separated from evaluating entailment. Current approaches to semantic inference in question answer-.

As algorithms pervade numerous facets of daily life, they are incorporated into systems for increasingly diverse purposes. These systems’ results are often interpreted differently by the designers who created them than by the lay persons who interact with them. This paper offers a proposal for human-centered algorithm design, which incorporates human and social interpretations into the design process for algorithmically based systems. It articulates three specific strategies for doing so: theoretical, participatory, and speculative. Drawing on the author’s work designing and (...) deploying multiple related systems, the paper provides a detailed example of using a theoretical approach. It also discusses findings pertinent to participatory and speculative design approaches. The paper addresses both strengths and challenges for each strategy in helping to center the process of designing algorithmically based systems around humans. (shrink)

This paper examines the Stanford typed dependencies representation, which was designed to provide a straightforward description of grammatical relations for any user who could benefit from automatic text understanding. For such purposes, we argue that dependency schemes must follow a simple design and provide semantically contentful information, as well as offer an automatic procedure to extract the relations. We consider the underlying design principles of the Stanford scheme from this perspective, and compare it to the GR and PARC representations. Finally, (...) we address the question of the suitability of the Stanford scheme for parser evaluation. (shrink)

In common law jurisdictions, legal professionals cite facts and legal principles from precedent cases to support their arguments before the court for their intended outcome in a current case. This practice stems from the doctrine of stare decisis, where cases that have similar facts should receive similar decisions with respect to the principles. It is essential for legal professionals to identify such facts and principles in precedent cases, though this is a highly time intensive task. In this paper, we present (...) studies that demonstrate that human annotators can achieve reasonable agreement on which sentences in legal judgements contain cited facts and principles. We further demonstrate that it is feasible to automatically annotate sentences containing such legal facts and principles in a supervised machine learning framework based on linguistic features, reporting per category precision and recall figures of between 0.79 and 0.89 for classifying sentences in legal judgements as cited facts, principles or neither using a Bayesian classifier, with an overall κ\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\kappa$$\end{document} of 0.72 with the human-annotated gold standard. (shrink)

The prevalence in Chinese of grammatical structures that translate into English in different word orders is an important cause of translation difficulty. While previous work has used phrase-structure parses to deal with such ordering problems, we introduce a richer set of Chinese grammatical relations that describes more semantically abstract relations between words. Using these Chinese grammatical relations, we improve a phrase orientation classifier (introduced by Zens and Ney (2006)) that decides the ordering of two phrases when translated into English by (...) adding path features designed over the Chinese typed dependencies. We then apply the log probability of the phrase orientation classifier as an extra feature in a phrase-based MT system, and get significant BLEU point gains on three test sets: MT02 (+0.59), MT03 (+1.00) and MT05 (+0.77). Our Chinese grammatical relations are also likely to be useful for other NLP tasks. (shrink)

Marie-Catherine de Marneffe, Anna N. Rafferty and Christopher D. Manning Linguistics Department Computer Science Department Stanford University Stanford University Stanford, CA 94305 Stanford, CA 94305 {rafferty,manning}@stanford.edu [email protected]..