We describe our efforts to generate a large (100,000 instance) corpus of textual entailment pairs from the lead paragraph and headline of news articles. We manually inspected a small set of news stories in order to locate the most productive source of entailments, then built an annotation interface for rapid manual evaluation of further exemplars. With this training data we built an SVM-based d...

Nowadays automatic systems for detecting and measuring textual similarity are being developed, in order to apply them to different tasks in the field of Natural Language Processing (NLP). Currently, these systems use surface linguistic features or statistical information. Nowadays, few researchers use deep linguistic information. In this work, we present an algorithm for detecting and measuring...

Researchers in discourse have long hypothesized that the nuclei of a rhetorical structure tree provide a good summary of the text for which that tree was built. In this paper, I discuss a psy-cholinguistic experiment that validates this hypothesis , but that also shows that the distinction between nuclei and satellites is not suucient if we want to build summaries of very high quality. I empiri...

Information graphics, such as bar charts and line graphs, play an important role in multimodal documents. This paper presents a novel approach to producing a brief textual summary of a simple bar chart. It outlines our approach to augmenting the core message of the graphic to produce a brief summary. Our method simultaneously constructs both the discourse and sentence structures of the textual ...

In this paper, we introduce a new framework for recognizing textual entailment which depends on extraction of the set of publiclyheld beliefs – known as discourse commitments – that can be ascribed to the author of a text or a hypothesis. Once a set of commitments have been extracted from a t-h pair, the task of recognizing textual entailment is reduced to the identification of the commitments ...

This paper discusses the mainstream discourse of chemistry and suggests a complementary discourse. On a disciplinary level, the discourse of chemistry is based on objectivism, rationalism, and molecular reductionism. On a societal level, the discourse is based on modernism. The aims of chemical research and education are often unclear, which nowadays often leads to an emphasis on the needs from...

Today’s information retrieval applications have become increasingly complex. The Social Book Search (SBS) lab at CLEF 2015 allows evaluating retrieval methods on a complex search task with several textual and non-textual meta-data fields. The challenge is to incorporate the different information types (modalities) into a single ranked list. We build a strong textual baseline and combine it with...

The long term goal of this research is to develop a program able to produce an automatic segmentation and categorization of textual sequences into discourse types. In this preliminary contribution, we present the construction of an algorithm which takes a segmented text as input and attempts to produce a categorization of sequences, such as narrative, argumentative, descriptive and so on. Also,...