Slot Values Research Articles

Knowledge-aware audio-grounded generative slot filling for limited annotated data

Manually annotating fine-grained slot-value labels for task-oriented dialogue (ToD) systems is an expensive and time-consuming endeavour. This motivates research into slot-filling methods that operate with limited amounts of labelled data. Moreover, the majority of current work on ToD is based solely on text as the input modality, neglecting the additional challenges of imperfect automatic speech recognition (ASR) when working with spoken language. In this work, we propose a Knowledge-Aware Audio-Grounded generative slot filling framework, termed KA2G, that focuses on few-shot and zero-shot slot filling for ToD with speech input. KA2G achieves robust and data-efficient slot filling for speech-based ToD by (1) framing it as a text generation task, (2) grounding text generation additionally in the audio modality, and (3) conditioning on available external knowledge (e.g. a predefined list of possible slot values). We show that combining both modalities within the KA2G framework improves the robustness against ASR errors. Further, the knowledge-aware slot-value generator in KA2G, implemented via a pointer generator mechanism, particularly benefits few-shot and zero-shot learning. Experiments, conducted on the standard speech-based single-turn SLURP dataset and a multi-turn dataset extracted from a commercial ToD system, display strong and consistent gains over prior work, especially in few-shot and zero-shot setups.

OSTOD: One-Step Task-Oriented Dialogue with activated state and retelling response

As of present, the progress of conversational AI research has been greatly propelled by large-scale pre-trained language models. In particular, task-oriented dialogue systems have gained widespread attention owing to their immense potential in helping individuals accomplish diverse objectives, such as booking hotels, making restaurant reservations, and purchasing train tickets. In the past, task-oriented dialogue systems were typically viewed as a multi-step process that included spoken language understanding, dialogue state tracking, dialogue policy learning, and natural language generation. More recently, large-scale pre-trained language models enables the development of end-to-end neural pipeline task-oriented dialogue systems, which combine multiple steps into a single model, allowing for joint optimization and preventing error propagation. However, in order to explicitly retrieve information from databases to ensure the interpretability of the system, almost all end-to-end neural pipeline methods inevitably require predicting dialogue state as an intermediate result specialized for the domain or task, which results in significant challenges for generalization. To solve the problem above, we propose One-Step Task-Oriented Dialogue (OSTOD) in this paper, which models task-oriented dialogue by synchronously generating activated states and retelling responses, where activated states refer to slot values that contribute to database access, and retelling responses are system responses that contain activated state information. Specifically, first, automatic methods are designed to build data containing activated states and retelling responses. Then, a joint generation model that synchronously predicts activated states and retelling responses in a single step is proposed for task-oriented dialogue modelling. Based on empirical results obtained from the MultiWOZ 2.0 and MultiWOZ 2.1 datasets, our OSTOD model demonstrates comparable performance to state-of-the-art baselines. Moreover, our model exhibits exceptional generalization capabilities in few-shot learning and domain transfer scenarios.

Multi-domain gate and interactive dual attention for multi-domain dialogue state tracking

Multi-domain dialogue state tracking (MDST) is a crucial component of task-oriented dialogue systems. In the context of multi-turn dialogues between the user and the system, MDST necessitates the continuous keeping track of dialogue states based on the information present in the current dialogue utterance and the dialogue states from the preceding turn. Recent work achieves the successful execution of multi-domain dialogue tasks by adopting an approach that treats each state as an individual label, while regrettably neglecting the potential benefits of incorporating domain-specific information associated with these states. Simultaneous, existing models exhibit a deficiency in effectively modelling the explicit correlations between dialogue contextual semantics and dialogue states. In this paper, we introduce the modules of multi-domain gate and interactive dual attention as novel solutions to address the aforementioned concerns. For the efficient exploitation of domain-specific information within states, we leverage the multi-domain gate as indices to amplify the states pertinent to the current utterance domain while filtering out irrelevant states. Interactive dual attention comprises utterance attention and slot attention, effectively modelling the correlation between dialogue utterances and slots. Additionally, interactive dual attention ensures that each dialogue utterance interacts with the slots once to derive all state updates, thereby ensuring computational efficiency. Specifically, slot attention models the associations between slots by incorporating semantic features to forecast updates in slot values. Meanwhile, utterance attention captures the semantics of dialogue context and integrates it with slot name features to generate dialogue states. All the aforementioned modules are designed based on a slot-independent framework, enabling efficient scalability of slots and circumventing issues related to model input limitations. The experimental results on the multi-domain dialogues dataset MultiWOZ 2.4 demonstrate the superior performance of our model compared to the baselines. Additionally, we conduct a comprehensive analysis of the effectiveness of the multi-domain gate and interactive dual attention modules, elucidating their contribution to the performance of the model through visualization and case studies.

A Stack-Propagation Framework With Slot Filling for Multi-Domain Dialogue State Tracking.

Dialogue state tracking (DST) is a core component of task-oriented dialogue systems. Recent works focus mainly on end-to-end DST models that omit the spoken language understanding (SLU) module to directly obtain the dialogue state based on a user's dialogue. However, the slot information detected by slot filling in SLU is closely tied to the slot-value pair that needs to be updated in DST. Efficient use of the key slot semantic knowledge obtained by slot filling contributes to improving the performance of DST. Based on this idea, we introduce slot filling as a subtask and build an end-to-end joint model to explicitly integrate the slot information detected by slot filling, which further guides DST. In this article, a novel stack-propagation framework with slot filling for multidomain DST is proposed. The stack-propagation framework is introduced to jointly model slot filling and DST. The framework directly feeds the key slot semantic knowledge detected by slot filling into the DST module. In addition, a slot-masked attention mechanism is designed to enable DST to focus on the key slot information obtained by slot filling. When the slot value is updated, a slot-value softcopy mechanism is designed to enhance the influence of the words marked by key slots. Experiments show that our approach outperforms previous methods and performs outstandingly on two benchmark datasets.

Cross-domain coreference modeling in dialogue state tracking with prompt learning

Dialogue state tracking (DST) is to identify user goals from dialogue context and it is an essential component in task-oriented dialogue systems. In multi-domain task-oriented dialogues, a user often refers to the information mentioned in the previous context when the topic is transferred to another domain. Accurate modeling of the cross-domain coreference plays an important role in building qualified DST systems. As far as we know, there is only one work attempting to model the cross-domain coreference phenomenon in DST. However, it still has low efficiency and suffers from the difficulty of handling the complex reasoning over the dialogue context. To tackle these problems, in this paper, we propose a simple but effective DST model, called Coref-DST, to track the cross-domain coreference slots. Instead of predicting the actual values via complex reasoning, Coref-DST directly identifies the coreferred domains and slots from the dialogue context. Moreover, a domain-specific prompt method is proposed to predict all the slot values in a domain simultaneously, so as to better capture the relationship among the slots. The extensive experimental results on the MultiWOZ 2.3 dataset demonstrate that Coref-DST not only outperforms the state-of-the-art DST baselines but also has higher efficiency of training and inference.

Out-of-scope intent detection with intent-invariant data augmentation

In practical dialogue systems, it is crucial to avoid undesired responses and poor user experiences by detecting Out-Of-Scope (OOS) intents from user utterances. Currently, to detect OOS intents, limited-supervised methods are more potential due to using limited true OOS data to better model the OOS data distribution. However, existing limited-supervised methods often yield low-quality OOS augmentations, i.e., noisy OOS and long-distant OOS, due to the use of the retrieval-based data augmentation mechanism, which will damage the OOS intent detection performance. To tackle this problem, in this paper, we propose a novel OOS intent detection method by leveraging intent-invariant data augmentation, called InInOOS, which can generate high-quality pseudo-OOS utterances with invariant OOS intents but various slot values and different expressions to further enhance the OOS intent detection performance. Specifically, we first generate pseudo-OOS candidates using our pre-trained intent-invariant utterance generation model, and then the most beneficial candidates are selected to train an OOS intent detection model. Extensive experiments on two public datasets show that our method performs better than state-of-the-art baselines.

BDMCA: a big data management system for Chinese auditing.

The advent of big data technologies makes a profound impact on various facets of our lives, which also presents an opportunity for Chinese audits. However, the heterogeneity of multi-source audit data, the intricacy of converting Chinese into SQL, and the inefficiency of data processing methods present significant obstacles to the growth of Chinese audits. In this article, we proposed BDMCA, a big data management system designed for Chinese audits. We developed a hybrid management architecture for handling Chinese audit big data, that can alleviate the heterogeneity of multi-mode data. Moreover, we defined an R-HBase spatio-temporal meta-structure for auditing purposes, which exhibits almost linear response time and excellent scalability. Compared to MD-HBase, R-HBase performs 4.5× and 3× better in range query and kNN query, respectively. In addition, we leveraged the slot value filling method to generate templates and build a multi-topic presentation learning model MRo-SQL. MRo-SQL outperforms the state-of-the-art X-SQL parsing model with improvements in logical-form accuracy of up to 5.2%, and execution accuracy of up to 5.9%.

SP-NLG: A Semantic-Parsing-Guided Natural Language Generation Framework

We propose SP-NLG: A semantic-parsing-guided natural language generation framework for logical content generation with high fidelity. Prior studies adopt large pretrained language models and coarse-to-fine decoding techniques to generate text with logic; while achieving considerable results on automatic evaluation metrics, they still face challenges in terms of logical fidelity based on human evaluation. Inspired by semantic parsing, which translates natural language utterances into executable logical forms, we propose to guide the generation process with a semantic parser. Different from semantic parsing and QA tasks, of which the logical correctness can be evaluated based on the execution result, the logic information of the generated content is implicit. To leverage a semantic parser for generation, we propose a slot-tied back-search algorithm. We follow the coarse-to-fine generation scheme, but instead of filling the slots with model predictions, which is less uncontrolled, the slot values are offline searched by the algorithm. The slot-tied back-search algorithm ties the parameters of a logic form with the slots of a template in one-to-one correspondence. We back-search the arguments that correctly execute the logic form and fill the arguments (as slot values) into the textual template to generate the final target, which ensures the logical correctness. Experiment results of a model built on SP-NLG demonstrates that our framework achieves high fidelity on logical text generation.

RSP-DST: Revisable State Prediction for Dialogue State Tracking

Task-oriented dialogue systems depend on dialogue state tracking to keep track of the intentions of users in the course of conversations. Although recent models in dialogue state tracking exhibit good performance, the errors in predicting the value of each slot at the current dialogue turn of these models are easily carried over to the next turn, and unlikely to be revised in the next turn, resulting in error propagation. In this paper, we propose a revisable state prediction for dialogue state tracking, which constructs a two-stage slot value prediction process composed of an original prediction and a revising prediction. The original prediction process jointly models the previous dialogue state and dialogue context to predict the original dialogue state of the current dialogue turn. Then, in order to avoid the errors existing in the original dialogue state continuing to the next dialogue turn, a revising prediction process utilizes the dialogue context to revise errors, alleviating the error propagation. Experiments are conducted on MultiWOZ 2.0, MultiWOZ 2.1, and MultiWOZ 2.4 and results indicate that our model outperforms previous state-of-the-art works, achieving new state-of-the-art performances with 56.35, 58.09, and 75.65% joint goal accuracy, respectively, which has a significant improvement (2.15, 1.73, and 2.03%) over the previous best results.

Neural response generation for task completion using conversational knowledge graph.

Effective dialogue generation for task completion is challenging to build. The task requires the response generation system to generate the responses consistent with intent and slot values, have diversity in response and be able to handle multiple domains. The response also needs to be context relevant with respect to the previous utterances in the conversation. In this paper, we build six different models containing Bi-directional Long Short Term Memory (Bi-LSTM) and Bidirectional Encoder Representations from Transformers (BERT) based encoders. To effectively generate the correct slot values, we implement a copy mechanism at the decoder side. To capture the conversation context and the current state of the conversation we introduce a simple heuristic to build a conversational knowledge graph. Using this novel algorithm we are able to capture important aspects in a conversation. This conversational knowledge-graph is then used by our response generation model to generate more relevant and consistent responses. Using this knowledge-graph we do not need the entire utterance history, rather only the last utterance to capture the conversational context. We conduct experiments showing the effectiveness of the knowledge-graph in capturing the context and generating good response. We compare these results against hierarchical-encoder-decoder models and show that the use of triples from the conversational knowledge-graph is an effective method to capture context and the user requirement. Using this knowledge-graph we show an average performance gain of 0.75 BLEU score across different models. Similar results also hold true across different manual evaluation metrics.

Intent Classification and Slot Filling Model for In-Vehicle Services in Korean

Since understanding a user’s request has become a critical task for the artificial intelligence speakers, capturing intents and finding correct slots along with corresponding slot value is significant. Despite various studies concentrating on a real-life situation, dialogue system that is adaptive to in-vehicle services are limited. Moreover, the Korean dialogue system specialized in an vehicle domain rarely exists. We propose a dialogue system that captures proper intent and activated slots for Korean in-vehicle services in a multi-tasking manner. We implement our model with a pre-trained language model, and it includes an intent classifier, slot classifier, slot value predictor, and value-refiner. We conduct the experiments on the Korean in-vehicle services dataset and show 90.74% of joint goal accuracy. Also, we analyze the efficacy of each component of our model and inspect the prediction results with qualitative analysis.

A multi‐queue priority‐based task scheduling algorithm in fog computing environment

AbstractFog computing is a novel, decentralized and heterogeneous computing environment that extends the traditional cloud computing systems by facilitating task processing near end‐users on computing resources called fog nodes. These diverse and resource‐constrained fog devices process a large volume of tasks generated by various fog applications. These tasks are generated by various applications, some of which may be latency‐sensitive, while others may tolerate some degree of delay in their normal functions. Task scheduling determines when a task should be allocated to a computing resource and how long that task can occupy the assigned resource. The majority of task scheduling algorithms focus on prioritizing the latency‐sensitive tasks only, which results in the long waiting time for the other type of tasks. Hence, these priority‐based schedulers cause task starvation for less important tasks while achieving delay‐optimal results for latency‐sensitive tasks. As a result, in this paper, we propose MQP, a multi‐queue priority‐based preemptive task scheduling approach that achieves a balanced task allocation for those applications that can tolerate a certain amount of processing delay and the latency‐sensitive fog applications. At run‐time, the MQP algorithm categorizes tasks as short and long based on their burst time. MQP algorithm maintains a separate task queue for each task category and dynamically updates the time slot value for preemption. The proposed technique's major purpose is to reduce response time for those data‐intensive applications in the fog computing environment, which include both latency‐sensitive tasks and tasks which are less latency‐sensitive, thereby addressing the starvation problem for less latency‐sensitive tasks. A smart traffic management case study is created to model a scenario with both latency‐sensitive short and less latency‐sensitive long tasks. We implement the MQP algorithm using iFogSim and confirm that it reduces the service latencies for long tasks. Simulation results show that the MQP algorithm allocates tasks to a fog device more efficiently and reduces the service latencies for long tasks. The average value of percentage reduction in the latency across all experimental configurations achieved is 22.68% and 38.45% in comparison to First Come‐First Serve and shortest job first algorithms.

Energy Management Strategy of a Reconfigurable Grid-Tied Hybrid AC/DC Microgrid for Commercial Building Applications

This paper proposes an energy management strategy (EMS) of a reconfigurable grid-tied hybrid ac/dc microgrid (HMG) architecture for commercial building (CB) applications. This HMG architecture consists of a multi-mode configuration (MMC) with renewable-based distributed generators (DGs), energy storages (ESs), and genset. The main advantage of this architecture is its capability to reconfigure its structure based on the predicted building load power (BLP) and renewable-based DGs power. However, minimizing the building electricity cost (BEC) and maximizing the reliability index (RI) of a reconfigurable grid-tied HMG architecture is a challenging task due to the stochastic behaviors of BLP and renewable-based DGs power. In this context, the BLP and renewable-based DGs behaviors are modeled using an artificial neural network approach to predict future time slot values. Then, system level models are developed for HMG energy sources and grid-tied converters/switches. Furthermore, BEC and RI models are developed based on the dynamic pricing of grid/HMG electricity cost and supplied energy. Then, an EMS is proposed for the developed reconfigurable grid-tied HMG architecture, which consists of a two-stage control strategy, i.e., stage I and stage II. Stage I control strategy minimizes BEC and maximizes RI using multi-objective particle swarm optimization (MOPSO) and MMC. Stage II control strategy generates control signals for HMG energy sources, converters, and grid-tied converters/switches based on stage I reference signals. Historical data is used to demonstrate the effectiveness of the proposed EMS for a reconfigurable grid-tied HMG architecture. Through numerical simulation studies, it is shown that the proposed EMS is capable of reducing BEC and increasing RI by concurrently enabling MMC of a reconfigurable grid-tied HMG architecture.

Numerical simulation of the nozzle configuration in strip casting process

This work examines the design of nozzles in continuous strip casting process. Three-dimensional (3D) simulations of steady turbulent (k-ε) flow are done at the upper part of the mould using a finite-volume (CFX) model. This is performed for different inlet systems, including the inlet nozzle jets with a free stream, the submerged nozzle jets, the slot inlet system, and the slot-submerged inlet system. The resulting heat flux to the solidifying shell has also been studied. Numerous operating parameters are examined, including the shape, size, position, and thickness of the ports and the bottom geometry. It is found that different inlet nozzle configurations change the molten flow and heat patterns, mainly in the upper region of the mould. By applying the slot nozzle inlet system, turbulence and values of the averaged velocity field in that area decrease significantly.

Cross-Domain Slot Filling as Machine Reading Comprehension: A New Perspective

With intelligent dialogue systems becoming more and more important in our daily lives, slot filling, one of the most important components of an intelligent dialogue system, has gotten a lot of attention from academia and industry. Despite many advancements in the single-domain learning paradigm for slot filling, leveraging resources from different domains to boost learning for a target domain remains a challenge. In contrast to prior methods that supplemented a sequence labeling model with slot meta-information, we address cross-domain slot filling as a machine reading comprehension (MRC) problem for the first time, where the extraction of slot values is viewed as a question answering process. In the framework above, we present both static and dynamic question generating mechanisms, which have complimentary effects in diverse cross-domain contexts. Furthermore, we devise a dynamic question generation approach that can generate numerous values for a slot at the same time. Finally, we construct a pre-training and fine-tuning training approach that enables us to improve learning by utilizing MRC’s resources. We conducted extensive experiments on four datasets to evaluate our approach, and the experimental results clearly justified the advantages of our approach in various cross-domain settings.

Generating Predictable and Adaptive Dialog Policies in Single- and Multi-domain Goal-oriented Dialog Systems

Most existing commercial goal-oriented chatbots are diagram-based; i.e. they follow a rigid dialog flow to fill the slot values needed to achieve a user’s goal. Diagram-based chatbots are predictable, thus their adoption in commercial settings; however, their lack of flexibility may cause many users to leave the conversation before achieving their goal. On the other hand, state-of-the-art research chatbots use Reinforcement Learning (RL) to generate flexible dialog policies. However, such chatbots can be unpredictable, may violate the intended business constraints, and require large training datasets to produce a mature policy. We propose a framework that achieves a middle ground between the diagram-based and RL-based chatbots: we constrain the space of possible chatbot responses using a novel structure, the chatbot dependency graph, and use RL to dynamically select the best valid responses. Dependency graphs are directed graphs that conveniently express a chatbot’s logic by defining the dependencies among slots: all valid dialog flows are encapsulated in one dependency graph. Our experiments in both single-domain and multi-domain settings show that our framework quickly adapts to user characteristics and achieves up to 23.77% improved success rate compared to a state-of-the-art RL model.

Elastic CRFs for Open-Ontology Slot Filling

Slot filling is a crucial component in task-oriented dialog systems that is used to parse (user) utterances into semantic concepts called slots. An ontology is defined by the collection of slots and the values that each slot can take. The most widely used practice of treating slot filling as a sequence labeling task suffers from two main drawbacks. First, the ontology is usually pre-defined and fixed and therefore is not able to detect new labels for unseen slots. Second, the one-hot encoding of slot labels ignores the correlations between slots with similar semantics, which makes it difficult to share knowledge learned across different domains. To address these problems, we propose a new model called elastic conditional random field (eCRF), where each slot is represented by the embedding of its natural language description and modeled by a CRF layer. New slot values can be detected by eCRF whenever a language description is available for the slot. In our experiment, we show that eCRFs outperform existing models in both in-domain and cross-domain tasks, especially in predicting unseen slots and values.

Research on Spoken Language Understanding Based on Deep Learning

Aiming at solving the problem that the recognition effect of rare slot values in spoken language is poor, which affects the accuracy of oral understanding task, a spoken language understanding method is designed based on deep learning. The local features of semantic text are extracted and classified to make the classification results match the dialogue task. An intention recognition algorithm is designed for the classification results. Each datum has a corresponding intention label to complete the task of semantic slot filling. The attention mechanism is applied to the recognition of rare slot value information, the weight of hidden state and corresponding slot characteristics are obtained, and the updated slot value is used to represent the tracking state. An auxiliary gate unit is constructed between the upper and lower slots of historical dialogue, and the word vector is trained based on deep learning to complete the task of spoken language understanding. The simulation results show that the proposed method can realize multiple rounds of man-machine spoken language. Compared with the spoken language understanding methods based on cyclic network, context information, and label decomposition, it has higher accuracy and F1 value and has higher practical application value.

Theorem for Calculating Time Duration

While developing an app the author came across the fact that while calculating time durations, certain variables are often overlooked which can result in errors. This paper provides an algorithm that considers the absolute values of the time slots and after a discrete set of steps results in the accurate time durations. The scope of this research is not limited to hours and minutes but, can be applied to seconds and milliseconds as well.

Effective Slot Filling via Weakly-Supervised Dual-Model Learning

Slot filling is a challenging task in Spoken Language Understanding (SLU). Supervised methods usually require large amounts of annotation to maintain desirable performance. A solution to relieve the heavy dependency on labeled data is to employ bootstrapping, which leverages unlabeled data. However, bootstrapping is known to suffer from semantic drift. We argue that semantic drift can be tackled by exploiting the correlation between slot values (phrases) and their respective types. By using some particular weakly labeled data, namely the plain phrases included in sentences, we propose a weakly-supervised slot filling approach. Our approach trains two models, namely a classifier and a tagger, which can effectively learn from each other on the weakly labeled data. The experimental results demonstrate that our approach achieves better results than standard baselines on multiple datasets, especially in the low-resource setting.