Articles

Large quantities of data are an increasingly essential resource for many Natural Lan- guage Processing techniques. The Web 1T corpus, a massive resource containing n- gram frequencies produced from one tril- lion words drawn from the World Wide Web, is a relatively new corpus whose size will increase performance on …...

This paper reports on the application of the Text Attribution Tool (TAT) to profiling the authors of Arabic emails. The TAT sys- tem has been developed for the purpose of language-independent author profiling and has now been trained on two email corpora, English and Arabic. We describe the overall TAT …...

The majority of the state-of-the-art ap- proaches to recognizing textual entailment focus on defining a generic approach to RTE. A generic approach never works well for every single entailment pair: there are entailment pairs that are recognized poorly by all the generic systems. Automatic iden- tification of such entailment pairs …...

Near-synonyms are words that mean ap- proximately the same thing, and which tend to be assigned to the same leaf in ontolo- gies such as WordNet. However, they can differ from each other subtly in both mean- ing and usage—consider the pair of near- synonyms frugal and stingy—and therefore choosing …...

Different parsers trained on the same cor- pus deliver different results, both in terms of overall performance and in terms of the individual analyses they provide. In par- ticular, for any given sentence, one parser may provide a correct analysis, while an- other will produce an incorrect analysis; but when …...

Data that has been annotated by linguists is often considered a gold standard on many tasks in the NLP field. However, linguists are expensive so researchers seek automatic techniques that correlate well with human performance. Linguists working on the ScamSeek project were given the task of deciding how many and …...

Evaluation results recently reported by Callison-Burch et al. (2006) and Koehn and Monz (2006), revealed that, in certain cases, the BLEU metric may not be a reliable MT quality indicator. This happens, for in- stance, when the systems under evaluation are based on different paradigms, and there- fore, do not …...

Evaluation and error analysis of machine translation output are important but difficult tasks. In this work, we propose a novel method for obtaining more details about ac- tual translation errors in the generated output by introducing the decomposition of Word Error Rate (WER) and Position independent word Error Rate (PER) …...

This paper studies the impact that difficult-to- translate source-language phrases might have on the machine translation process. We formu- late the notion of difficulty as a measurable quantity; we show that a classifier can be trained to predict whether a phrase might be difficult to translate; and we develop a …...

The paper proposes formulating MT evalu- ation as a ranking problem, as is often done in the practice of assessment by human. Un- der the ranking scenario, the study also in- vestigates the relative utility of several fea- tures. The results show greater correlation with human assessment at the sentence …...

This paper explores the problem of com- puting text similarity between verb phrases describing skilled human behav- ior for the purpose of finding approximate matches. Four parsers are evaluated on a large corpus of skill statements extracted from an enterprise-wide expertise taxon- omy. A similarity measure utilizing com- mon semantic …...

Semantic inference is a key component for advanced natural language under- standing. However, existing collections of automatically acquired inference rules have shown disappointing results when used in applications such as textual en- tailment and question answering. This pa- per presents ISP, a collection of methods for automatically learning admissible ar- …...

Most research on semantic role labeling (SRL) has been focused on training and evaluating on the same corpus in order to develop the technology. This strategy, while appropriate for initiating research, can lead to over-training to the particular corpus. The work presented in this pa- per focuses on analyzing the …...

PropBank has been widely used as train- ing data for Semantic Role Labeling. However, because this training data is taken from the WSJ, the resulting machine learning models tend to overfit on idiosyn- crasies of that text’s style, and do not port well to other genres. In addition, since PropBank …...

In this paper, we present a new string pat- tern matching-based passage ranking al- gorithm for extending traditional text- based QA toward videoQA. Users interact with our videoQA system through natural language questions, while our system re- turns passage fragments with correspond- ing video clips as answers. We collect 75.6 …...

This paper addresses the task of provid- ing extended responses to questions re- garding specialized topics. This task is an amalgam of information retrieval, topical summarization, and Information Extrac- tion (IE). We present an approach which draws on methods from each of these ar- eas, and compare the effectiveness of …...

This paper describes a probabilistic an- swer selection framework for question an- swering. In contrast with previous work using individual resources such as ontolo- gies and the Web to validate answer can- didates, our work focuses on developing a unified framework that not only uses multiple resources for validating answer …...

We introduce an answer typing strategy specific to quantifiable how questions. Us- ing the web as a data source, we auto- matically collect answer units appropri- ate to a given how-question type. Exper- imental results show answer typing with these units outperforms traditional fixed- category answer typing and other strate- …...

We present an efficient, novel two-pass approach to mitigate the computational impact resulting from online intersection of an n-gram language model (LM) and a probabilistic synchronous context-free grammar (PSCFG) for statistical machine translation. In first pass CYK-style decod- ing, we consider first-best chart item ap- proximations, generating a hypergraph of …...

In phrase-based statistical machine transla- tion, the phrase-table requires a large amount of memory. We will present an efficient repre- sentation with two key properties: on-demand loading and a prefix tree structure for the source phrases. We will show that this representation scales well to large data tasks and that …...