Building an open-domain conversational agent is a challenging problem. Current evaluation methods, mostly post-hoc judgments of static conversation, do not capture conversation quality in a realistic interactive context. In this paper, we investigate interactive human evaluation and provide evidence for its necessity; we then introduce a novel, model-agnostic, and dataset-agnostic method to approximate it. In particular, we propose a self-play scenario where the dialog system talks to itself and we calculate a combination of proxies such as sentiment and semantic coherence on the conversation trajectory. We show that this metric is capable of capturing the human-rated quality of a dialog model better than any automated metric known to-date, achieving a significant Pearson correlation (r .7,

Despite many years of research into latent Dirichlet allocation (LDA), applying LDA to collections of non-categorical items is still challenging for practitioners. Yet many problems with much richer data share a similar structure and could benefit from the vast literature on LDA. We propose logistic LDA, a novel discriminative variant of latent Dirichlet allocation which is easy to apply to arbitrary inputs. In particular, our model can easily be applied to groups of images, arbitrary text embeddings, or integrate deep neural networks. Although it is a discriminative model, we show that logistic LDA can learn from unlabeled data in an unsupervised manner by exploiting the group structure present in the data.

Attentional models are distinctly characterized by their ability to learn relative importance, i.e., assigning a different weight to input values. This paper proposes a new quasi-attention that is compositional in nature, i.e., learning whether to \textit{add}, \textit{subtract} or \textit{nullify} a certain vector when learning representations. This is strongly contrasted with vanilla attention, which simply re-weights input tokens. Our proposed \textit{Compositional De-Attention} (CoDA) is fundamentally built upon the intuition of both similarity and dissimilarity (negative affinity) when computing affinity scores, benefiting from a greater extent of expressiveness. We evaluate CoDA on six NLP tasks, i.e. open domain question answering, retrieval/ranking, natural language inference, machine translation, sentiment analysis and text2code generation.

Learning hidden topics in data streams has been paid a great deal of attention by researchers with a lot of proposed methods, but exploiting prior knowledge in general and a knowledge graph in particular has not been taken into adequate consideration in these methods. Prior knowledge that is derived from human knowledge (e.g. Wordnet) or a pre-trained model (e.g.Word2vec) is very valuable and useful to help topic models work better, especially on short texts. However, previous work often ignores this resource, or it can only utilize prior knowledge of a vector form in a simple way. In this paper, we propose a novel graph convolutional topic model (GCTM) which integrates graph convolutional networks (GCN) into a topic model and a learning method which learns the networks and the topic model simultaneously for data streams. In each minibatch, our method not only can exploit an external knowledge graph but also can balance between the external and old knowledge to perform well on new data. We conduct extensive experiments to evaluate our method with both human graph knowledge(Wordnet) and a graph built from pre-trained word embeddings (Word2vec). The experimental results show that our method achieves significantly better performances than the state-of-the-art baselines in terms of probabilistic predictive measure and topic coherence. In particular, our method can work well when dealing with short texts as well as concept drift. The implementation of GCTM is available at https://github.com/bachtranxuan/GCTM.git.

Aspect-based opinion mining is the task of identifying sentiment at the aspect level in opinionated text, which consists of two subtasks: aspect category extraction and sentiment polarity classification. While aspect category extraction aims to detect and categorize opinion targets such as product features, sentiment polarity classification assigns a sentiment label, i.e. positive, negative, or neutral, to each identified aspect. Supervised learning methods have been shown to deliver better accuracy for this task but they require labeled data, which is costly to obtain, especially for resource-poor languages like Vietnamese. To address this problem, we present a supervised aspect-based opinion mining method that utilizes labeled data from a foreign language (English in this case), which is translated to Vietnamese by an automated translation tool (Google Translate). Because aspects and opinions in different languages may be expressed by different words, we propose using word embeddings, in addition to other features, to reduce the vocabulary difference between the original and translated texts, thus improving the effectiveness of aspect category extraction and sentiment polarity classification processes. We also introduce an annotated corpus of aspect categories and sentiment polarities extracted from restaurant reviews in Vietnamese, and conduct a series of experiments on the corpus. Experimental results demonstrate the effectiveness of the proposed approach.

IBM is announcing several new IBM Watson technologies designed to help organizations begin identifying, understanding and analyzing some of the most challenging aspects of the English language with greater clarity, for greater insights. The new technologies represent the first commercialization of key Natural Language Processing (NLP) capabilities to come from IBM Research's Project Debater, the only AI system capable of debating humans on complex topics. For example, a new advanced sentiment analysis feature is defined to identify and analyze idioms and colloquialisms for the first time. Phrases, like'hardly helpful,' or'hot under the collar,' have been challenging for AI systems because they are difficult for algorithms to spot. With advanced sentiment analysis, businesses can begin analyzing such language data with Watson APIs for a more holistic understanding of their operation. Further, IBM is bringing technology from IBM Research for understanding business documents, such as PDF's and contracts, to also add to their AI models.

IBM is announcing several new IBM Watson technologies designed to help organizations begin identifying, understanding and analyzing some of the most challenging aspects of the English language with greater clarity, for greater insights. The new technologies represent the first commercialization of key Natural Language Processing (NLP) capabilities to come from IBM Research's Project Debater, the only AI system capable of debating humans on complex topics. For example, a new advanced sentiment analysis feature is defined to identify and analyze idioms and colloquialisms for the first time. Phrases, like'hardly helpful,' or'hot under the collar,' have been challenging for AI systems because they are difficult for algorithms to spot. With advanced sentiment analysis, businesses can begin analyzing such language data with Watson APIs for a more holistic understanding of their operation.

In natural language the intended meaning of a word or phrase is often implicit and depends on the context. In this work, we propose a simple yet effective method for sentiment analysis using contextual embeddings and a self-attention mechanism. The experimental results for three languages, including morphologically rich Polish and German, show that our model is comparable to or even outperforms state-of-the-art models. In all cases the superiority of models leveraging contextual embeddings is demonstrated. Finally, this work is intended as a step towards introducing a universal, multilingual sentiment classifier.

I made it with Max last night! OMG! Welcome to womanhood!! How was it/he? And right about now, Mary's mom gets a'notification' on her cell phone that her daughter is texting sexual references, then displays Mary's texts with Shelly upon mom's request. Mom spends the rest of the day at work fuming, conjuring dialog with her daughter for later that evening when they'll be home together. Never did, and she'd told Mary not to see him.

Task 1 of the DSTC8-track1 challenge aims to develop an end-to-end multi-domain dialogue system to accomplish complex users' goals under tourist information desk settings. This paper describes our submitted solution, Hierarchical Context Enhanced Dialogue System (HCEDS), for this task. The main motivation of our system is to comprehensively explore the potential of hierarchical context for sufficiently understanding complex dialogues. More specifically, we apply BERT to capture token-level information and employ the attention mechanism to capture sentence-level information. The results listed in the leaderboard show that our system achieves first place in automatic evaluation and the second place in human evaluation.