Corpus ID: 7586401

Don’t ‘Have a Clue’? Unsupervised Co-Learning of Downward-Entailing Operators.

  title={Don’t ‘Have a Clue’? Unsupervised Co-Learning of Downward-Entailing Operators.},
  author={Cristian Danescu-Niculescu-Mizil and Lillian Lee},
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… Expand
Unsupervised Detection of Downward-Entailing Operators By Maximizing Classification Certainty
An unsupervised, iterative method for detecting downward-entailing operators (DEOs), which are important for deducing entailment relations between sentences, and achieves the best results in identifying DEOs in two corpora. Expand
Intrinsic and extrinsic approaches to recognizing textual entailment
A general framework is proposed to view textual entailment as one of the generalized Textual Semantic Relations (TSRs) and instead of tackling the RTE task in a standalone manner, it is looked at its connection to other semantic relations between two texts. Expand
Modal Verbs in the Common Ground: Discriminating Among Actual and Nonactual Uses of Could and Would for Improved Text Interpretation
  • Lori Moon
  • Computer Science
  • AAAI Fall Symposium: Building Representations of Common Ground with Intelligent Agents
  • 2011
Linguistic features which disambiguate those instances of the past tense modal verbs `could’ and `would’ which occur in contexts where the proposition in the scope of the modal is not true in the actual world of the discourse are presented. Expand
Closed-domain natural language approaches: methods and applications
This PhD dissertation is aimed for identifying and analyzing main difficulties that arise on closed-domain NL approaches in order to propose valuable scientific contributions to the state of the art in form of technological solutions. Expand
Lexicon-based Comments-oriented News Sentiment Analyzer system
A lexicon-based Comments-oriented News Sentiment Analyzer (LCN-SA), which is able to deal with the tendency of many users to express their views in non-standard language and the design of a linguistic modularized knowledge model with low-cost adaptability. Expand
Recognizing Textual Entailment: Models and Applications
This book discusses the development of knowledge acquisition techniques in the field of text-based learning and discusses their applications in the context of education and research. Expand
Recent Progress on Monotonicity
This paper is a summary of much work concerning formal treatments of monotonicity and polarity in natural language, and it discusses connections to related work on exclusion relations, and connections to psycholinguistics and computational linguistics. Expand


Without a ’doubt’? Unsupervised Discovery of Downward-Entailing Operators
Here, the first algorithm for the challenging lexical-semantics problem of learning linguistic constructions that, like 'doubt', are downward entailing (DE) is presented. Expand
Computing relative polarity for textual inference
Semantic relations between main and complement sentences are of great significance in any system of automatic data processing that depends on natural language. In this paper we present a strategy forExpand
Modeling Semantic Containment and Exclusion in Natural Language Inference
This work proposes an approach to natural language inference based on a model of natural logic, which identifies valid inferences by their lexical and syntactic features, without full semantic interpretation, to incorporate both semantic exclusion and implicativity. Expand
The Role of Negative Polarity and Concord Marking in Natural Language Reasoning
For better or for worse, most of the large body of research on natural lan­ guage semantics done in the past two decades has employed semantic (model­ theoretic) methods but has ignored deduction. OfExpand
Monotonicity and Processing Load
Starting out from the assumption that monotonicity plays a central role in interpretation and inference, we derive a number of predictions about the complexity of processing quantified sentences. AExpand
A simple system for detecting non-entailment
This work uses the observation that a text usually must mention all of the information in the hypothesis as a basis for a simple system for detecting non-entailment, which performs well on the Recognizing Textual Entailment (RTE) evaluation. Expand
Efficient Semantic Deduction and Approximate Matching over Compact Parse Forests
A new data structure is presented, termed compact forest, which allows efficient generation and representation of entailed consequents, each represented as a parse tree, in rule-based inference, complemented with a new approximate matching measure inspired by tree kernels. Expand
Creating a Natural Logic Inference System with Combinatory Categorial Grammar
This dissertation presents an integrated system for producing Natural Logic inferences, which are used in a wide variety of natural language understanding tasks. Natural Logic is the process ofExpand
The PASCAL Recognising Textual Entailment Challenge
This paper presents the Third PASCAL Recognising Textual Entailment Challenge (RTE-3), providing an overview of the dataset creating methodology and the submitted systems. In creating this year'sExpand
Negative Polarity Items Corpus Linguistics, Semantics, and Psycholinguistics