple utterances and a response candidate. Compared with previous persona fusion approaches which enhance the representation of a context by calculating its similarity with a given persona, the DIM model adopts a dual matching architecture, which performs interactive matching between responses and contexts and between responses and personas respectively for ranking response candidates. Experimental results on PERSONA-CHAT dataset show that the DIM model outperforms its baseline model, i.e., IMN with persona fusion, by a margin of 14.5% and outperforms the current state-of-the-art model by a margin of 27.7% in terms of top-1 accuracy hits@1.

cs.CL↗

arXiv2020

Fine-Tuning BERT for Schema-Guided Zero-Shot Dialogue State Tracking

We present our work on Track 4 in the Dialogue System Technology Challenges 8 (DSTC8). The DSTC8-Track 4 aims to perform dialogue state tracking (DST) under the zero-shot settings, in which the model needs to generalize on unseen service APIs given a schema definition of these target APIs. Serving as the core for many virtual assistants such as Siri, Alexa, and Google Assistant, the DST keeps track of the user's goal and what happened in the dialogue history, mainly including intent prediction, slot filling, and user state tracking, which tests models' ability of natural language understanding. Recently, the pretrained language models have achieved state-of-the-art results and shown impressive generalization ability on various NLP tasks, which provide a promising way to perform zero-shot learning for language understanding. Based on this, we propose a schema-guided paradigm for zero-shot dialogue state tracking (SGP-DST) by fine-tuning BERT, one of the most popular pretrained language models. The SGP-DST system contains four modules for intent prediction, slot prediction, slot transfer prediction, and user state summarizing respectively. According to the official evaluation results, our SGP-DST (team12) ranked 3rd on the joint goal accuracy (primary evaluation metric for ranking submissions) and 1st on the requsted slots F1 among 25 participant teams.

cs.CL↗

arXiv2019

Utterance-to-Utterance Interactive Matching Network for Multi-Turn Response Selection in Retrieval-Based Chatbots

This paper proposes an utterance-to-utterance interactive matching network (U2U-IMN) for multi-turn response selection in retrieval-based chatbots. Different from previous methods following context-to-response matching or utterance-to-response matching frameworks, this model treats both contexts and responses as sequences of utterances when calculating the matching degrees between them. For a context-response pair, the U2U-IMN model first encodes each utterance separately using recurrent and self-attention layers. Then, a global and bidirectional interaction between the context and the response is conducted using the attention mechanism to collect the matching information between them. The distances between context and response utterances are employed as a prior component when calculating the attention weights. Finally, sentence-level aggregation and context-response-level aggregation are executed in turn to obtain the feature vector for matching degree prediction. Experiments on four public datasets showed that our proposed method outperformed baseline methods on all metrics, achieving a new state-of-the-art performance and demonstrating compatibility across domains for multi-turn response selection.

cs.CL↗

arXiv2019

Interactive Matching Network for Multi-Turn Response Selection in Retrieval-Based Chatbots

In this paper, we propose an interactive matching network (IMN) for the multi-turn response selection task. First, IMN constructs word representations from three aspects to address the challenge of out-of-vocabulary (OOV) words. Second, an attentive hierarchical recurrent encoder (AHRE), which is capable of encoding sentences hierarchically and generating more descriptive representations by aggregating with an attention mechanism, is designed. Finally, the bidirectional interactions between whole multi-turn contexts and response candidates are calculated to derive the matching information between them. Experiments on four public datasets show that IMN outperforms the baseline models on all metrics, achieving a new state-of-the-art performance and demonstrating compatibility across domains for multi-turn response selection.

cs.CL↗

arXiv2019

Hypericin: Single molecule spectroscopy of an active natural ingredient

Hypericin can be found in nature in Hypericum perforatum (St. John's Wort) and has become subject of intense biochemical research. Studies report of antidepressive, antineoplastic, antitumor and antiviral activity of hypericin. Among the variety of potential applications hypericin can be used as photosensitizer in photodynamic therapy (PDT), where it is brought into cancer cells and produces singlet oxygen upon irradiation with a suitable light source. Therefore, the photophysical properties of hypericin are crucial for a successful application in a medical treatment. Here, we present the first single molecule optical spectroscopy study of hypericin. Its photostability is large enough to obtain single molecule fluorescence, surface enhanced Raman spectra (SERS), fluorescence lifetime, antibunching and blinking dynamics. Embedding hypericin in a PVA matrix changes the blinking dynamics, reduces the fluorescence lifetime and increases the photostability. Single molecule SERS spectra show both the neutral and deprotonated form of hypericin and exhibit sudden spectral changes, which can be associated with a reorientation of the single molecule with respect to the surface.

physics.chem-ph↗

arXiv2019

A Dye-Sensitized CdSe Nanocrystal Optical Transistor with High ON/OFF Ratio in the First Telecom Window with 74 ns Rise Time

We report an optically gated transistor composed of CdSe nanocrystals (NCs), sensitized with the dye Zinc beta-tetraaminophthalocyanine for operation in the first telecom window. This device shows a high ON/OFF ratio of six orders of magnitude in the red spectral region and an unprecedented 4.5 orders of magnitude at 847 nm. By transient absorption spectroscopy, we reveal that this unexpected infrared sensitivity is due to electron transfer from the dye to the CdSe NCs within 5 ps. We show by time-resolved photocurrent measurements that this enables fast rise times during near-infrared optical gating of 74 ns. Electronic coupling and accelerated non-radiative recombination of charge carriers at the interface between the dye and the CdSe NCs are further corroborated by steady-state and time-resolved photoluminescence measurements. Field-effect transistor measurements indicate that the increase in photocurrent upon laser illumination is mainly due to the increase in carrier concentration while the mobility remains unchanged. Our results illustrate that organic dyes as ligands for NCs invoke new optoelectronic functionalities, such as fast optical gating at sub-bandgap optical excitation energies.

cond-mat.mtrl-sci↗

arXiv2019

Several Experiments on Investigating Pretraining and Knowledge-Enhanced Models for Natural Language Inference

Natural language inference (NLI) is among the most challenging tasks in natural language understanding. Recent work on unsupervised pretraining that leverages unsupervised signals such as language-model and sentence prediction objectives has shown to be very effective on a wide range of NLP problems. It would still be desirable to further understand how it helps NLI; e.g., if it learns artifacts in data annotation or instead learn true inference knowledge. In addition, external knowledge that does not exist in the limited amount of NLI training data may be added to NLI models in two typical ways, e.g., from human-created resources or an unsupervised pretraining paradigm. We runs several experiments here to investigate whether they help NLI in the same way, and if not,how?

cs.CL↗

arXiv2019

Condition-Transforming Variational AutoEncoder for Conversation Response Generation

This paper proposes a new model, called condition-transforming variational autoencoder (CTVAE), to improve the performance of conversation response generation using conditional variational autoencoders (CVAEs). In conventional CVAEs , the prior distribution of latent variable z follows a multivariate Gaussian distribution with mean and variance modulated by the input conditions. Previous work found that this distribution tends to become condition independent in practical application. In our proposed CTVAE model, the latent variable z is sampled by performing a non-lineartransformation on the combination of the input conditions and the samples from a condition-independent prior distribution N (0; I). In our objective evaluations, the CTVAE model outperforms the CVAE model on fluency metrics and surpasses a sequence-to-sequence (Seq2Seq) model on diversity metrics. In subjective preference tests, our proposed CTVAE model performs significantly better than CVAE and Seq2Seq models on generating fluency, informative and topic relevant responses.

cs.CL↗

arXiv2019

Exploring Unsupervised Pretraining and Sentence Structure Modelling for Winograd Schema Challenge

Winograd Schema Challenge (WSC) was proposed as an AI-hard problem in testing computers' intelligence on common sense representation and reasoning. This paper presents the new state-of-theart on WSC, achieving an accuracy of 71.1%. We demonstrate that the leading performance benefits from jointly modelling sentence structures, utilizing knowledge learned from cutting-edge pretraining models, and performing fine-tuning. We conduct detailed analyses, showing that fine-tuning is critical for achieving the performance, but it helps more on the simpler associative problems. Modelling sentence dependency structures, however, consistently helps on the harder non-associative subset of WSC. Analysis also shows that larger fine-tuning datasets yield better performances, suggesting the potential benefit of future work on annotating more Winograd schema sentences.

cs.CL↗

arXiv2019

Promoting Diversity for End-to-End Conversation Response Generation

We present our work on Track 2 in the Dialog System Technology Challenges 7 (DSTC7). The DSTC7-Track 2 aims to evaluate the response generation of fully data-driven conversation models in knowledge-grounded settings, which provides the contextual-relevant factual texts. The Sequenceto-Sequence models have been widely used for end-to-end generative conversation modelling and achieved impressive results. However, they tend to output dull and repeated responses in previous studies. Our work aims to promote the diversity for end-to-end conversation response generation, which follows a two-stage pipeline: 1) Generate multiple responses. At this stage, two different models are proposed, i.e., a variational generative (VariGen) model and a retrieval based (Retrieval) model. 2) Rank and return the most related response by training a topic coherence discrimination (TCD) model for the ranking process. According to the official evaluation results, our proposed Retrieval and VariGen systems ranked first and second respectively on objective diversity metrics, i.e., Entropy, among all participant systems. And the VariGen system ranked second on NIST and METEOR metrics.

cs.CL↗

arXiv2018

The USTC-NEL Speech Translation system at IWSLT 2018

This paper describes the USTC-NEL system to the speech translation task of the IWSLT Evaluation 2018. The system is a conventional pipeline system which contains 3 modules: speech recognition, post-processing and machine translation. We train a group of hybrid-HMM models for our speech recognition, and for machine translation we train transformer based neural machine translation models with speech recognition output style text as input. Experiments conducted on the IWSLT 2018 task indicate that, compared to baseline system from KIT, our system achieved 14.9 BLEU improvement.

cs.CL↗

arXiv2018

Building Sequential Inference Models for End-to-End Response Selection

This paper presents an end-to-end response selection model for Track 1 of the 7th Dialogue System Technology Challenges (DSTC7). This task focuses on selecting the correct next utterance from a set of candidates given a partial conversation. We propose an end-to-end neural network based on enhanced sequential inference model (ESIM) for this task. Our proposed model differs from the original ESIM model in the following four aspects. First, a new word representation method which combines the general pre-trained word embeddings with those estimated on the task-specific training set is adopted in order to address the challenge of out-of-vocabulary (OOV) words. Second, an attentive hierarchical recurrent encoder (AHRE) is designed which is capable to encode sentences hierarchically and generate more descriptive representations by aggregation. Third, a new pooling method which combines multi-dimensional pooling and last-state pooling is used instead of the simple combination of max pooling and average pooling in the original ESIM. Last, a modification layer is added before the softmax layer to emphasize the importance of the last utterance in the context for response selection. In the released evaluation results of DSTC7, our proposed method ranked second on the Ubuntu dataset and third on the Advising dataset in subtask 1 of Track 1.

cs.CL↗

arXiv2018

Biocompatible Two-dimensional Titanium Nanosheets for Efficient Plasmonic Photothermal Cancer Therapy

Photothermal therapy (PTT) has shown significant potential in cancer treatment. However, developing nanomaterial-based photothermal agents with good biocompatibility and high photothermal conversion efficiency (PTCE) remains a key challenge. Titanium has been widely employed as biomedical materials based on their excellent biocompatibility. In this work, the titanium based plasmonic photothermal therapy (Ti-PPTT) is demonstrated. Using the liquid-phase exfoliation (LPE), the metallic Ti can be fabricated into the two-dimensional (2D) nanosheets (NSs), similar to exfoliating other layered 2D materials. The 2D Ti NSs exhibited good biocompatibility, high extinction coefficient of 20.8 Lg-1cm1 and high PTCE of 73.4%, owing to localized surface plasmon resonances (LSPR); which is significantly higher than other photothermal agents, including Au (21%), MoS2 (24.4%), BP (28.4%) and Ti3C2 MXene (30.6%). Consequently, 2D Ti-PPTT exhibited a notable therapeutic effect in a human hepatocellular carcinoma model without side effects. Our study could pave a new avenue for PTT using metal Ti and arouse a wide interest in the potential efficient PTT for other elemental transition metals owing to their LSPR. Furthermore, the efficient photothermal effect and environmental friendliness of Ti NSs make them deserve more research toward other application, such as solar energy harvesting and sea water desalination.

physics.app-ph↗