We show that generation of contextually appropriate syntactic variation can be improved using a model based on automatically extracted features. We adapt a model for predicting dative alternation from (Bresnan et al. 2005); this model incorporates lexical, syntactic, semantic and pragmatic features. We evaluate the effect of using different types of feature on this classification task and show ...

Previous studies have demonstrated that verbs violating selectional constraints of their arguments elicit N400 effects in the event-related potentials (ERPs) in sentence comprehension. The present study examined brain responses to verbs violating semantic constraints specified by syntactic structures (i.e., phrasal constructions), contrasting them with those elicited by lexical-semantic violati...

The Phrase-Based Statistical Machine Translation (PB-SMT) model has recently begun to include source context modeling, under the assumption that the proper lexical choice of an ambiguous word can be determined from the context in which it appears. Various types of lexical and syntactic features such as words, parts-of-speech, and supertags have been explored as effective source context in SMT. ...

We present a classifier to predict contextual polarity of subjective phrases in a sentence. Our approach features lexical scoring derived from the Dictionary of Affect in Language (DAL) and extended through WordNet, allowing us to automatically score the vast majority of words in our input avoiding the need for manual labeling. We augment lexical scoring with n-gram analysis to capture the effe...

Question Classification is an important task in Question Answering Systems. This paper presents a Spanish Question Classifier based on machine learning, automatic online translators and different language features. Our system works with English collections and bilingual questions (English/Spanish). We have tested two Spanish-English online translators to identify the lost of precision. We have ...

This paper describes the SyntaLex entries in the English Lexical Sample Task of SENSEVAL-3. There are four entries in all, where each of the different entries corresponds to use of word bigrams or Part of Speech tags as features. The systems rely on bagged decision trees, and focus on using pairs of lexical and syntactic features individually and in combination. They are descendants of the Dulu...

In this work, we explore the use of SVMs and CRFs in the problem of predicting certainty in sentences. We consider this as a task of tagging uncertainty cues in context, for which we used lexical, wordlist-based and deep-syntactic features. Results show that the syntactic context of the tokens in conjunction with the wordlist-based features turned out to be useful in predicting uncertainty cues.

In this paper we present the results of experiments comparing (a) rich syntactic and semantic feature sets and (b) big context windows, for the TempEval time expression and event segmentation and classification tasks. We show that it is possible for models using only lexical features to approach the performance of models using rich syntactic and semantic feature sets.

In this paper we explore the identification of negated molecular events (e.g. protein binding, gene expressions, regulation, etc.) in biomedical research abstracts. We construe the problem as a classification task and apply a machine learning (ML) approach that uses lexical, syntactic, and semantic features associated with sentences that represent events. Lexical features include negation cues,...