Henning Wachsmuth

Sentiment Flow - A General Model of Web Review Argumentation

Web reviews have been intensively studied in argumentation-related tasks such as sentiment analysis. However, due to their focus on content-based features, many sentiment analysis approaches are effective only for reviews from those domains they have been specifically modeled for. This paper puts its focus on domain independence and asks whether a general model can be found for how people argue in web reviews. Our hypothesis is that people express their global sentiment on a topic with similar sequences of local sentiment independent of the domain. We model such sentiment flow robustly under uncertainty through abstraction. To test our hypothesis, we predict global sentiment based on sentiment flow. In systematic experiments, we improve over the domain independence of strong baselines. Our findings suggest that sentiment flow qualifies as a general model of web review argumentation.

Cross-Domain Mining of Argumentative Text through Distant Supervision.

Argumentation mining is considered as a key technology for future search engines and automated decision making. In such applications, argumentative text segments have to be mined from large and diverse document collections. However, most existing argumentation mining approaches tackle the classification of argumentativeness only for a few manually annotated documents from narrow domains and registers. This limits their practical applicability. We hence propose a distant supervision approach that acquires argumentative text segments automatically from online debate portals. Experiments across domains and registers show that training on such a corpus improves the effectiveness and robustness of mining argumentative text. We freely provide the underlying corpus for research.

PBlaman: performance blame analysis based on Palladio contracts

In performance‐driven software engineering, the performance of a system is evaluated through models before the system is assembled. After assembly, the performance is then validated using performance tests. When a component‐based system fails certain performance requirements during the tests, it is important to find out whether individual components yield performance errors or whether the composition of components is faulty. This task is called performance blame analysis. Existing performance blame analysis approaches and also alternative error analysis approaches are restricted, because they either do not employ expected values, use expected values from regression testing, or use static developer‐set limits. In contrast, this paper describes the new performance blame analysis approach PBlaman that builds upon our previous work and that employs the context‐portable performance contracts of Palladio. PBlaman decides what components to blame by comparing the observed response time data series of each single component operation in a failed test case to the operations expected response time data series derived from the contracts. System architects are then assisted by a visual presentation of the obtained analysis results. We exemplify the benefits of PBlaman in two case studies, each of which representing applications that follow a particular architectural style. Copyright

Automatic pipeline construction for real-time annotation

Many annotation tasks in computational linguistics are tackled with manually constructed pipelines of algorithms. In real-time tasks where information needs are stated and addressed ad-hoc, however, manual construction is infeasible. This paper presents an artificial intelligence approach to automatically construct annotation pipelines for given information needs and quality prioritizations. Based on an abstract ontological model, we use partial order planning to select a pipelines algorithms and informed search to obtain an efficient pipeline schedule. We realized the approach as an expert system on top of Apache UIMA, which offers evidence that pipelines can be constructed ad-hoc in near-zero time.

Argumentation Quality Assessment: Theory vs. Practice.

Argumentation quality is viewed differently in argumentation theory and in practical assessment approaches. This paper studies to what extent the views match empirically. We find that most observations on quality phrased spontaneously are in fact adequately represented by theory. Even more, relative comparisons of arguments in practice correlate with absolute quality ratings based on theory. Our results clarify how the two views can learn from each other.

Information extraction as a filtering task

Information extraction is usually approached as an annotation task: Input texts run through several analysis steps of an extraction process in which different semantic concepts are annotated and matched against the slots of templates. We argue that such an approach lacks an efficient control of the input of the analysis steps. In this paper, we hence propose and evaluate a model and a formal approach that consistently put the filtering view in the focus: Before spending annotation effort, filter those portions of the input texts that may contain relevant information for filling a template and discard the others. We model all dependencies between the semantic concepts sought for with a truth maintenance system, which then efficiently infers the portions of text to be annotated in each analysis step. The filtering view enables an information extraction system (1) to annotate only relevant portions of input texts and (2) to easily trade its run-time efficiency for its recall. We provide our approach as an open-source extension of Apache UIMA and we show the potential of our approach in a number of experiments.

A Universal Model for Discourse-Level Argumentation Analysis

The argumentative structure of texts is increasingly exploited for analysis tasks, for example, for stance classification or the assessment of argumentation quality. Most existing approaches, however, model only the local structure of single arguments. This article considers the question of how to capture the global discourse-level structure of a text for argumentation-related analyses. In particular, we propose to model the global structure as a flow of “task-related rhetorical moves,” such as discourse functions or aspect-based sentiment. By comparing the flow of a text to a set of common flow patterns, we map the text into the feature space of global structures, thus capturing its discourse-level argumentation. We show how to identify different types of flow patterns, and we provide evidence that they generalize well across different domains of texts. In our evaluation for two analysis tasks, the classification of review sentiment and the scoring of essay organization, the features derived from flow patterns prove both effective and more robust than strong baselines. We conclude with a discussion of the universality of modeling flow for discourse-level argumentation analysis.

Text Analysis Pipelines

The understanding of natural language is one of the primary abilities that provide the basis for human intelligence. Since the invention of computers, people have thought about how to operationalize this ability in software applications (Jurafsky and Martin 2009). The rise of the internet in the 1990s then made explicit the practical need for automatically processing natural language in order to access relevant information . Search engines , as a solution, have revolutionalized the way we can find such information ad-hoc in large amounts of text (Manning et al. 2008). Until today, however, search engines excel in finding relevant texts rather than in understanding what information is relevant in the texts. Chapter 1 has proposed text mining as a means to achieve progress towards the latter, thereby making information search more intelligent. At the heart of every text mining application lies the analysis of text, mostly realized in the form of text analysis pipelines . In this chapter, we present the basics required to follow the approaches of this book to improve such pipelines for enabling text mining ad-hoc on large amounts of text as well as the state of the art in this respect.