L'article, publie dans Science, sur une des premieres utilisations analytiques de Google Books, fondee sur les n-grammes (Google Ngrams) We constructed a corpus of digitized texts containing about 4% of all books ever printed. Analysis of this corpus enables us to investigate cultural trends quantitatively. We survey the vast terrain of "culturomics", focusing on linguistic and cultural phenomena that were reflected in the English language between 1800 and 2000. We show how this approach can ...

Quantitative Analysis of Culture Using Millions of Digitized Books

We present Meena, a multi-turn open-domain chatbot trained end-to-end on data mined and filtered from public domain social media conversations. This 2.6B parameter neural network is simply trained to minimize perplexity of the next token. We also propose a human evaluation metric called Sensibleness and Specificity Average (SSA), which captures key elements of a human-like multi-turn conversation. Our experiments show strong correlation between perplexity and SSA. The fact that the best perplexity end-to-end trained Meena scores high on SSA (72% on multi-turn evaluation) suggests that a human-level SSA of 86% is potentially within reach if we can better optimize perplexity. Additionally, the full version of Meena (with a filtering mechanism and tuned decoding) scores 79% SSA, 23% higher in absolute SSA than the existing chatbots we evaluated.

Towards a Human-like Open-Domain Chatbot

There is a growing interest in chatbots, which are machine agents serving as natural language user interfaces for data and service providers. However, no studies have empirically investigated people’s motivations for using chatbots. In this study, an online questionnaire asked chatbot users (N = 146, aged 16–55 years) from the US to report their reasons for using chatbots. The study identifies key motivational factors driving chatbot use. The most frequently reported motivational factor is “productivity”; chatbots help users to obtain timely and efficient assistance or information. Chatbot users also reported motivations pertaining to entertainment, social and relational factors, and curiosity about what they view as a novel phenomenon. The findings are discussed in terms of the uses and gratifications theory, and they provide insight into why people choose to interact with automated agents online. The findings can help developers facilitate better human–chatbot interaction experiences in the future. Possible design guidelines are suggested, reflecting different chatbot user motivations.

Why People Use Chatbots

In the shades of the uncanny valley: An experimental study of human–chatbot interaction

Communicating with customers through live chat interfaces has become an increasingly popular means to provide real-time customer service in many e-commerce settings. Today, human chat service agents are frequently replaced by conversational software agents or chatbots, which are systems designed to communicate with human users by means of natural language often based on artificial intelligence (AI). Though cost- and time-saving opportunities triggered a widespread implementation of AI-based chatbots, they still frequently fail to meet customer expectations, potentially resulting in users being less inclined to comply with requests made by the chatbot. Drawing on social response and commitment-consistency theory, we empirically examine through a randomized online experiment how verbal anthropomorphic design cues and the foot-in-the-door technique affect user request compliance. Our results demonstrate that both anthropomorphism as well as the need to stay consistent significantly increase the likelihood that users comply with a chatbot’s request for service feedback. Moreover, the results show that social presence mediates the effect of anthropomorphic design cues on user compliance.

/pdf/ai-based-chatbots-in-customer-service-and-their-effects-on-19rdjp46hh.pdf

AI-based chatbots in customer service and their effects on user compliance

Real conversations with artificial intelligence

In this paper, we propose a method of automatically generating multiple-choice fill-inthe-blank exercises from existing text passages that challenge a reader’s comprehension skills and contextual awareness. We use a unique application of word co-occurrence likelihoods and the Google n-grams corpus to select words with strong contextual links to their surrounding text, and to generate distractors that make sense only in an isolated narrow context and not in the full context of the passage. Results show that our method is successful at generating questions with distractors that are semantically consistent in a narrow context but inconsistent given the full text, with larger n-grams yielding significantly better results.

/pdf/automatic-generation-of-context-based-fill-in-the-blank-1c7ph15dxi.pdf

Automatic Generation of Context-Based Fill-in-the-Blank Exercises Using Co-occurrence Likelihoods and Google n-grams

In this paper, we discuss the design of CAPITAL Words, an educational Android application to help low-literacy adults improve their phonemic awareness. We discuss our design choices concerning iconography, linearity, consistency, robustness, interactivity, and visibility when creating mobile software usable by illiterate users. We conducted a usability study with 11 adult learners at a local literacy center to determine how successfully users are able to interact with our interface. Results show that the majority of our design choices were intuitive for low-literacy adults with prior smartphone experience and highly learnable for inexperienced users, and that users overwhelmingly enjoyed using the app as a learning tool. This suggests that, if users are given a small amount of guidance initially, there is a high likelihood that they will be both willing and able to continue using our app independently to improve their literacy skills.

Designing a Literacy-Based Mobile Application for Adult Learners

of Dissertation ................................................................................................... iv Table of

Jennifer Hill

Papers

Real conversations with artificial intelligence

Automatic Generation of Context-Based Fill-in-the-Blank Exercises Using Co-occurrence Likelihoods and Google n-grams

Designing a Literacy-Based Mobile Application for Adult Learners

Algorithmic Generation and Mobile Distribution of Phonetic, Orthographic, and Inference-Based Literacy Exercises for Adult Learners.