We present a new supervised framework that learns to estimate automatic Pyramid scores and uses them for optimizationbased extractive multi-document summarization.For learning automatic Pyramid scores, we developed a method for automatic training data generation which is based on a genetic algorithm using automatic Pyramid as the fitness function.Our experimental evaluation shows that our new framework significantly outperforms strong baselines regarding automatic Pyramid, and that there is much room for improvement in comparison with the upperbound for automatic Pyramid.

Sallam Abualhaija, Tristan Miller, Judith Eckle-Kohler, Iryna Gurevych, Karl-Heinz Zimmermann. Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers. 2017.

We revisit Levin's theory about the correspondence of verb meaning and syntax and infer semantic classes from a large syntactic classification of more than 600 German verbs taking clausal and non-finite arguments.Grasping the meaning components of Levin-classes is known to be hard.We address this challenge by setting up a multi-perspective semantic characterization of the inferred classes.To this end, we link the inferred classes and their English translation to independently constructed semantic classes in three different lexicons -the German wordnet GermaNet, VerbNet and FrameNet -and perform a detailed analysis and evaluation of the resulting German-English classification (available at www.ukp.tu-darmstadt.de/modality-verbclasses/).

This paper presents a problem-reduction \napproach to extractive multi-document \nsummarization: we propose a reduction \nto the problem of scoring individual sentences \nwith their ROUGE scores based on \nsupervised learning. For the summarization, \nwe solve an optimization problem \nwhere the ROUGE score of the selected \nsummary sentences is maximized. To this \nend, we derive an approximation of the \nROUGE-N score of a set of sentences, and \ndefine a principled discrete optimization \nproblem for sentence selection. Mathematical \nand empirical evidence suggests \nthat the sentence selection step is solved \nalmost exactly, thus reducing the problem \nto the sentence scoring task. We perform \na detailed experimental evaluation on two \nDUC datasets to demonstrate the validity \nof our approach.

Sentence intersection captures the semantic overlap of two texts, generalizing over paradigms such as textual entailment and semantic text similarity. Despite its modeling power, it has received little attention because it is difficult for non-experts to annotate. We analyze 200 pairs of similar sentences and identify several underlying properties of sentence intersection. We leverage these insights to design an algorithm that decomposes the sentence intersection task into several simpler annotation tasks, facilitating the construction of a high quality dataset via crowdsourcing. We implement this approach and provide an annotated dataset of 1,764 sentence intersections.

We introduce the task of detecting cross-lingual marketing blunders, which occur if a trade name resembles an inappropriate or negatively connotated word in a target language. To this end, we suggest a formal task definition and a semi-automatic method based the propagation of pragmatic labels from Wiktionary across sense-disambiguated translations. Our final tool assists users by providing clues for problematic names in any language, which we simulate in two experiments on detecting previously occurred marketing blunders and identifying relevant clues for established international brands. We conclude the paper with a suggested research roadmap for this new task. To initiate further research, we publish our online demo along with the source code and data at http://uby.ukp.informatik.tu-darmstadt.de/blunder/.

Extracting summaries via integer linear programming and submodularity are popular and successful techniques in extractive multi-document summarization. However, many interesting optimization objectives are neither submodular nor factorizable into an integer linear program. We address this issue and present a general optimization framework where any function of input documents and a system summary can be plugged in. Our framework includes two kinds of summarizers – one based on genetic algorithms, the other using a swarm intelligence approach. In our experimental evaluation, we investigate the optimization of two information-theoretic summary evaluation metrics and find that our framework yields competitive results compared to several strong summarization baselines. Our comparative analysis of the genetic and swarm summarizers reveals interesting complementary properties.

Research in multi-document summarization has focused on newswire corpora since the early beginnings. However, the newswire genre provides genre-specific features such as sentence position which are easy to exploit in summarization systems. Such easy to exploit genre-specific features are available in other genres as well. We therefore present the new hMDS corpus for multi-document summarization, which contains heterogeneous source documents from multiple text genres, as well as summaries with different lengths. For the construction of the corpus, we developed a novel construction approach which is suited to build large and heterogeneous summarization corpora with little effort. The method reverses the usual process of writing summaries for given source documents: it combines already available summaries with appropriate source documents. In a detailed analysis, we show that our new corpus is significantly different from the homogeneous corpora commonly used, and that it is heterogeneous along several dimensions. Our experimental evaluation using well-known state-of-the-art summarization systems shows that our corpus poses new challenges in the field of multi-document summarization. Last but not least, we make our corpus publicly available to the research community at the corpus web page https://github.com/AIPHES/hMDS.

We present a new approach for generating role-labeled training data using Linked Lexical Resources, i.e., integrated lexical resources that combine several resources (e.g., Word-Net, FrameNet, Wiktionary) by linking them on the sense or on the role level. Unlike resource-based supervision in relation extraction, we focus on complex linguistic annotations, more specifically FrameNet senses and roles. The automatically labeled training data ( www.ukp.tu-darmstadt.de/knowledge-based-srl/ ) are evaluated on four corpora from different domains for the tasks of word sense disambiguation and semantic role classification. Results show that classifiers trained on our generated data equal those resulting from a standard supervised setting.

This paper presents a study on the role of discourse markers in argumentative discourse.We annotated a German corpus with arguments according to the common claim-premise model of argumentation and performed various statistical analyses regarding the discriminative nature of discourse markers for claims and premises.Our experiments show that particular semantic groups of discourse markers are indicative of either claims or premises and constitute highly predictive features for discriminating between them.

We present a novel approach for creating sense annotated corpora automatically.Our approach employs shallow syntacticosemantic patterns derived from linked lexical resources to automatically identify instances of word senses in text corpora.We evaluate our labelling method intrinsically on SemCor and extrinsically by using automatically labelled corpus text to train a classifier for verb sense disambiguation.Testing this classifier on verbs from the English MASC corpus and on verbs from the Senseval-3 all-words disambiguation task shows that it matches the performance of a classifier which has been trained on manually annotated data.