Natural language processing (NLP) is one of the biggest fields of AI development. Numerous NLP solutions like chatbots, automatic speech recognition, and sentiment analysis programs can improve efficiency and productivity in various businesses around the world. 

With all the mass reach social media has these days, the power that comes with riding on its wave is simply hard to deny. With thousands of posts and tweets, there is seemingly no end to the chatter. But it is important to know if all that chatter is in favor of or against your agendas. Imagine launching a product that has become the talk of the town. But is all that talk good or bad?

This paper is concerned with dialogue state tracking (DST) in a task-oriented dialogue system. Significant progress has been achieved recently on the development of DST technologies. However, building a DST module that is scalable and effective is still a challenging issue. This paper proposes a new approach to dialogue state tracking, referred to as Seq2Seq-DU, which formalizes DST as a sequence-to-sequence problem. It employs two BERT-based encoders to respectively encode the utterances in the dialogue and the descriptions of schemas, an attender to calculate attentions between the utterance embeddings and the schema embeddings, and a decoder to generate pointers to represent the current state of dialogue. Seq2Seq-DU has the following advantages. It can jointly model the relations between intents, slots, and slot values; it can utilize rich language representations of utterances and schemas; it can effectively deal with categorical slots, non-categorical slots, and unseen schemas. In addition, Seq2Seq-DU can also be used in the NLU (natural language understanding) module of a dialogue system. Experimental results on benchmark datasets in different settings (SGD, MultiWOZ2.2, WOZ2.0, DSTC2, M2M, SNIPS, and ATIS) show that Seq2Seq-DU outperforms the existing methods.

We present a new approach to dialogue specification for Virtual Personal Assistants (VPAs) based on so-called dialogue workflow graphs, with several demonstrated advantages over current ontology-based methods. Our new dialogue specification language (DSL) enables customers to more easily participate in the VPA modeling process due to a user-friendly modeling framework. Resulting models are also significantly more compact. VPAs can be developed much more rapidly. The DSL is a new modeling layer on top of our ontology-based Dialogue Management (DM) framework OntoVPA. We explain the rationale and benefits behind the new language and support our claims with concrete reduced Level-of-Effort (LOE) numbers from two recent OntoVPA projects.

Goal-oriented dialog systems enable users to complete specific goals like requesting information about a movie or booking a ticket. Typically the dialog system pipeline contains multiple ML models, including natural language understanding, state tracking and action prediction (policy learning). These models are trained through a combination of supervised or reinforcement learning methods and therefore require collection of labeled domain specific datasets. However, collecting annotated datasets with language and dialog-flow variations is expensive, time-consuming and scales poorly due to human involvement. In this paper, we propose an approach for automatically creating a large corpus of annotated dialogs from a few thoroughly annotated sample dialogs and the dialog schema. Our approach includes a novel goal-sampling technique for sampling plausible user goals and a dialog simulation technique that uses heuristic interplay between the user and the system (Alexa), where the user tries to achieve the sampled goal. We validate our approach by generating data and training three different downstream conversational ML models. We achieve 18 ? 50% relative accuracy improvements on a held-out test set compared to a baseline dialog generation approach that only samples natural language and entity value variations from existing catalogs but does not generate any novel dialog flow variations. We also qualitatively establish that the proposed approach is better than the baseline. Moreover, several different conversational experiences have been built using this method, which enables customers to have a wide variety of conversations with Alexa.

Training a multimodal network is challenging and it requires complex architectures to achieve reasonable performance. We show that one reason for this phenomena is the difference between the convergence rate of various modalities. We address this by pre-training modality-specific sub-networks in multimodal architectures independently before end-to-end training of the entire network. Furthermore, we show that the addition of an attention mechanism between sub-networks after pre-training helps identify the most important modality during ambiguous scenarios boosting the performance. We demonstrate that by performing these two tricks a simple network can achieve similar performance to a complicated architecture that is significantly more expensive to train on multiple tasks including sentiment analysis, emotion recognition, and speaker trait recognition.

In "How to Make a Racist AI Without Really Trying," Robyn Speer shows how to build a simple sentiment analysis system, using standard, well-known sources for word embeddings (GloVe and word2vec), and a widely used sentiment lexicon. Her program assigns "negative" sentiment to names and phrases associated with minorities, and "positive" sentiment to names and phrases associated with Europeans. Even a sentence like "Let's go get Mexican food" gets a much lower sentiment score than "Let's go get Italian food." That result isn't surprising, nor are Speer's conclusions: if you take a simplistic approach to sentiment analysis, you shouldn't be surprised when you get a program that embodies racist, discriminatory values. It's possible to minimize algorithmic racism (though possibly not eliminate it entirely), and Speer discusses several strategies for doing so.

We introduce PerSenT, a dataset of crowd-sourced annotations of the sentiment expressed by the authors towards the main entities in news articles. The dataset also includes paragraph-level sentiment annotations to provide more fine-grained supervision for the task. Our benchmarks of multiple strong baselines show that this is a difficult classification task. The results also suggest that simply fine-tuning document-level representations from BERT isn't adequate for this task. Making paragraph-level decisions and aggregating them over the entire document is also ineffective. We present empirical and qualitative analyses that illustrate the specific challenges posed by this dataset. We release this dataset with 5.3k documents and 38k paragraphs covering 3.2k unique entities as a challenge in entity sentiment analysis.

In the field of social media data analytics, one popular area of research is the sentiment analysis of twitter data. Twitter is one of the most popular social media platforms in the world, with 330 million monthly active users and 500 million tweets sent each day. By carefully analyzing the sentiment of these tweets--whether they are positive, negative, or neutral, for example--we can learn a lot about how people feel about certain topics. Understanding the sentiment of tweets is important for a variety of reasons: business marketing, politics, public behavior analysis, and information gathering are just a few examples. Sentiment analysis of twitter data can help marketers understand the customer response to product launches and marketing campaigns, and it can also help political parties understand the public response to policy changes or announcements.

With robotics rapidly advancing, more effective human-robot interaction is increasingly needed to realize the full potential of robots for society. While spoken language must be part of the solution, our ability to provide spoken language interaction capabilities is still very limited. The National Science Foundation accordingly convened a workshop, bringing together speech, language, and robotics researchers to discuss what needs to be done. The result is this report, in which we identify key scientific and engineering advances needed. Our recommendations broadly relate to eight general themes. First, meeting human needs requires addressing new challenges in speech technology and user experience design. Second, this requires better models of the social and interactive aspects of language use. Third, for robustness, robots need higher-bandwidth communication with users and better handling of uncertainty, including simultaneous consideration of multiple hypotheses and goals. Fourth, more powerful adaptation methods are needed, to enable robots to communicate in new environments, for new tasks, and with diverse user populations, without extensive re-engineering or the collection of massive training data. Fifth, since robots are embodied, speech should function together with other communication modalities, such as gaze, gesture, posture, and motion. Sixth, since robots operate in complex environments, speech components need access to rich yet efficient representations of what the robot knows about objects, locations, noise sources, the user, and other humans. Seventh, since robots operate in real time, their speech and language processing components must also. Eighth, in addition to more research, we need more work on infrastructure and resources, including shareable software modules and internal interfaces, inexpensive hardware, baseline systems, and diverse corpora.