Paraphrase patterns are useful in paraphrase recognition and generation. In this paper, we present a pivot approach for extracting paraphrase patterns from bilingual parallel corpora, whereby the English paraphrase patterns are extracted using the sentences in a foreign language as pivots. We propose a loglinear model to compute the paraphrase likelihood of two patterns and exploit feature functions based on maximum likelihood estimation (MLE) and lexical weighting (LW). Using the presented method, we extract over 1,000,000 pairs of paraphrase patterns from 2M bilingual sentence pairs, the precision of which exceeds 67%. The evaluation results show that: (1) The pivot approach is effective in extracting paraphrase patterns, which significantly outperforms the conventional method DIRT. Especially, the log-linear model with the proposed feature functions achieves high performance. (2) The coverage of the extracted paraphrase patterns is high, which is above 84%. (3) The extracted paraphrase patterns can be classified into 5 types, which are useful in various applications. 1

Almost all automatic semantic role labeling (SRL) systems rely on a preliminary parsing step that derives a syntactic structure from the sentence being analyzed. This makes the choice of syntactic representation an essential design decision. In this paper, we study the influence of syntactic representation on the performance of SRL systems. Specifically, we compare constituent-based and dependencybased representations for SRL of English in the FrameNet paradigm. Contrary to previous claims, our results demonstrate that the systems based on dependencies perform roughly as well as those based on constituents: For the argument classification task, dependencybased systems perform slightly higher on average, while the opposite holds for the argument identification task. This is remarkable because dependency parsers are still in their infancy while constituent parsing is more mature. Furthermore, the results show that dependency-based semantic role classifiers rely less on lexicalized features, which makes them more robust to domain changes and makes them learn more efficiently with respect to the amount of training data.

Automatic detection of linguistic negation in free text is a critical need for many text processing applications, including sentiment analysis. This paper presents a negation detection system based on a conditional random field modeled using features from an English dependency parser. The scope of negation detection is limited to explicit rather than implied negations within single sentences. A new negation corpus is presented that was constructed for the domain of English product reviews obtained from the open web, and the proposed negation extraction system is evaluated against the reviews corpus as well as the standard BioScope negation corpus, achieving 80.0 % and 75.5 % F1 scores, respectively. The impact of accurate negation detection on a state-of-the-art sentiment analysis system is also reported. 1

Kernel techniques have long been used in SVM to handle linearly inseparable problems by transforming data to a high dimensional space, but training and testing large data sets is often time consuming. In contrast, we can efficiently train and test much larger data sets using linear SVM without kernels. In this work, we apply fast linear-SVM methods to the explicit form of polynomially mapped data and investigate implementation issues. The approach enjoys fast training and testing, but may sometimes achieve accuracy close to that of using highly nonlinear kernels. Empirical experiments show that the proposed method is useful for certain large-scale data sets. We successfully apply the proposed method to a natural language processing (NLP) application by improving the testing accuracy under some training/testing speed requirements.

We introduce a word alignment framework that facilitates the incorporation of syntax encoded in bilingual dependency tree pairs. Our model consists of two sub-models: an anchor word alignment model which aims to find a set of high-precision anchor links and a syntaxenhanced word alignment model which focuses on aligning the remaining words relying on dependency information invoked by the acquired anchor links. We show that our syntaxenhanced word alignment approach leads to a 10.32 % and 5.57 % relative decrease in alignment error rate compared to a generative word alignment model and a syntax-proof discriminative word alignment model respectively. Furthermore, our approach is evaluated extrinsically using a phrase-based statistical machine translation system. The results show that SMT systems based on our word alignment approach tend to generate shorter outputs. Without length penalty, using our word alignments yields statistically significant improvement in Chinese–English machine translation in comparison with the baseline word alignment. 1

We describe here in detail our work toward creating a dynamic lexicon from the texts in a large digital library. By leveraging a small structured knowledge source (a 30,457 word treebank), we are able to extract selectional preferences for words from a 3.5 million word Latin corpus. This is promising news for low-resource languages and digital collections seeking to leverage a small human investment into much larger gain. The library architecture in which this work is developed allows us to query customized subcorpora to report on lexical usage by author, genre or era and allows us to continually update the lexicon as new texts are added to the collection.

We introduce a syntactically enhanced word alignment model that is more flexible than state-of-the-art generative word alignment models and can be tuned according to different end tasks. First of all, this model takes the advantages of both unsupervised and supervised word alignment approaches by obtaining anchor alignments from unsupervised generative models and seeding the anchor alignments into a supervised discriminative model. Second, this model offers the flexibility of tuning the alignment according to different optimisation criteria. Our experiments show that using our word alignment in a Phrase-Based Statistical Machine Translation system yields a 5.38 % relative increase on IWSLT 2007 task in terms of BLEU score. 1

We describe here a collaboration between two separate treebank projects annotating data for the same language (Latin). By working together to create a common standard for the annotation of Latin syntax and sharing our annotated data as it is created, we are each able to rely on the resources and expertise of the other while also ensuring that our data will be compatible in the future. 1

We explore the contribution of morphological features – both lexical and inflectional – to dependency parsing of Arabic, a morphologically rich language. Using controlled experiments, we find that definiteness, person, number, gender, and the undiacritzed lemma are most helpful for parsing on automatically tagged input. We further contrast the contribution of form-based and functional features, and show that functional gender and number (e.g., “broken plurals”) and the related rationality feature improve over form-based features. It is the first time functional morphological features are used for Arabic NLP. 1

Lexical-Functional Grammar (LFG) f-structures (Kaplan and Bresnan, 1982) have attracted some attention in recent years as an intermediate data representation for statistical machine translation. So far, however, there are no alignment tools capable of aligning f-structures directly, and plain word alignment tools are used for this purpose. In this way no use is made of the structural information contained in f-structures. We present the first version of a specialized f-structure alignment open-source software tool. 1