Articles

Previous approaches to the task of native language identification (Koppel et al., 2005) have been limited to small, within-corpus evaluations. Because these are restrictive and unreliable, we apply cross-corpus evaluation to the task. We demonstrate the efficacy of lexical features, which had previously been avoided due to the within-corpus topic …...

The emergence of dialogue on social medial neccessitates the development of new dialogue processing models. We argue that to address coherence and to infer the implicatures of social dialogue it is vital to understand the social aspirations of the dialogue participants. One key aspect of understanding social dialogue is to …...

This paper explores the use of Natural Language Generation (NLG) for facilitating the provision of feedback to citizen scientists in the context of a nature conservation programme, BEEWATCH. BEEWATCH aims to capture the distribution of bumblebees, an ecologically and economically important species group in decline, across the UK and beyond. …...

Subjectivity analysis has been actively used in various applications such as opinion mining of customer reviews in online review sites, question-answering in CQA sites, multi-document summarization, etc. However, there has been very little focus on subjectivity analysis in the domain of online forums. Online forums contain huge amounts of user-generated …...

Many parsers learn sparse class distributions over trees to model natural language. Recursive Neural Networks (RNN) use much denser representations, yet can still achieve an F-score of 92.06% for right binarized sentences up to 15 words long. We examine an RNN model by comparing it with an abstract generative probabilistic …...

Statistical post-editing (SPE) of the output produced by rule-based MT (RBMT) systems has been reported to produce extraordinary BLEU (and other automatic evaluation) score improvements. SPE has also been applied to the output of statistical MT (SMT) systems, albeit with more mixed results. We present a statistical post-editing pipeline and …...

The Web is an ever increasing, dynamically changing, multilingual repository of text. There have been several approaches to harvest this repository for bootstrapping, supplementing and adapting data needed for training models in speech and language applications. In this paper, we present semi-supervised and unsupervised approaches to harvesting multilingual text that …...

We describe an automatic paraphrase-inference procedure for a highly inflected language like Arabic. Paraphrases are derived from comparable documents, that is, distinct documents dealing with the same topic. A co-training approach is taken, with two classifiers, one designed to model the contexts surrounding occurrences of paraphrases, and the other trained …...

Supplementary data selection from out-of-domain or related-domain data is a well established technique in domain adaptation of statistical machine translation. The selection criteria for such data are mostly based on measures of similarity with available in-domain data, but not directly in terms of translation quality. In this paper, we present …...

A machine learning mechanism is learned from human annotations in order to perform preference ranking. The mechanism operates on a sentence level and ranks the alternative machine translations of each source sentence. Rankings are decomposed into pairwise comparisons so that binary classifiers can be trained using black-box features of automatic …...

In this article we investigate the translation of financial terms from English into German in the isolation of an ontology vocabulary. For this study we automatically built new domain-specific resources from the translation search engine Linguee and from the online encyclopaedia Wikipedia. Due to the fact that we performed the …...

Online content analysis employs algorithmic methods to identify entities in unstructured text. Both machine learning and knowledge-base approaches lie at the foundation of contemporary named entities extraction systems. However, the progress in deploying these approaches on web-scale has been been hampered by the computational cost of NLP over massive text …...

Unsupervised Relation Extraction (URE) is the task of extracting relations of a priori unknown semantic types using clustering methods on a vector space model of entity pairs and patterns. In this paper, we show that an informed feature generation technique based on dependency trees significantly improves clustering quality, as measured …...

In this paper, we introduce new features for question-answering systems. These features are inspired by the fact that justification of the correct answer (out of many candidate answers) may be present in multiple passages. Our features attempt to combine evidence from multiple passages retrieved for a candidate answer. We present …...

We investigate differences in point of view (POV) between two objective documents, where one is describing the subject matter in a more positive/negative way than the other, and present an automatic method for detecting such POV differences. We use Amazon Mechanical Turk (AMT) to annotate sentences as positive, negative or …...

Though it is generally accepted that language models do not capture all aspects of real language, no adequate measures to quantify their shortcomings have been proposed until now. We will use n-gram models as workhorses to demonstrate that the differences between natural and generated language are indeed quantifiable. More specifically, …...

This paper proposes a method to improve shift-reduce constituency parsing by using lexical de- pendencies. The lexical dependency information is obtained from a large amount of auto-parsed data that is generated by a baseline shift-reduce parser on unlabeled data. We then incorporate a set of novel features defined on this …...

Search log sessions contain a large number of paraphrases contributed by users during query rewriting. However, it is a big challenge to distinguish paraphrases from the simply related queries in the sessions. This paper addresses this problem by making innovative use of user behavior information embodied in query sessions. Specifically, …...

In previous work on unsupervised learning of morphology, the long-tail pattern in the rank-frequency distribution of words, as well as of morphological units, is usually considered as following Zipf’s law (power-law). We argue that these long-tail distributions can also be considered as lognormal. Since we know the conjugate prior distribution …...

With the emergence of community-based question answering (cQA) services, question retrieval has become an integral part of information and knowledge acquisition. Though existing information retrieval (IR) technologies have been found to be successful for document retrieval, they are less effective for question retrieval due to the inherent characteristics of questions, …...