Jacob Eisenstein

Applying model-based techniques to the development of UIs for mobile computers

Mobile computing poses a series of unique challenges for user interface design and development: user interfaces must now accommodate the capabilities of various access devices and be suitable for different contexts of use, while preserving consistency and usability. We propose a set of techniques that will aid UI designers who are working in the domain of mobile computing. These techniques will allow designers to build UIs across several platforms, while respecting the unique constraints posed by each platform. In addition, these techniques will help designers to recognize and accommodate the unique contexts in which mobile computing occurs. Central to our approach is the development of a user-interface model that serves to isolate those features that are common to the various contexts of use, and to specify how the user-interface should adjust when the context changes. We claim that without some abstract description of the UI, it is likely that the design and the development of user-interfaces for mobile computing will be very time consuming, error-prone or even doomed to failure.

Towards a general computational framework for model-based interface development systems

Abstract Model-based interface development systems have not been able to progress beyond producing narrowly focused interface designs of restricted applicability. We identify a level-of-abstraction mismatch in interface models, which we call the mapping problem, as the cause of the limitations in the usefulness of model-based systems. We propose a general computational framework for solving the mapping problem in model-based systems. We show an implementation of the framework within the MOBI-D (Model-Based Interface Designer) interface development environment. The MOBI-D approach to solving the mapping problem enables for the first time with model-based technology the design of a wide variety of types of user interfaces.

XIML: a common representation for interaction data

We introduce XIML (eXtensible Interface Markup Language), a proposed common representation for interaction data. We claim that XIML fulfills the requirements that we have found essential for a language of its type: (1) it supports design, operation, organization, and evaluation functions, (2) it is able to relate the abstract and concrete data elements of an interface, and (3) it enables knowledge-based systems to exploit the captured data.

Bayesian Unsupervised Topic Segmentation

This paper describes a novel Bayesian approach to unsupervised topic segmentation. Unsupervised systems for this task are driven by lexical cohesion: the tendency of well-formed segments to induce a compact and consistent lexical distribution. We show that lexical cohesion can be placed in a Bayesian context by modeling the words in each topic segment as draws from a multinomial language model associated with the segment; maximizing the observation likelihood in such a model yields a lexically-cohesive segmentation. This contrasts with previous approaches, which relied on hand-crafted cohesion metrics. The Bayesian framework provides a principled way to incorporate additional features such as cue phrases, a powerful indicator of discourse structure that has not been previously used in unsupervised segmentation systems. Our model yields consistent improvements over an array of state-of-the-art systems on both text and speech datasets. We also show that both an entropy-based analysis and a well-known previous technique can be derived as special cases of the Bayesian framework.

Gender identity and lexical variation in social media

We present a study of the relationship between gender, linguistic style, and social networks, using a novel corpus of 14,000 Twitter users. Prior quantitative work on gender often treats this social variable as a female/male binary; we argue for a more nuanced approach. By clustering Twitter users, we find a natural decomposition of the dataset into various styles and topical interests. Many clusters have strong gender orientations, but their use of linguistic resources sometimes directly conflicts with the population-level language statistics. We view these clusters as a more accurate reflection of the multifaceted nature of gendered language styles. Previous corpus-based work has also had little to say about individuals whose linguistic styles defy population-level gender patterns. To identify such individuals, we train a statistical classifier, and measure the classifier confidence for each individual in the dataset. Examining individuals whose language does not match the classifiers model for their gender, we find that they have social networks that include significantly fewer same-gender social connections and that, in general, social network homophily is correlated with the use of same-gender language markers. Pairing computational methods and social theory thus offers a new perspective on how gender emerges as individuals position themselves relative to audiences, topics, and mainstream gender norms.

Adapting to mobile contexts with user-interface modeling

Mobile computing offers the possibility of dramatically expanding the versatility of computers, by bringing them off the desktop and into new and unique contexts. However, this new found versatility poses difficult challenges for user interface (UI) designers. We propose three model-based techniques that should aid UI designers who are working in the domain of mobile computing. These techniques allow designers to build UIs across several platforms, while respecting the unique constraints posed by each platform. In addition, these techniques should help designers to recognize and accommodate the unique contexts in which mobile computing occurs. All three techniques depend on the development of a UI model which serves to isolate those features that are common to the various contexts of use, and to specify how the UI should adjust when the context changes. UI models allow automatic and automated tool support that enables UI designers to overcome the challenges posed by mobile computing.

Adaptation in automated user-interface design

Design problems involve issues of stylistic preference and flexible standards of success; human designers often proceed by intuition and are unaware of following any strict rule-based procedures. These features make design tasks especially difficult to automate. Adaptation is proposed as a means to overcome these challenges. We describe a system that applies an adaptive algorithm to automated user interface design within the framework of the MOBI-D (Model-Based Interface Designer) interface development environment. Preliminary experiments indicate that adaptation improves the performance of the automated user interface design system.

Representation Learning for Text-level Discourse Parsing

Text-level discourse parsing is notoriously difficult, as distinctions between discourse relations require subtle semantic judgments that are not easily captured using standard features. In this paper, we present a representation learning approach, in which we transform surface features into a latent space that facilitates RST discourse parsing. By combining the machinery of large-margin transition-based structured prediction with representation learning, our method jointly learns to parse discourse while at the same time learning a discourse-driven projection of surface features. The resulting shift-reduce discourse parser obtains substantial improvements over the previous state-of-the-art in predicting relations and nuclearity on the RST Treebank.

Unified analysis of streaming news

News clustering, categorization and analysis are key components of any news portal. They require algorithms capable of dealing with dynamic data to cluster, interpret and to temporally aggregate news articles. These three tasks are often solved separately. In this paper we present a unified framework to group incoming news articles into temporary but tightly-focused storylines, to identify prevalent topics and key entities within these stories, and to reveal the temporal structure of stories as they evolve. We achieve this by building a hybrid clustering and topic model. To deal with the available wealth of data we build an efficient parallel inference algorithm by sequential Monte Carlo estimation. Time and memory costs are nearly constant in the length of the history, and the approach scales to hundreds of thousands of documents. We demonstrate the efficiency and accuracy on the publicly available TDT dataset and data of a major internet news site.

Unsupervised Multilingual Learning for POS Tagging

We demonstrate the effectiveness of multilingual learning for unsupervised part-of-speech tagging. The key hypothesis of multilingual learning is that by combining cues from multiple languages, the structure of each becomes more apparent. We formulate a hierarchical Bayesian model for jointly predicting bilingual streams of part-of-speech tags. The model learns language-specific features while capturing cross-lingual patterns in tag distribution for aligned words. Once the parameters of our model have been learned on bilingual parallel data, we evaluate its performance on a held-out monolingual test set. Our evaluation on six pairs of languages shows consistent and significant performance gains over a state-of-the-art monolingual baseline. For one language pair, we observe a relative reduction in error of 53%.