In this paper, we demonstrate that significant performance gains can be achieved in CCG semantic parsing by introducing a linguistically motivated grammar induction scheme. We present a new morpho-syntactic factored lexicon that models systematic variations in morphology, syntax, and semantics across word classes. The grammar uses domain-independent facts about the English language to restrict ...

In this paper we investigate the impact of translation on readability. We propose a quantitative analysis of several shallow, lexical and morpho-syntactic features that have been traditionally used for assessing readability and have proven relevant for this task. We conduct our experiments on a parallel corpus of transcribed parliamentary sessions and we investigate readability metrics for the ...

This paper focuses on the linguistic aspect of noun phrase coreference, investigating the knowledge sources that can potentially improve a learningbased coreference resolution system. Unlike traditional, knowledge-lean coreference resolvers, which rely almost exclusively on morpho-syntactic cues, we show how to induce features that encode semantic knowledge from labeled and unlabeled corpora. E...

The Informative Boundary Hypothesis (IBH: [4]) claims that a prosodic boundary is interpreted relative to preceding boundaries. This study tests predictions of the IBH with Korean learners of English (L2ers) and English native speakers (L1ers) in a prosody experiment on the resolution of an Early vs. Late Closure ambiguity in spoken English sentences. A control experiment assessed and controlle...

This paper gives an overview of the morpho-syntactic features of the Amazighe language and corpus encoding, afterwards we present our experience of constructing an annotated corpus with part-of-speech (POS) information. The annotated corpora consist of 20,667 Moroccan Amazighe tokens chosen from different materials; it is to our knowledge the first one dealing with Amazighe language. The experi...

This article describes how the assemble of several opinion analysis techniques can improve the accuracy or in other NLP problems where the available size of the training corpus is small compared to the space of hypotheses and therefore should be explored a range of strategies. One of the strategies is based in a new way to include morpho-syntactic features to find relationships that traditional...

The verb to like has fallen repeatedly under the gaze of scholars. One aspect which stimulated vigorous discussion is its original use in impersonal constructions and later change argument structure along with disappearance impersonals from English. Nonetheless, evidence current informal English shows that now used bear a close resemblance older impersonals, although always displaying alternati...

Every good piece of writing, fictional or otherwise is marked by a introduction. This initial part the primary provider reader’s first impression that sustains reading. The introduction as well other parts written spoken text essentially realized through specially selected language. In prose fiction, special selections and patterns are hallmarks. paper explores devices style deployed Usman in c...

This paper presents a prosodic phrasing model for Korean to be used in a textto-speech synthesis (TTS) system. Read text corpora were morpho-syntactically parsed and prosodically labeled following the Penn Korean Treebank [Han et al., 2002] and K-ToBI prosodic labeling conventions [Sun-Ah, 2000] respectively. Decision trees were trained with morpho-syntactic and textual distance features to pre...