This paper describes our contribution to the SemEval-2015 task 17 on “Taxonomy Extraction Evaluation”. We propose a hypernym detection system combining three modules: a lexico-syntactic pattern matcher, a morphosyntactic analyzer and a module retrieving hypernym relations from structured lexical resources. Our system ranked first in the competition when considering the gold standard and manual ...

We present in this paper a method to automatically acquire a syntactic lexicon of subcategorization frames for French verbs directly from large corpora. The method is evaluated against existing lexical resources: we show that our system is capable of producing new frames that were not previously registered. Lastly, we show that it is possible to induce lexico-semantic classes « à la Levin » (19...

Linguistic theory in the generative tradition is based on a small number of simple but important observations about human languages and how they are acquired. First, the structure of language is extremely complex– so complex that it is often argued that it would be impossible to learn without prior knowledge as to its general character (Chomsky, 1965). Second, children learn languages rapidly a...

Automated evaluation is crucial in the context of automated text summaries, as is the case with evaluation of any of the language technologies. While the quality of a summary is determined by both content and form of a summary, throughout the literature there has been extensive study on the automatic and semi-automatic evaluation of content of summaries and most such applications have been larg...

A classifier which is capable of distinguishing a syntactically well formed sentence from a syntactically ill formed one has the potential to be useful in an L2 language-learning context. In this article, we describe a classifier which classifies English sentences as either well formed or ill formed using information gleaned from three different natural language processing techniques. We descri...

We present a set of new measures designed to reveal latent information of language use in children at the lexico-syntactic level. Our analysis of spontaneous narratives from children identified with language impairment and children developing typically shows that these metrics are a promising approach that could aid in the task of language assessment.

We examined the learning process with 3 sets of stimuli that have identical symbolic structure but differ in appearance (meaningless letter strings, arrangements of geometric shapes, and sequences of cities). One hypothesis is that the learning process aims to encode symbolic regularity in the same way, largely regardless of appearance. Another is that different types of stimuli bias the learni...

We propose a simple generative, syntactic language model that conditions on overlapping windows of tree context (or treelets) in the same way that n-gram language models condition on overlapping windows of linear context. We estimate the parameters of our model by collecting counts from automatically parsed text using standard n-gram language model estimation techniques, allowing us to train a ...

-1INTRODUCTION Halfway through the twentieth century, linguistics underwent a major methodological shift, from distributional analysis of native-speaker speech (BloomÞeld, 1961), to the analysis of native-speaker intuitions about legal sentence types (Chomsky, 1957; for reviews, see Newmeyer, 1980; Sells, Shieber & Wasow, 1991). In most cases, the native speakers who furnish these intuitions ha...

Effects of negative input for 13 categories of grammatical error were assessed in a longitudinal study of naturalistic adult-child discourse. Two-hour samples of conversational interaction were obtained at two points in time, separated by a lag of 12 weeks, for 12 children (mean age 2;0 at the start). The data were interpreted within the framework offered by Saxton's (1997, 2000) contrast theor...