In this paper we define two intermediate models of textual entailment, which correspond to lexical and lexical-syntactic levels of representation. We manually annotated a sample from the RTE dataset according to each model, compared the outcome for the two models, and explored how well they approximate the notion of entailment. We show that the lexicalsyntactic model outperforms the lexical mod...

We present a Textual Entailment (TE) recognition system that uses semantic features based on the Universal Networking Language (UNL). The proposed TE system compares the UNL relations in both the text and the hypothesis to arrive at the two-way entailment decision. The system has been separately trained on each development corpus released as part of the Recognizing Textual Entailment (RTE) comp...

Our system combines text similarity measures with a textual entailment system. In the main task, we focused on the influence of lexicalized versus unlexicalized features, and how they affect performance on unseen questions and domains. We also participated in the pilot partial entailment task, where our system significantly outperforms a strong baseline.

Online reviews are an important asset for users deciding to buy a product, see a movie, or go to a restaurant, as well as for businesses tracking user feedback. However, most reviews are written in a free-text format, and are therefore difficult for computers to understand, analyze, and aggregate. One consequence of this lack of structure is that searching text reviews is often frustrating for ...

this essay examines the practice of free indirect discourse (fid), as a narrative-stylistic device, in hossein sanapour’s lips on a blade (2010). after a brief overview of the novel ’s narrative structure, the four modes of representing characters’ discourses in narrative fiction are introduced and exemplified. among these modes, fid is the most important since it is the only one which leads to...

Textual representations play an important role in the field of natural language processing (NLP). The efficiency of NLP tasks, such as text comprehension and information extraction, can be significantly improved with proper textual representations. As neural networks are gradually applied to learn the representation of words and phrases, fairly efficient models of learning short text representa...

We introduce CST (cross-document structure theory), a paradigm for multidocument analysis. CST takes into account the rhetorical structure of clusters of related textual documents. We present a taxonomy of cross-document relationships. We argue that CST can be the basis for multidocument summarization guided by user preferences for summary length, information provenance, cross-source agreement,...

In this paper, we present the explanation structure of procedural texts, that supports and motivates the goal-instruction structure. We focus in particular on arguments, and show how arguments of type warnings and advices can be extracted. Finally, we show how a domain dependent knowhow textual knowledge base can be constructed and queried.

This paper presents ongoing work dedicated to parsing the textual structure of procedural texts. This work is based on a two level approach: first, basic structures in texts are segmented using automata techniques and then a text grammar is applied to assemble these fragments. The grammar is based on X-bar syntax, transposed to text structure.