Zero-shot Dialogue State Tracking (DST) addresses the challenge of acquiring and annotating task-oriented dialogues, which can be time-consuming and costly. However, DST extends beyond simple slot-filling and requires effective updating strategies for tracking dialogue state as conversations progress. In this paper, we propose ParsingDST, a new In-Context Learning (ICL) method, to introduce additional intricate updating strategies in zero-shot DST. Our approach reformulates the DST task by leveraging powerful Large Language Models (LLMs) and translating the original dialogue text to JSON through semantic parsing as an intermediate state. We also design a novel framework that includes more modules to ensure the effectiveness of updating strategies in the text-to-JSON process. Experimental results demonstrate that our approach outperforms existing zero-shot DST methods on MultiWOZ, exhibiting significant improvements in Joint Goal Accuracy (JGA) and slot accuracy compared to existing ICL methods. Our code has been released.

Welcome to the world of intelligent chatbots: your companion and conversation agents who should make your life smarter. A leading research paper even said that by 2020, the average person would have more conversations with bots than with their spouse. So, be ready to embrace this new life in a year from now. Have you ever tried telling Siri or Google to "find restaurants that don't serve pizza?" At least they are both consistent in that they gave the same answer -- suggesting restaurants that do serve pizza. The first citizen humanoid robot, Sofia, is making her way to every media event, conducting interviews using human-like conversations. How does she compare to these competitors? Well, the truth is far from reality.

In this paper, we implement an optical fiber communication system as an end-to-end deep neural network, including the complete chain of transmitter, channel model, and receiver. This approach enables the optimization of the transceiver in a single end-to-end process. We illustrate the benefits of this method by applying it to intensity modulation/direct detection (IM/DD) systems and show that we can achieve bit error rates below the 6.7\% hard-decision forward error correction (HD-FEC) threshold. We model all componentry of the transmitter and receiver, as well as the fiber channel, and apply deep learning to find transmitter and receiver configurations minimizing the symbol error rate. We propose and verify in simulations a training method that yields robust and flexible transceivers that allow---without reconfiguration---reliable transmission over a large range of link dispersions. The results from end-to-end deep learning are successfully verified for the first time in an experiment. In particular, we achieve information rates of 42\,Gb/s below the HD-FEC threshold at distances beyond 40\,km. We find that our results outperform conventional IM/DD solutions based on 2 and 4 level pulse amplitude modulation (PAM2/PAM4) with feedforward equalization (FFE) at the receiver. Our study is the first step towards end-to-end deep learning-based optimization of optical fiber communication systems.

CakeChat is a dialog system that is able to express emotions in a text conversation. It is written in Theano and Lasagne. It uses end-to-end trained embeddings of 5 different emotions to generate responses conditioned by a given emotion. The code is flexible and allows to condition a response by an arbitrary categorical variable defined for some samples in the training data. With CakeChat you can, for example, train your own persona-based neural conversational model[5] or create an emotional chatting machine without external memory[4].

Slack is a popular messaging app that brings communication together in one place. It provides the abilities for messaging, archiving, and searching for teams, while organizing conversations into channels. The names of channels are often not sufficiently informative to understand which topics are relevant to a given channel. Veterans just know; newbies struggle. This blog post introduces Slack Maestro, a bot that learns the topics of different channels, monitors conversations, and warns users when they go off topic.

We consider incorporating topic information into a sequence-to-sequence framework to generate informative and interesting responses for chatbots. To this end, we propose a topic aware sequence-to-sequence (TA-Seq2Seq) model. The model utilizes topics to simulate prior human knowledge that guides them to form informative and interesting responses in conversation, and leverages topic information in generation by a joint attention mechanism and a biased generation probability. The joint attention mechanism summarizes the hidden vectors of an input message as context vectors by message attention and synthesizes topic vectors by topic attention from the topic words of the message obtained from a pre-trained LDA model, with these vectors jointly affecting the generation of words in decoding. To increase the possibility of topic words appearing in responses, the model modifies the generation probability of topic words by adding an extra probability item to bias the overall distribution. Empirical studies on both automatic evaluation metrics and human annotations show that TA-Seq2Seq can generate more informative and interesting responses, significantly outperforming state-of-the-art response generation models.

During the past year, a prototype expert system for tactical data fusion has been under development,. This computer program combines various messages concerning electronic intelligence (ELINT) to aid in decision making concerning enemy actions and intentions. The prototype system is written in Prolog, a language that has proved to be very powerful and easy to use for problem /rule development. The resulting prototype system (called EXPRS-Expert Prolog System) uses English-like rule constructs of Prolog code. This approach enables the system to generate answers automatically to "why" a ruled fired, and "how" that rule fired. In addition, a rule clause construct is provided which allows direct access to Prolog code routines. This paper describes the structure of the rules used and provides typical user interactions.