1. Articles in category: Entailment

    1-24 of 50 1 2 »
    1. Entailment evaluation device, entailment evaluation method, and recording medium

      An entailment evaluation device includes: a generation unit which generates first information indicating at least the order of occurrence of events of first and second simple sentences included in the hypothesis text and generates second information indicating at least the order of occurrence of events of third and fourth simple sentences included in a target text, the third simple sentence being related to the first simple sentence, the fourth simple sentence being related to the second simple sentence; a calculation unit which obtains a calculation result by comparing, based on the first and second information, the order of occurrence of ...

      Read Full Article
    2. A Vector Space for Distributional Semantics for Entailment. (arXiv:1607.03780v1 [cs.CL])

      Distributional semantics creates vector-space representations that capture many forms of semantic similarity, but their relation to semantic entailment has been less clear. We propose a vector-space model which provides a formal foundation for a distributional semantics of entailment. Using a mean-field approximation, we develop approximate inference procedures and entailment operators over vectors of probabilities of features being known (versus unknown).

      Read Full Article
    3. Addressing Limited Data for Textual Entailment Across Domains. (arXiv:1606.02638v1 [cs.CL])

      We seek to address the lack of labeled data (and high cost of annotation) for textual entailment in some domains. To that end, we first create (for experimental purposes) an entailment dataset for the clinical domain, and a highly competitive supervised entailment system, ENT, that is effective (out of the box) on two domains. We then explore self-training and active learning strategies to address the lack of labeled data.

      Read Full Article
    4. Recognizing Entailment and Contradiction by Tree-based Convolution. (arXiv:1512.08422v1 [cs.CL])

      Recognizing entailment and contradiction between two sentences has wide applications in NLP. Traditional methods include feature-rich classifiers or formal reasoning. However, they are usually limited in terms of accuracy and scope. Recently, the renewed prosperity neural networks has made many improvements in a variety of NLP tasks.

      Read Full Article
      Mentions: NLP
    5. Enacting textual entailment and ontologies for automated essay grading in chemical domain. (arXiv:1511.02669v1 [cs.AI])

      We propose a system for automated essay grading using ontologies and textual entailment. The process of textual entailment is guided by hypotheses, which are extracted from a domain ontology. Textual entailment checks if the truth of the hypothesis follows from a given text. We enact textual entailment to compare students answer to a model answer obtained from ontology. We validated the solution against various essays written by students in the chemistry domain.

      Read Full Article
    6. A large annotated corpus for learning natural language inference. (arXiv:1508.05326v1 [cs.CL])

      Understanding entailment and contradiction is fundamental to understanding natural language, and inference about entailment and contradiction is a valuable testing ground for the development of semantic representations. However, machine learning research in this area has been dramatically limited by the lack of large-scale resources.

      Read Full Article
    7. Textual entailment method for linking text of an abstract to text in the main body of a document

      A system and method are provided for processing an input document which enable assessment of the coherence of an abstract of the document. The method includes storing the document in memory and, for each sentence of the abstract, comparing the sentence with sentences of a main body of the document using textual entailment techniques to identify whether the sentence of the abstract entails a sentence in the main body of the document. Links can then be generated between the entailing sentences of the abstract and the corresponding entailed sentences of the document. The document and generated links are output. The ...

      Read Full Article
    8. Refining the Judgment Threshold to Improve Recognizing Textual Entailment Using Similarity

      In recent years, Recognizing Textual Entailment (RTE) catches strongly the attention of the Natural Language Processing (NLP) community. Using Similarity is an useful method for RTE, in which the Judgment Threshold plays an important role as the learning model. This paper proposes an RTE model based on using similarity. We describe clearly the solutions to determine and to refine the Judgment Threshold for Improvement RTE. The measure of the synonym similarity also is considered. Experiments on a Vietnamese version of the RTE3 corpus are showed. Content Type Book ChapterPages 335-344DOI 10.1007/978-3-642-34707-8_34Authors Quang-Thuy Ha, College of Technology (UET), Vietnam ...
      Read Full Article
    9. An Empirical Study of Recognizing Textual Entailment in Japanese Text

      Recognizing Textual Entailment (RTE) is a fundamental task in Natural Language Understanding. The task is to decide whether the meaning of a text can be inferred from the meaning of the other one. In this paper, we conduct an empirical study of the RTE task for Japanese, adopting a machine-learning-based approach. We quantitatively analyze the effects of various entailment features and the impact of RTE resources on the performance of a RTE system. This paper also investigates the use of Machine Translation for the RTE task and determines whether Machine Translation can be used to improve the performance of our ...
      Read Full Article
    10. A Statistics-Based Semantic Textual Entailment System

      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) competitions RTE-1, RTE-2, RTE-3 and RTE-5 and tested on the respective RTE test sets. Content Type Book ChapterPages 267-276DOI 10.1007/978-3-642-25324-9_23Authors Partha Pakray, Computer Science and Engineering Department, Jadavpur University, Kolkata, IndiaUtsab Barman, Computer Science and Engineering Department, Jadavpur ...
      Read Full Article
    11. An Entailment-Based Question Answering System over Semantic Web Data

      This paper reports a novel knowledge-based Question Answering (QA) method with the use of Semantic Web technologies and textual entailment recognition. Different from most of ontology-driven QA methods, this method does not perform deep question analysis to transform a natural language question into an ontology-compliant query for answer retrieval. Instead, it performs textual entailment recognition to discover the question template entailed by a user question from the whole machine-generated set and then takes the associated SPARQL query template to produce the complete query for retrieving the answers from the Semantic Web data that subscribe to the same ontology. An evaluation ...
      Read Full Article
    12. A WordNet-based semantic approach to textual entailment and cross-lingual textual entailment

      Abstract  In this paper we explain how to build a recognizing textual entailment (RTE) system which only uses semantic similarity measures based on WordNet. We show how the widely used WordNet-based semantic measures can be generalized to build sentence level semantic metrics in order to be used in both mono-lingual and cross-lingual textual entailment. We experiment with a wide variety of RTE datasets and evaluate the contribution of an algorithm which expands the RTE monolingual corpus. Results achieved with this method yielded significant statistical differences when predicting RTE test sets. We provide an efficiency analysis of these metrics drawing some ...
      Read Full Article
    13. Answer Validation through Textual Entailment

      Ongoing research work on an Answer Validation System (AV) based on Textual Entailment and Question Answering has been presented. A number of answer validation modules have been developed based on Textual Entailment, Named Entity Recognition, Question-Answer type analysis, Chunk boundary module and Syntactic similarity module. These answer validation modules have been integrated using a voting technique. We combine the question and the answer into the Hypothesis (H) and the Supporting Text as Text (T) to identify the entailment relation as either “VALIDATED” or “REJECTED”. The important features in the lexical Textual Entailment module are: WordNet based unigram match, bi-gram match ...
      Read Full Article
    14. Defining Specialized Entailment Engines Using Natural Logic Relations

      In this paper we propose a framework for the definition and combination of specialized entailment engines, each of which able to deal with a certain aspect of language variability. Such engines are based on transformations, and we define them taking advantage of the conceptual and formal tools available from an extended model of Natural Logic (NL). Given a T,H pair, each engine performs atomic edits to solve the specific linguistic phenomenon it is built to deal with, and assigns an entailment relation as the output of this operation. NL mechanisms of semantic relations composition are then applied to join ...
      Read Full Article
      Mentions: Natural Logic
    15. Answer Validation Using Textual Entailment

      We present an Answer Validation System (AV) based on Textual Entailment and Question Answering. The important features used to develop the AV system are Lexical Textual Entailment, Named Entity Recognition, Question-Answer type analysis, chunk boundary module and syntactic similarity module. The proposed AV system is rule based. We first combine the question and the answer into Hypothesis (H) and the Supporting Text as Text (T) to identify the entailment relation as either “VALIDATED” or “REJECTED”. The important features used for the lexical Textual Entailment module in the present system are: WordNet based unigram match, bigram match and skip-gram. In the ...
      Read Full Article
    16. Recognizing Textual Entailment with Statistical Methods

      In this paper we propose a new cause-effect non-symmetric measure applied to the task of Recognizing Textual Entailment .First we searched over a big corpus for sentences which contains the discourse marker “because” and collected cause-effect pairs. The entailment recognition is based on measure the cause-effect relation between the text and the hypothesis using the relative frequencies of words from the cause-effect pairs. Our measure outperformed the baseline method, over the three test sets of the PASCAL Recognizing Textual Entailment Challenges (RTE). The measure shows to be good at discriminate over the “true” class. Therefore we develop a meta-classifier using ...
      Read Full Article
    17. Don't 'have a clue'? Unsupervised co-learning of downward-entailing operators. (arXiv:1008.3169v2 [cs.CL] UPDATED)

      Researchers in textual entailment have begun to consider inferences involving 'downward-entailing operators', an interesting and important class of lexical items that change the way inferences are made. Recent work proposed a method for learning English downward-entailing operators that requires access to a high-quality collection of 'negative polarity items' (NPIs). However, English is one of the very few languages for which such a list exists. We propose the first approach that can be applied to the many languages for which there is no pre-existing high-precision database of NPIs. As a case study, we apply our method to Romanian and show that ...
      Read Full Article
    18. Learning Parse-Free Event-Based Features for Textual Entailment Recognition

      We propose new parse-free event-based features to be used in conjunction with lexical, syntactic, and semantic features of texts and hypotheses for Machine Learning-based Recognizing Textual Entailment. Our new similarity features are extracted without using shallow semantic parsers, but still lexical and compositional semantics are not left out. Our experimental results demonstrate that these features can improve the effectiveness of the identification of entailment and no-entailment relationships. Content Type Book ChapterDOI 10.1007/978-3-642-17432-2_19Authors Bahadorreza Ofoghi, Centre for Informatics and Applied Optimization, University of Ballarat, P.O. Box 663, Ballarat, Victoria 3350, AustraliaJohn Yearwood, Centre for Informatics and Applied Optimization ...
      Read Full Article
    19. Translators in Textual Entailment

      This paper presents how the size of Textual Entailment Corpus could be increased by using Translators to generate additional 〈t, h〉 pairs. Also, we show the theoretical upper bound of a Corpus expanded by translators. Then, we propose an algorithm to expand the corpus size using Translator engines starting from a RTE Corpus, and finally we show the benefits that it could produce on RTE systems. Content Type Book ChapterDOI 10.1007/978-3-642-14883-5_25Authors Julio Javier Castillo, National University of Cordoba-FaMAF, Cordoba, Argentina Book Series Advances in Soft ComputingOnline ISSN 1860-0794Print ISSN 1615-3871 Book Series Volume Volume 79/2010 Book Distributed ...
      Read Full Article
      Mentions: Argentina Cordoba RTE
    20. Towards Better Ontological Support for Recognizing Textual Entailment

      Many applications in modern information technology utilize ontological knowledge to increase their performance, precision, and success rate. However, the integration of ontological sources is in general a difficult task since the semantics of all concepts, individuals, and relations must be preserved across the various sources. In this paper we discuss the importance of combined background knowledge for recognizing textual entailment (RTE). We present and analyze formally a new graph-based procedure for integration of concepts and individuals from ontologies based on the hierarchy of WordNet. We embed it in our experimental RTE framework where a deep-shallow semantic text analysis combined with ...
      Read Full Article
      Mentions: Germany WordNet RTE
    21. Using Sentence Semantic Similarity Based on WordNet in Recognizing Textual Entailment

      This paper presents a Recognizing Textual Entailment system which uses semantic distances to sentence level over WordNet to assess the impact on predicting Textual Entailment datasets. We extent word-to-word metrics to sentence level in order to best fit in textual entailment domain. Finally, we show experiments over several RTE datasets and draw conclusions about the useful of WordNet semantic measures on this task. As a conclusion, we show that an initial but average-score system can be built using only semantic information from WordNet. Content Type Book ChapterDOI 10.1007/978-3-642-16952-6_37Authors Julio J. Castillo, National University of Cordoba-FaMAF, Cordoba, ArgentinaMarina E ...
      Read Full Article
    22. A Semantic Oriented Approach to Textual Entailment Using WordNet-Based Measures

      In this paper, we present a Recognizing Textual Entailment system which uses semantic similarity metrics to sentence level only using WordNet as source of knowledge. We show how the widely used semantic measures WordNet-based can be generalized to build sentence level semantic metrics in order to be used in the RTE. We also provide an analysis of efficiency of these metrics and drawn some conclusions about their utility in the practice in recognizing textual entailment. We also show that using the proposed method to extend word semantic measures could be used in building an average score system that only uses ...
      Read Full Article
      Mentions: Argentina Cordoba RTE
    23. Recognizing Textual Entailment Using a Machine Learning Approach

      We present our experiments on Recognizing Textual Entailment based on modeling the entailment relation as a classification problem. As features used to classify the entailment pairs we use a symmetric similarity measure and a non-symmetric similarity measure. Our system achieved an accuracy of 66% on the RTE-3 development dataset (with 10-fold cross validation) and accuracy of 63% on the RTE-3 test dataset. Content Type Book ChapterDOI 10.1007/978-3-642-16773-7_15Authors Miguel Angel Ríos Gaona, Center for Computing Research, National Polytechnic Institute, MexicoAlexander Gelbukh, Center for Computing Research, National Polytechnic Institute, MexicoSivaji Bandyopadhyay, Computer Science & Engineering Department, Jadavpur University, Kolkata, 700 032 ...
      Read Full Article
    24. NL from Logic: Connecting Entailment and Generation

      The paper introduces an index of fully-specified logical form for unrestricted natural language. The index is argued to facilitate both computation of entailment and generation under semantic control. Content Type Book ChapterDOI 10.1007/978-3-642-14287-1_10Authors Crit Cremers, Leiden University Centre for Linguistics Book Series Lecture Notes in Computer ScienceOnline ISSN 1611-3349Print ISSN 0302-9743 Book Series Volume Volume 6042/2010 Book Logic, Language and MeaningDOI 10.1007/978-3-642-14287-1Print ISBN 978-3-642-14286-4
      Read Full Article
      Mentions: Leiden
    1-24 of 50 1 2 »
  1. Categories

    1. Default:

      Discourse, Entailment, Machine Translation, NER, Parsing, Segmentation, Semantic, Sentiment, Summarization, WSD
  2. Popular Articles