Search

Task-oriented dialogue systems (TODs) enable users to complete specific goals and are widely used in practice. Although existing models have achieved delightful performance for single-domain dialogues, scalability to new domains is far from well explored. Traditional dialogue systems rely on domain-specific information like dialogue state and database (DB), which limits the scalability of such systems. In this paper, we propose a Scalable Task-Oriented Dialogue modeling framework (STOD). Instead of labeling multiple dialogue components, which have been adopted by previous work, we only predict structured API queries to interact with DB and generate responses based on the complete DB results. Further, we construct a new API-schema-based TOD dataset MultiWOZ-API with API query and DB result annotation based on MultiWOZ 2.1. We then propose MSTOD and CSTOD for multi-domain and cross-domain TOD systems, respectively. We perform extensive qualitative experiments to verify the effectiveness of our proposed framework. We find the following. (1) Scalability across multiple domains: MSTOD achieves 2% improvements than the previous state-of-the-art in the multi-domain TOD. (2) Scalability to new domains: our framework enables satisfying generalization capability to new domains, a significant margin of 10% to existing baselines.

Glycyrrhizae Radix et Rhizoma, a traditional Chinese medicine also known as Gan Cao (GC), is frequently included in clinical prescriptions for the treatment of pneumonia. However, the pharmacological components of GC for pneumonia treatment are rarely explored. Gan An He Ji oral liquid (GAHJ) has a simple composition and contains GC liquid extracts and paregoric, and has been used clinically for many years. Therefore, GAHJ was selected as a compound preparation for the study of GC in the treatment of pneumonia. We conducted an in vivo study of patients with pneumonia undergoing GAHJ treatments for three days. Using the intelligent mass spectrometry data-processing technologies to analyze the metabolism of GC in vivo, we obtained 168 related components of GC in humans, consisting of 24 prototype components and 144 metabolites, with 135 compounds screened in plasma and 82 in urine. After analysis of the metabolic transformation relationship and relative exposure, six components (liquiritin, liquiritigenin, glycyrrhizin, glycyrrhetinic acid, daidzin, and formononetin) were selected as potential effective components. The experimental results based on two animal pneumonia models and the inflammatory cell model showed that the mixture of these six components was effective in the treatment of pneumonia and lung injury and could effectively downregulate the level of inducible nitric oxide synthase (iNOS). Interestingly, glycyrrhetinic acid exhibited the strongest inhibition on iNOS and the highest exposure in vivo. The following molecular dynamic simulations indicated a strong bond between glycyrrhetinic acid and iNOS. Thus, the current study provides a pharmaceutical basis for GC and reveals the possible corresponding mechanisms in pneumonia treatment.

Context modeling has always been the groundwork for the dialogue response generation task, yet it presents challenges due to the loose context relations among open-domain dialogue sentences. Introducing simulated dialogue futures has been proposed as a solution to mitigate the problem of low history–response relevance. However, these approaches simply assume that the history and future of a dialogue have the same effect on response generation. In reality, the coherence between dialogue sentences varies, and thus, history and the future are not uniformly helpful in response prediction. Consequently, determining and leveraging the relevance between history–response and response–future to aid in response prediction emerges as a pivotal concern. This paper addresses this concern by initially establishing three context relations of response and its context (history and future), reflecting the relevance between the response and preceding and following sentences. Subsequently, we annotate response contextual relation labels on a large-scale dataset, DailyDialog (DD). Leveraging these relation labels, we propose a response generation model that adaptively integrates contributions from preceding and succeeding sentences guided by explicit relation labels. This approach mitigates the impact in cases of lower relevance and amplifies contributions in cases of higher relevance, thus improving the capability of context modeling. Experimental results on public dataset DD demonstrate that our response generation model significantly enhances coherence by 3.02% in long sequences (4-gram) and augments bi-gram diversity by 17.67%, surpassing the performance of previous models.

The sixth generation (6G) mobile networks will reshape the world by offering instant, efficient, and intelligent hyper-connectivity, as envisioned by the previously proposed Ubiquitous-X 6G networks. Such hyper-massive and global connectivity will introduce tremendous challenges into the operation and management of 6G networks, calling for revolutionary theories and technological innovations. To this end, we propose a new route to boost network capabilities toward a wisdom-evolutionary and primitive-concise network (WePCN) vision for the Ubiquitous-X 6G network. In particular, we aim to concretize the evolution path toward the WePCN by first conceiving a new semantic representation framework, namely semantic base, and then establishing an intelligent and efficient semantic communication (IE-SC) network architecture. In the IE-SC architecture, a semantic intelligence plane is employed to interconnect the semantic-empowered physical-bearing layer, network protocol layer, and application-intent layer via semantic information flows. The proposed architecture integrates artificial intelligence and network technologies to enable intelligent interactions among various communication objects in 6G. It features a lower bandwidth requirement, less redundancy, and more accurate intent identification. We also present a brief review of recent advances in semantic communications and highlight potential use cases, complemented by a range of open challenges for 6G.

Complexes possessing coordination spheres that can accommodate nine ligand atoms typically display spherical distributions of these atoms. Here, the authors predict that M-centered [OB-B7O7-BO] adopts unusual heptagonal bipyramidal nonacoordination.

ObjectiveTo characterize the serum metabolomic profile and its role in the prediction of poor ovarian response (POR).Patient(s)Twenty-five women with normal ovarian reserve (24-33 years, antral follicle count [AFC] ≥5, anti-Müllerian hormone [AMH] ≥1.2 ng/ml) as the control group and another twenty-five women with POR (19-35 years, AFC

Niche theory is significant for understanding the function of community structure, interspecific relationships, and community dynamic succession. However, there are few studies on the soil animal niche in returning farmland to forest areas on the Loess Plateau, making it challenging to comprehend the utilization of soil animal resources, the stability of the local community, and the succession process in the areas. Therefore, this study collected soil animals in five typical vegetation types: Robinia pseudoacacia (R), Hippophae rhamnoides (H), Populus simonii (P), Pinus tabulaeformis (T), and Armeniaca sibirica x Hippophae rhamnoides (M), with abandoned grassland (G) used as a control group. Then, the number of soil animal taxa, individuals, diversity, and niche were sampled and examined in the study areas during the four seasons of spring, summer, autumn, and winter using the manual sorting method and the Tullgren method. The results revealed that 3872 soil animals from 3 Phyla, 8 Classes, 22 Orders, and 49 Families were captured in the study areas. The dominant groups of soil macrofauna were Diptera larvae, Julidae, and Formicidae, and the dominant groups of meso–micro soil fauna were Oribatida, Protospira, and Collembola juveniles. Soil animals have rich nutritional function groups, with the most saprophytic soil animal groups. The individual density and taxa number of soil animals in G were lower than other vegetation on the whole. H, M, and P had a higher Shannon–Winner index than the other vegetation. Seasonal changes had different effects on macro and meso–micro soil fauna. The diversity of soil macrofauna is higher in spring and summer, and that of meso–micro soil fauna is higher in autumn and winter. Oribatida, Diptera Larvae, and Formicidae had a large niche width in the main taxa of soil animals, with universal adaptability to the environment. Cicadellidae and Culicidae had narrow niche widths and were highly dependent on resources and the environment. There were 67 pairs of highly overlapped (Oik > 0.8) taxa of soil animals and 56 pairs of moderately overlapped (0.6 < Oik ≤ 0.8) taxa, accounting for 80.39% of the total number of taxa. Soil animals had high commonality in resource utilization, intense competition, and poor community stability. As a result, we can conclude that the soil animal community in the study areas was in the stage of succession.

Dialog management plays an important role in the task-oriented dialog system. Most of the previous works divide dialog management into state tracker and action selector. The two parts are modeled separately and implemented in a pipelined way, which suffers from the problem of error accumulation, and the feedback signal from action selector cannot be propagated to state tracker and natural language understanding module. This paper proposes a word-based partially observable Markov decision processes' dialog management that integrates natural language understanding, state tracker, and action selector into an end-to-end architecture. Our proposed dialog management takes the words from user utterances as inputs and then produces optimal action as well as slot values of natural language understanding which are necessary for response generation. To this end, we propose a hybrid learning method, which integrates reinforcement learning and supervised learning, to optimize the action selector and slot filler jointly. In addition, we develop a high-return prioritized experience replay to speed up the convergence of the training process. The experimental results show that the proposed dialog management outperforms four strong baselines in a series of different dialog tasks. A human user's evaluation also shows the same results. The high-return prioritized experience replay accelerates the convergence effectively, especially in the scenario in which the proposed dialog management works on more complex tasks.

Answering different multi-choice machine reading comprehension (MRC) questions generally requires different information due to the abundant diversity of the questions, options and passages. Recently, pre-trained language models which provide rich information have been widely used to address MRC tasks. Most of the existing work only focuses on the output representation at the top layer of the models; the subtle and beneficial information provided by the intermediate layers is ignored. This paper therefore proposes a multi-decision based transformer model that builds multiple decision modules by utilizing the outputs at different layers to confront the various questions and passages. To avoid the information diversity in different layers being damaged during fine-tuning, we also propose a learning rate decaying method to control the updating speed of the parameters in different blocks. Experimental results on multiple publicly available datasets show that our model can answer different questions by utilizing the representation in different layers and speed up the inference procedure with considerable accuracy.

Dialogue management plays a vital role in task-oriented dialogue systems, which has become an active area of research in recent years. Despite the promising results brought from deep reinforcement learning, most of the studies need to develop a manual user simulator additionally. To address the time-consuming development of simulator policy, we propose a multi-agent dialogue model where an end-to-end dialogue manager and a user simulator are optimized simultaneously. Different from prior work, we optimize the two-agents from scratch and apply the reward shaping technology based on adjacency pairs constraints in conversational analysis to speed up learning and to avoid the derivation from normal human-human conversation. In addition, we generalize the one-to-one learning strategy to one-to-many learning strategy, where a dialogue manager can be concurrently optimized with various user simulators, to improve the performance of trained dialogue manager. The experimental results show that one-to-one agents trained with adjacency pairs constraints can converge faster and avoid derivation. In cross-model evaluation with human users involved, the dialogue manager trained in one-to-many strategy achieves the best performance.

In the title compound, [PtCl2(C6H7N)(C2H6OS)], the PtII ion has an approximately square-planar coordination environment. It binds to the N atom of the aniline ligand and is trans to the S atom of the dimethyl sulfoxide. The two Cl− anions are also in trans positions. In the crystal, molecules are linked by N—H...O, C—H...Cl and C—H...O hydrogen bonds.

In the title compound, C21H14N6, the pyridine ring and two pyrazine rings are nearly coplanar [dihedral angles = 2.03 (7) and 1.60 (7)°], while the dihedral angle between the indole ring system and the pyridine ring is 29.04 (6)°. In the crystal, molecules are linked by N—H...N hydrogen bonds, which generate [\overline{1}10] chains. The packing is consolidated by C—H...N hydrogen bonds and aromatic π–π stacking, generating a three-dimensional network.