Recent work in open-domain conversational agents has demonstrated that significant improvements in humanness and user preference can be achieved via massive scaling in both pre-training data and model size (Adiwardana et al., 2020; Roller et al., 202
0). However, if we want to build agents with human-like abilities, we must expand beyond handling just text. A particularly important topic is the ability to see images and communicate about what is perceived. With the goal of getting humans to engage in multi-modal dialogue, we investigate combining components from state-of-the-art open-domain dialogue agents with those from state-of-the-art vision models. We study incorporating different image fusion schemes and domain-adaptive pre-training and fine-tuning strategies, and show that our best resulting model outperforms strong existing models in multi-modal dialogue while simultaneously performing as well as its predecessor (text-only) BlenderBot (Roller et al., 2020) in text-based conversation. We additionally investigate and incorporate safety components in our final model, and show that such efforts do not diminish model performance with respect to human preference.
Communication between human and mobile agents is getting increasingly important as such agents are widely deployed in our daily lives. Vision-and-Dialogue Navigation is one of the tasks that evaluate the agent's ability to interact with humans for as
sistance and navigate based on natural language responses. In this paper, we explore the Navigation from Dialogue History (NDH) task, which is based on the Cooperative Vision-and-Dialogue Navigation (CVDN) dataset, and present a state-of-the-art model which is built upon Vision-Language transformers. However, despite achieving competitive performance, we find that the agent in the NDH task is not evaluated appropriately by the primary metric -- Goal Progress. By analyzing the performance mismatch between Goal Progress and other metrics (e.g., normalized Dynamic Time Warping) from our state-of-the-art model, we show that NDH's sub-path based task setup (i.e., navigating partial trajectory based on its correspondent subset of the full dialogue) does not provide the agent with enough supervision signal towards the goal region. Therefore, we propose a new task setup called NDH-Full which takes the full dialogue and the whole navigation path as one instance. We present a strong baseline model and show initial results on this new task. We further describe several approaches that we try, in order to improve the model performance (based on curriculum learning, pre-training, and data-augmentation), suggesting potential useful training methods on this new NDH-Full task.
We seek to create agents that both act and communicate with other agents in pursuit of a goal. Towards this end, we extend LIGHT (Urbanek et al. 2019)---a large-scale crowd-sourced fantasy text-game---with a dataset of quests. These contain natural l
anguage motivations paired with in-game goals and human demonstrations; completing a quest might require dialogue or actions (or both). We introduce a reinforcement learning system that (1) incorporates large-scale language modeling-based and commonsense reasoning-based pre-training to imbue the agent with relevant priors; and (2) leverages a factorized action space of action commands and dialogue, balancing between the two. We conduct zero-shot evaluations using held-out human expert demonstrations, showing that our agents are able to act consistently and talk naturally with respect to their motivations.
Spoken language understanding (SLU) extracts the intended mean- ing from a user utterance and is a critical component of conversational virtual agents. In enterprise virtual agents (EVAs), language understanding is substantially challenging. First, t
he users are infrequent callers who are unfamiliar with the expectations of a pre-designed conversation flow. Second, the users are paying customers of an enterprise who demand a reliable, consistent and efficient user experience when resolving their issues. In this work, we describe a general and robust framework for intent and entity extraction utilizing a hybrid of statistical and rule-based approaches. Our framework includes confidence modeling that incorporates information from all components in the SLU pipeline, a critical addition for EVAs to en- sure accuracy. Our focus is on creating accurate and scalable SLU that can be deployed rapidly for a large class of EVA applications with little need for human intervention.
Conversational agents trained on large unlabeled corpora of human interactions will learn patterns and mimic behaviors therein, which include offensive or otherwise toxic behavior. We introduce a new human-and-model-in-the-loop framework for evaluati
ng the toxicity of such models, and compare a variety of existing methods in both the cases of non-adversarial and adversarial users that expose their weaknesses. We then go on to propose two novel methods for safe conversational agents, by either training on data from our new human-and-model-in-the-loop framework in a two-stage system, or ''baking-in'' safety to the generative model itself. We find our new techniques are (i) safer than existing models; while (ii) maintaining usability metrics such as engagingness relative to state-of-the-art chatbots. In contrast, we expose serious safety issues in existing standard systems like GPT2, DialoGPT, and BlenderBot.
In this paper we argue that embodied multimodal agents, i.e., avatars, can play an important role in moving natural language processing toward deep understanding.'' Fully-featured interactive agents, model encounters between two people,'' but a langu
age-only agent has little environmental and situational awareness. Multimodal agents bring new opportunities for interpreting visuals, locational information, gestures, etc., which are more axes along which to communicate. We propose that multimodal agents, by facilitating an embodied form of human-computer interaction, provide additional structure that can be used to train models that move NLP systems closer to genuine understanding'' of grounded language, and we discuss ongoing studies using existing systems.
The objective of the research is to determine the level of customer satisfaction with the performance of the members of the distribution channels in Joud Company for electrical household appliances according to the following characteristics: honesty,
responsibility, knowledge, skills, presentation and negotiation. Through conducting a field study through which a segment of the customers who are targeting the distribution outlets of the company were targeted. The sample of the study was a soft sample from the previous society. The sample consisted of (200) individual, distributed to the customers of the company, and 176 (complete questionnaire) were retrieved and valid for the statistical analysis , With a response rate of (88%). The questionnaire was designed from 31 words distributed on five axes that included the characteristics of the members of the distribution channels. The research reached a number of results, the most important of which is that the level of customer satisfaction with the performance of the members of the distribution channels regarding the level of honesty, responsibility, knowledge, skills, presentation and negotiation in Joud Company for household and electrical appliances is high.
The objective of the research is to determine the level of customer satisfaction with the
performance of the members of the distribution channels in Joud Company for electrical
household appliances according to the following characteristics: honest
y, responsibility,
knowledge, skills, presentation and negotiation. Through conducting a field study through
which a segment of the customers who are targeting the distribution outlets of the company
were targeted. The sample of the study was a soft sample from the previous society. The
sample consisted of (200) individual, distributed to the customers of the company, and 176
(complete questionnaire) were retrieved and valid for the statistical analysis , With a
response rate of (88%). The questionnaire was designed from 31 words distributed on five
axes that included the characteristics of the members of the distribution channels. The
research reached a number of results, the most important of which is that the level of
customer satisfaction with the performance of the members of the distribution channels
regarding the level of honesty, responsibility, knowledge, skills, presentation and
negotiation in Joud Company for household and electrical appliances is high.
In this study , a dyeing process of vat dyes was carried out for
cotton fabrics (100%) at an optimal conditions for material's
concentrations (sodium hydrosolphite , oxidization agent
,alkaline agent) to obtained a reference sample using for
comp
arison with another samples which dyeing at difference
concentrations of materials and different oxidization agent and
conditions of works ( work at close condition or open) , and it
was observed the decrease of fastness's values for the tester
samples against dry and wet rubbing opposite of reference
sample and that due to the difference of concentration of
reducing agent and the weakness of bonds between the dye
and textile because of the difference of oxidization conditions.
This research traces, after conducting a wide literature survey, the areas not covered by prominent agent oriented software engineering (AOSE) methodologies. Each methodology has its strength and weakness and focuses on some stages of software
devel
opment lifecycle but not all stages. This paper presents an addition to a well established AOSE methodology (MaSE). MaSE is considered one of the strongest in the field, it does not, however, support handling early requirements. This work integrates MaSE with another methodology known for its strength in early requirement representation. The integration implied the development of a wide set of translation rules between two different environments of notations and graphical representations. A software tool was developed to automate the translation and a case study is used to demonstrate the work.
