Existing simulations designed for cultural and interpersonal skill training rely on pre-defined responses with a menu option selection interface. Using a multiple-choice interface and restricting trainees' responses may limit the trainees' ability to apply the lessons in real life situations. This systems also uses a simplistic evaluation model, where trainees' selected options are marked as either correct or incorrect. This model may not capture sufficient information that could drive an adaptive feedback mechanism to improve trainees' cultural awareness. This paper describes the design of a dialogue-based simulation for cultural awareness training. The simulation, built around a disaster management scenario involving a joint coalition between the US and the Chinese armies. Trainees were able to engage in realistic dialogue with the Chinese agent. Their responses, at different points, get evaluated by different multi-label classification models. Based on training on our dataset, the models score the trainees' responses for cultural awareness in the Chinese culture. Trainees also get feedback that informs the cultural appropriateness of their responses. The result of this work showed the following; i) A feature-based evaluation model improves the design, modeling and computation of dialogue-based training simulation systems; ii) Output from current automatic speech recognition (ASR) systems gave comparable end results compared with the output from manual transcription; iii) A multi-label classification model trained as a cultural expert gave results which were comparable with scores assigned by human annotators.

Aspect-Based Sentiment Analysis (ABSA) deals with the extraction of sentiments and their targets. Collecting labeled data for this task in order to help neural networks generalize better can be laborious and time-consuming. As an alternative, similar data to the real-world examples can be produced artificially through an adversarial process which is carried out in the embedding space. Although these examples are not real sentences, they have been shown to act as a regularization method which can make neural networks more robust. In this work, we apply adversarial training, which was put forward by Goodfellow et al. (2014), to the post-trained BERT (BERT-PT) language model proposed by Xu et al. (2019) on the two major tasks of Aspect Extraction and Aspect Sentiment Classification in sentiment analysis. After improving the results of post-trained BERT by an ablation study, we propose a novel architecture called BERT Adversarial Training (BAT) to utilize adversarial training in ABSA. The proposed model outperforms post-trained BERT in both tasks. To the best of our knowledge, this is the first study on the application of adversarial training in ABSA.

Learning suitable and well-performing dialogue behaviour in statistical spoken dialogue systems has been in the focus of research for many years. While most work which is based on reinforcement learning employs an objective measure like task success for modelling the reward signal, we use a reward based on user satisfaction estimation. We propose a novel estimator and show that it outperforms all previous estimators while learning temporal dependencies implicitly. Furthermore, we apply this novel user satisfaction estimation model live in simulated experiments where the satisfaction estimation model is trained on one domain and applied in many other domains which cover a similar task. We show that applying this model results in higher estimated satisfaction, similar task success rates and a higher robustness to noise.

Certain type of documents such as tweets are collected by specifying a set of keywords. As topics of interest change with time it is beneficial to adjust keywords dynamically. The challenge is that these need to be specified ahead of knowing the forthcoming documents and the underlying topics. The future topics should mimic past topics of interest yet there should be some novelty in them. We develop a keyword-based topic model that dynamically selects a subset of keywords to be used to collect future documents. The generative process first selects keywords and then the underlying documents based on the specified keywords. The model is trained by using a variational lower bound and stochastic gradient optimization. The inference consists of finding a subset of keywords where given a subset the model predicts the underlying topic-word matrix for the unknown forthcoming documents. We compare the keyword topic model against a benchmark model using viral predictions of tweets combined with a topic model. The keyword-based topic model outperforms this sophisticated baseline model by 67%.

Topic models have become popular tools for dimension reduction and exploratory analysis of text data which consists in observed frequencies of a vocabulary of $p$ words in $n$ documents, stored in a $p\times n$ matrix. The main premise is that the mean of this data matrix can be factorized into a product of two non-negative matrices: a $p\times K$ word-topic matrix $A$ and a $K\times n$ topic-document matrix $W$. This paper studies the estimation of $A$ that is possibly element-wise sparse, and the number of topics $K$ is unknown. In this under-explored context, we derive a new minimax lower bound for the estimation of such $A$ and propose a new computationally efficient algorithm for its recovery. We derive a finite sample upper bound for our estimator, and show that it matches the minimax lower bound in many scenarios. Our estimate adapts to the unknown sparsity of $A$ and our analysis is valid for any finite $n$, $p$, $K$ and document lengths. Empirical results on both synthetic data and semi-synthetic data show that our proposed estimator is a strong competitor of the existing state-of-the-art algorithms for both non-sparse $A$ and sparse $A$, and has superior performance is many scenarios of interest.

In such systems the dialogue state tracker (DST) is a core component, aimed to maintain a distribution over the dialogue states based on the dialogue history. A dialogue state at any turn t in the dialogue is typically represented as a set of slot-value pairs, such as ( price, moderate) or ( food, italian) in the context of restaurant reservation. The goal of the DST is to determine the user's intent and the user's goal during the dialogue and represent them as such slot-value pairs. The downstream components of a dialogue system (e.g the dialogue manager) that are responsible to choose the next system action, rely on an accurate DST for an effective dialogue strategy. Because of the importance of DST in dialogue systems, their development attracted lots of research both in academia and industry. Typical dialogue systems are modeled for a fixed ontology consisting of a single domain (Mrk ˇ si c et al. 2017; Zhong, Xiong, and Socher 2018; Ren et al. 2018), and the domain ontology schema defines intents, slots and values for each slot of the domain.

Code-mixing is the practice of alternating between two or more languages. Mostly observed in multilingual societies, its occurrence is increasing and therefore its importance. A major part of sentiment analysis research has been monolingual, and most of them perform poorly on code-mixed text. In this work, we introduce methods that use different kinds of multilingual and cross-lingual embeddings to efficiently transfer knowledge from monolingual text to code-mixed text for sentiment analysis of code-mixed text. Our methods can handle code-mixed text through a zero-shot learning. Our methods beat state-of-the-art on English-Spanish code-mixed sentiment analysis by absolute 3\% F1-score. We are able to achieve 0.58 F1-score (without parallel corpus) and 0.62 F1-score (with parallel corpus) on the same benchmark in a zero-shot way as compared to 0.68 F1-score in supervised settings. Our code is publicly available.

Conversational AI is becoming an integral part of business practice across industries. More companies are adopting the advantages chatbots bring to customer service, sales, and marketing. Even though chatbots are becoming a "must-have" asset for leading businesses, their performance is still very far from human. Researchers from major research institutions and tech leaders have explored ways to boost the performance of dialog systems by increasing the diversity of their responses, enabling emotion recognition, improving their ability to track long-term aspects of the conversation, ensuring the maintenance of a consistent persona, etc. We've searched through important conversational AI research papers published in 2019 to present you the top 10 that set the new state-of-the-art in both task-oriented and open-domain dialog systems. Subscribe to our AI Research mailing list at the bottom of this article to be alerted when we release new summaries.

As the field of Spoken Dialogue Systems and Conversational AI grows, so does the need for tools and environments that abstract away implementation details in order to expedite the development process, lower the barrier of entry to the field, and offer a common test-bed for new ideas. In this paper, we present Plato, a flexible Conversational AI platform written in Python that supports any kind of conversational agent architecture, from standard architectures to architectures with jointly-trained components, single- or multi-party interactions, and offline or online training of any conversational agent component. Plato has been designed to be easy to understand and debug and is agnostic to the underlying learning frameworks that train each component.

How do you test an application which constantly listens to the customers, learns their behaviour and create personalised engagements based out of learnings!! Today data plays a vital role in every decision making and hence making sense of the data to derive useful insights for our customers is a key for success. Sentiment Analysis is the process of classifying the data into positive, negative or neutral implemented using natural language processing (NLP) and Machine Learning techniques that helps in analysing the data to gauge public opinion, market research, monitor brand and product reputation, and understand customer experiences and is mostly offered as Sentiment Analysis as-a-Service . In this talk we will discuss the Challenges are around analysing, explicit and implict opinions, sarcasm, comparative opinions, Multilingual, Emojis, defination on neutral to just name a few and the strategies to test such applications with a use case on Airlines Sentiment (trained with tweets about airlines to identify between positive, neutral, and negative tweets).