Amendable Generation for Dialogue State Tracking

In task-oriented dialogue systems, recent dialogue state tracking methods tend to perform one-pass generation of the dialogue state based on the previous dialogue state. The mistakes of these models made at the current turn are prone to be carried over to the next turn, causing error propagation. In this paper, we propose a novel Amendable Generation for Dialogue State Tracking (AG-DST), which contains a two-pass generation process: (1) generating a primitive dialogue state based on the dialogue of the current turn and the previous dialogue state, and (2) amending the primitive dialogue state from the first pass. With the additional amending generation pass, our model is tasked to learn more robust dialogue state tracking by amending the errors that still exist in the primitive dialogue state, which plays the role of reviser in the double-checking process and alleviates unnecessary error propagation. Experimental results show that AG-DST significantly outperforms previous works in two active DST datasets (MultiWOZ 2.2 and WOZ 2.0), achieving new state-of-the-art performances.

Not So Fast, Classifier -- Accuracy and Entropy Reduction in Incremental Intent Classification

Incremental intent classification requires the assignment of intent labels to partial utterances. However, partial utterances do not necessarily contain enough information to be mapped to the intent class of their complete utterance (correctly and with a certain degree of confidence). Using the final interpretation as the ground truth to measure a classifier's accuracy during intent classification of partial utterances is thus problematic. We release inCLINC, a dataset of partial and full utterances with human annotations of plausible intent labels for different portions of each utterance, as an upper (human) baseline for incremental intent classification. We analyse the incremental annotations and propose entropy reduction as a measure of human annotators' convergence on an interpretation (i.e. intent label). We argue that, when the annotators do not converge to one or a few possible interpretations and yet the classifier already identifies the final intent class early on, it is a sign of overfitting that can be ascribed to artefacts in the dataset.

Generative Adversarial Networks based on Mixed-Attentions for Citation Intent Classification in Scientific Publications

We propose the mixed-attention-based Generative Adversarial Network (named maGAN), and apply it for citation intent classification in scientific publication. We select domain-specific training data, propose a mixed-attention mechanism, and employ generative adversarial network architecture for pre-training language model and fine-tuning to the downstream multi-class classification task. Experiments were conducted on the SciCite datasets to compare model performance. Our proposed maGAN model achieved the best Macro-F1 of 0.8532.

Ontology Population Reusing Resources for Dialogue Intent Detection: Generic and Multilingual Approach

This work presents a generic semi-automatic strategy to populate the domain ontology of an ontology-driven task-oriented dialogue system, with the aim of performing successful intent detection in the dialogue process, reusing already existing multilingual resources. This semi-automatic approach allows ontology engineers to exploit available resources so as to associate the potential situations in the use case to FrameNet frames and obtain the relevant lexical units associated to them in the target language, following lexical and semantic criteria, without linguistic expert knowledge. This strategy has been validated and evaluated in two use cases, from industrial scenarios, for interaction in Spanish with a guide robot and with a Computerized Maintenance Management System (CMMS). In both cases, this method has allowed the ontology engineer to instantiate the domain ontology with the intent-relevant information with quality data in a simple and low-resource-consuming manner.

Unknown Intent Detection Using Multi-Objective Optimization on Deep Learning Classifiers

Modelling and understanding dialogues in a conversation depends on identifying the user intent from the given text. Unknown or new intent detection is a critical task, as in a realistic scenario a user intent may frequently change over time and divert even to an intent previously not encountered. This task of separating the unknown intent samples from known intents one is challenging as the unknown user intent can range from intents similar to the predefined intents to something completely different. Prior research on intent discovery often consider it as a classification task where an unknown intent can belong to a predefined set of known intent classes. In this paper we tackle the problem of detecting a completely unknown intent without any prior hints about the kind of classes belonging to unknown intents. We propose an effective post-processing method using multi-objective optimization to tune an existing neural network based intent classifier and make it capable of detecting unknown intents. We perform experiments using existing state-of-the-art intent classifiers and use our method on top of them for unknown intent detection. Our experiments across different domains and real-world datasets show that our method yields significant improvements compared with the state-of-the-art methods for unknown intent detection.

The Function of the Intention to Donate in Grant Contract

Issues relating to the will in contracts usually cause a lot of difficulty. This is because will is clearly related to the mental and personal elements. Difficulties arise in defining the concept on the first hand, and in proving it on the other. Hence, the issue of intention to donate, which forms the mental element of the Grant Contract. This study attempts to simplify this difficulty by discussing the function of the intention to donate in Grant Contract. The function of intention to donate in Grant Contracts is twofold: formative and normative. By formative is meant the role of intention to donate in the formation and creation of the Grant Contract as seen in the elements of the contract. Normative refers to the role of intention to donate in distinguishing the Grant Contract from other legal actions, which might overlap with it in some actual cases.

The impact of internet marketing obstacles the intention of e-procurement “A field study on students of the collages in Tartous”

The objective of this research is to identify the obstacles to the use of internet marketing by individuals, has been relying on descriptive analytical method, a questionnaire was developed and make sure of his sincerity and the persistence coefficient, the questionnaire was distributed to the students of the Faculty the second of Economy in Tartous, in order to obtain necessary data for the study. The study found the following results: There were no statistically significant differences between (the Internet infrastructure, the expected risk, distrust for electronic marketing, legislation and laws) and the faith in e-procurement, while no statistically significant relationship between the weakness of experience and awareness of internet marketing and intent in e-procurement and these results back to the nature of the sample taken. The study was presented a set of recommendations including: the need to raise awareness of and confidence in scientific knowledge about the importance of internet marketing, and the need to increase awareness of the importance of the use of computer.

The Effect of Comparative Advertising on Consumer Attitudes (Field Study)

This research consists of two parts. The first part depends on the previous researches and literature dealing with the subject research "comparative advertising". This research aims through the first part to analysis 'comparative advertising' phenomenon, advertisers use "comparative advertising" to persuade consumer to buy the brand through information and facts. This research Through field study aims to measure effect of comparative advertising form(one way advertisement VS. two way advertisement) on consumer attitude toward advertising and consumer attitude toward brand and consumer intention to purchase the brand . Through field study the research shows that there is a significant effect of two way comparative advertising on consumer attitude toward advertising and consumer attitude toward brand and consumer intention to purchase the brand, but there is no significant effect of one way comparative advertising on consumer attitude toward advertising and consumer attitude toward brand and consumer intention to purchase the brand.