This paper studies the use of structural representations for learning relations between pairs of short texts (e.g., sentences or paragraphs) of the kind: the second text answers to, or conveys exactly the same information of, or is implied by, the first text. Engineering effective features that can capture syntactic and semantic relations between the constituents composing the target text pairs...

This paper describes the systems of THU QUANTA in Text Analysis Conference (TAC) 2008. We participated in the Question Answering (QA) track, and the Recognizing Textual Entailment (RTE) track. For question answering track, we enhanced the traditional question answering system by sentiment lexicon based opinion analysis. The rigid list questions are divided into two categories based on their ans...

In this work, we present a feature-based approach to the RTE (Recognizing Text Entailment) task that verifies the similarity between two sentences including syntactic and semantic aspects. The selected features come from the winning work of the RTE task of the workshop ASSIN (Semantic Similarity Evaluation and Textual Inference) with some changes and addition of other semantic feature. The eval...

  Abstract Critical Discourse Analysis as an interdisciplinary approach aims at making transparent the connections between discourse practices and social practices and provides ways of looking into translations from a critical standpoint.Farahzad is among the scholars who presented her specific CDA model inspired by Fairclough’s approach. The present Critical Discourse Analysis (CDA)-based s...

We present in this paper the structure of a textual entailer, offer a detailed view of lexical aspects of entailment and study the impact of syntactic information on the overall performance of the textual entailer. It is shown that lemmatization has a big impact on the lexical component of our approach and that syntax leads to accurate entailment decisions for a subset of the test data.

The automatic analysis and classification of text using fine-grained attitude labels is the main task we address in our research. The developed @AM system relies on compositionality principle and a novel approach based on the rules elaborated for semantically distinct verb classes. The evaluation of our method on 1000 sentences, that describe personal experiences, showed promising results: aver...

This paper is a contribution to ongoing debates about the value and limitations of textual analysis in digital games research. It is argued that due to the particular nature of digital games, both structural analysis and textual analysis are relevant to game studies. Unfortunately they tend to be conflated. Neither structural nor textual factors will fully determine meaning, but they are aspect...

Ontologies are continuously confronted to evolution problem. Due to the complexity of the changes to be made, a maintenance process, at least a semi-automatic one, is more and more necessary to facilitate this task and to ensure its reliability. In this paper, we propose a maintenance ontology model for a domain, whose originality is to be language independent and based on a sequence of text pr...

and analysis J. W. Murdock J. Fan A. Lally H. Shima B. K. Boguraev One useful source of evidence for evaluating a candidate answer to a question is a passage that contains the candidate answer and is relevant to the question. In the DeepQA pipeline, we retrieve passages using a novel technique that we call Supporting Evidence Retrieval, in which we perform separate search queries for each candi...