Search

Natural language interfaces have become a common part of modern digital life. Chatbots utilize text-based conversations to communicate with users; personal assistants on smartphones such as Google Assistant take direct speech commands from their users; and speech-controlled devices such as Amazon Echo use voice as their only input mode. In this paper, we introduce InstructableCrowd, a crowd-powered system that allows users to program their devices via conversation. The user verbally expresses a problem to the system, in which a group of crowd workers collectively respond and program relevant multi-part IF-THEN rules to help the user. The IF-THEN rules generated by InstructableCrowd connect relevant sensor combinations (e.g., location, weather, device acceleration, etc.) to useful effectors (e.g., text messages, device alarms, etc.). Our study showed that non-programmers can use the conversational interface of InstructableCrowd to create IF-THEN rules that have similar quality compared with the rules created manually. InstructableCrowd generally illustrates how users may converse with their devices, not only to trigger simple voice commands, but also to personalize their increasingly powerful and complicated devices., Comment: Published at Human Computation (2019) 6:1:113-146

This paper introduces semantic frame forecast, a task that predicts the semantic frames that will occur in the next 10, 100, or even 1,000 sentences in a running story. Prior work focused on predicting the immediate future of a story, such as one to a few sentences ahead. However, when novelists write long stories, generating a few sentences is not enough to help them gain high-level insight to develop the follow-up story. In this paper, we formulate a long story as a sequence of "story blocks," where each block contains a fixed number of sentences (e.g., 10, 100, or 200). This formulation allows us to predict the follow-up story arc beyond the scope of a few sentences. We represent a story block using the term frequencies (TF) of semantic frames in it, normalized by each frame's inverse document frequency (IDF). We conduct semantic frame forecast experiments on 4,794 books from the Bookcorpus and 7,962 scientific abstracts from CODA-19, with block sizes ranging from 5 to 1,000 sentences. The results show that automated models can forecast the follow-up story blocks better than the random, prior, and replay baselines, indicating the task's feasibility. We also learn that the models using the frame representation as features outperform all the existing approaches when the block size is over 150 sentences. The human evaluation also shows that the proposed frame representation, when visualized as word clouds, is comprehensible, representative, and specific to humans. Our code is available at https://github.com/appleternity/FrameForecasting., Comment: 9 pages, NAACL 2021

Many English-as-a-second language learners have trouble using near-synonym words (e.g., small vs.little; briefly vs.shortly) correctly, and often look for example sentences to learn how two nearly synonymous terms differ. Prior work uses hand-crafted scores to recommend sentences but has difficulty in adopting such scores to all the near-synonyms as near-synonyms differ in various ways. We notice that the helpfulness of the learning material would reflect on the learners' performance. Thus, we propose the inference-based learner-like agent to mimic learner behavior and identify good learning materials by examining the agent's performance. To enable the agent to behave like a learner, we leverage entailment modeling's capability of inferring answers from the provided materials. Experimental results show that the proposed agent is equipped with good learner-like behavior to achieve the best performance in both fill-in-the-blank (FITB) and good example sentence selection tasks. We further conduct a classroom user study with college ESL learners. The results of the user study show that the proposed agent can find out example sentences that help students learn more easily and efficiently. Compared to other models, the proposed agent improves the score of more than 17% of students after learning., Comment: 9 pages, to appear in EMNLP 2020 as a long paper

Stories are diverse and highly personalized, resulting in a large possible output space for story generation. Existing end-to-end approaches produce monotonous stories because they are limited to the vocabulary and knowledge in a single training dataset. This paper introduces KG-Story, a three-stage framework that allows the story generation model to take advantage of external Knowledge Graphs to produce interesting stories. KG-Story distills a set of representative words from the input prompts, enriches the word set by using external knowledge graphs, and finally generates stories based on the enriched word set. This distill-enrich-generate framework allows the use of external resources not only for the enrichment phase, but also for the distillation and generation phases. In this paper, we show the superiority of KG-Story for visual storytelling, where the input prompt is a sequence of five photos and the output is a short story. Per the human ranking evaluation, stories generated by KG-Story are on average ranked better than that of the state-of-the-art systems. Our code and output stories are available at https://github.com/zychen423/KE-VIST., AAAI 2020

In this paper, we introduce Dixit, an interactive visual storytelling system that the user interacts with iteratively to compose a short story for a photo sequence. The user initiates the process by uploading a sequence of photos. Dixit first extracts text terms from each photo which describe the objects (e.g., boy, bike) or actions (e.g., sleep) in the photo, and then allows the user to add new terms or remove existing terms. Dixit then generates a short story based on these terms. Behind the scenes, Dixit uses an LSTM-based model trained on image caption data and FrameNet to distill terms from each image and utilizes a transformer decoder to compose a context-coherent story. Users change images or terms iteratively with Dixit to create the most ideal story. Dixit also allows users to manually edit and rate stories. The proposed procedure opens up possibilities for interpretable and controllable visual storytelling, allowing users to understand the story formation rationale and to intervene in the generation process., WWW'19 Demo, demo video: https://www.youtube.com/watch?v=CUu1MOwnveI

A significant body of research in Artificial Intelligence (AI) has focused on generating stories automatically, either based on prior story plots or input images. However, literature has little to say about how users would receive and use these stories. Given the quality of stories generated by modern AI algorithms, users will nearly inevitably have to edit these stories before putting them to real use. In this paper, we present the first analysis of how human users edit machine-generated stories. We obtained 962 short stories generated by one of the state-of-the-art visual storytelling models. For each story, we recruited five crowd workers from Amazon Mechanical Turk to edit it. Our analysis of these edits shows that, on average, users (i) slightly shortened machine-generated stories, (ii) increased lexical diversity in these stories, and (iii) often replaced nouns and their determiners/articles with pronouns. Our study provides a better understanding on how users receive and edit machine-generated stories,informing future researchers to create more usable and helpful story generation systems., To appear in CHI'19 Late-Breaking Work on Human Factors in Computing Systems (CHI LBW 2019), 2019

We introduce the first dataset for human edits of machine-generated visual stories and explore how these collected edits may be used for the visual story post-editing task. The dataset, VIST-Edit, includes 14,905 human edited versions of 2,981 machine-generated visual stories. The stories were generated by two state-of-the-art visual storytelling models, each aligned to 5 human-edited versions. We establish baselines for the task, showing how a relatively small set of human edits can be leveraged to boost the performance of large visual storytelling models. We also discuss the weak correlation between automatic evaluation scores and human ratings, motivating the need for new automatic metrics., Comment: Accepted by ACL 2019

Urban air pollution has been linked to various human health considerations, including cardiopulmonary diseases. Communities who suffer from poor air quality often rely on experts to identify pollution sources due to the lack of accessible tools. Taking this into account, we developed Smell Pittsburgh, a system that enables community members to report odors and track where these odors are frequently concentrated. All smell report data are publicly accessible online. These reports are also sent to the local health department and visualized on a map along with air quality data from monitoring stations. This visualization provides a comprehensive overview of the local pollution landscape. Additionally, with these reports and air quality data, we developed a model to predict upcoming smell events and send push notifications to inform communities. Our evaluation of this system demonstrates that engaging residents in documenting their experiences with pollution odors can help identify local air pollution patterns, and can empower communities to advocate for better air quality., Accepted by ACM IUI 2019 conference, with error corrections

Crowd-powered conversational assistants have found to be more robust than automated systems, but do so at the cost of higher response latency and monetary costs. One promising direction is to combined the two approaches for high quality and low cost solutions. However, traditional offline approaches of building automated systems with the crowd requires first collecting training data from the crowd, and then training a model before an online system can be launched. In this paper, we introduce Evorus, a crowd-powered conversational assistant with online-learning capability that automate itself over time. Evorus expands a previous crowd-powered conversation system by reducing its reliance on the crowd over time while maintaining the robustness and reliability of human intelligence, by (i) allowing new chatbots to be added to help contribute possible answers, (ii) learning to reuse past responses to similar queries over time, and (iii) learning to reduce the amount of crowd oversight necessary to retain quality. Our deployment study with 28 users show that automated responses were chosen 12.84% of the time, and voting cost was reduced by 6%. Evorus introduced a new framework for constructing crowd-powered conversation systems that can gradually automate themselves using machine learning, a concept that we believe can be generalize to other types of crowd-powered systems for future research.

Smart devices connected to the Internet are proliferating.To reduce costs of devices that havetraditionally been inexpensive(toasters, microwaves, printers, etc), manyof these devices have chosen to use a speech interface rather than a visual one. This transition has been hastened by the increasing capabilities of speech interfaces,exemplifiedbyproducts likeAmazon Echo and Apple'sSiri.A consequence of these products moving to voice control is that people who are deaf and hard of hearing (DHH) may be unable to use them. In this paper, we briefly introduce two technical approaches we are pursuingfor enabling DHH people to provide input to these devices: (i) human computationworkflows for understanding "deaf speech," and (ii) mobile interfaces that can be instructed to speak on the user's behalf.

We present MoodSwipe, a soft keyboard that suggests text messages given the user-specified emotions utilizing the real dialog data. The aim of MoodSwipe is to create a convenient user interface to enjoy the technology of emotion classification and text suggestion, and at the same time to collect labeled data automatically for developing more advanced technologies. While users select the MoodSwipe keyboard, they can type as usual but sense the emotion conveyed by their text and receive suggestions for their message as a benefit. In MoodSwipe, the detected emotions serve as the medium for suggested texts, where viewing the latter is the incentive to correcting the former. We conduct several experiments to show the superiority of the emotion classification models trained on the dialog data, and further to verify good emotion cues are important context for text suggestion.

In this paper, the brief reviews of the significance of the myelin thickness to various root courses of the diseases for a human being, and the similarities between the human and the lab mouse being researched extensively so far are presented. Once we establish the necessity for a biological statistical analysis of the myelin thickness with regard to the particular category of the brain cell, we can then develop a mixed algorithm based on the watershed principle and the binaryzation principle that can be used to automatically process the scanning electron microscope pictures in batches. The initial analysis does indicate that the mixed method improved efficiency of data processing while not overlooking some important medical diagnostic factors.

In this paper, we introduce InstructableCrowd, a system that allows end-users to instruct the crowd to create trigger-action ("if, then") rules based on their needs. We create a framework which enables users to converse with the crowd using their phone and describe a problem which they might have. We create an interface for a crowd worker to both chat with the user and compose a rule with an "IF" part connected to the user's phone sensors (e.g. incoming emails, GPS location, meeting calendar, weather information etc.), and a "THEN" part connected to user's phone effectors (e.g. sending an email, creating an alarm, posting a tweet, etc.). The system then sends the rules created by the crowd to the user's phone in order to help the user solve his problem.

We introduce the first dataset for sequential vision-to-language, and explore how this data may be used for the task of visual storytelling. The first release of this dataset, SIND1 v.1, includes 81,743 unique photos in 20,211 sequences, aligned to both descriptive (caption) and story language. We establish several strong baselines for the storytelling task, and motivate an automatic metric to benchmark progress. Modelling concrete description as well as figurative and social language, as provided in this dataset and the storytelling task, has the potential to move artificial intelligence from basic understandings of typical visual scenes towards more and more human-like understanding of grounded event structure and subjective expression.