Articles

We present a simple preordering approach for machine translation based on a feature- rich logistic regression model to predict whether two children of the same node in the source-side parse tree should be swapped or not. Given the pair-wise chil- dren regression scores we conduct an effi- cient depth-first branch-and-bound …...

Distributional semantic models (DSMs) have been effective at representing seman- tics at the word level, and research has re- cently moved on to building distributional representations for larger segments of text. In this paper, we introduce novel ways of applying context selection and normalisa- tion to vary model sparsity and …...

Scripts represent knowledge of stereotyp- ical event sequences that can aid text un- derstanding. Initial statistical methods have been developed to learn probabilis- tic scripts from raw text corpora; how- ever, they utilize a very impoverished rep- resentation of events, consisting of a verb and one dependent argument. We present …...

In this paper, we present work on ex- tracting social networks from unstructured text. We introduce novel features de- rived from semantic annotations based on FrameNet. We also introduce novel se- mantic tree kernels that help us improve the performance of the best reported sys- tem on social event detection …...

Translation Memory (TM) systems are one of the most widely used translation technologies. An important part of TM systems is the matching algorithm that de- termines what translations get retrieved from the bank of available translations to assist the human translator. Although detailed accounts of the matching algo- rithms used …...

Paraphrase evaluation is typically done ei- ther manually or through indirect, task- based evaluation. We introduce an in- trinsic evaluation PARADIGM which mea- sures the goodness of paraphrase col- lections that are represented using syn- chronous grammars. We formulate two measures that evaluate these paraphrase grammars using gold standard sentential …...

We present a natural language genera- tion system which supports the incremen- tal specification of ontology-based queries in natural language. Our contribution is two fold. First, we introduce a chart based surface realisation algorithm which supports the kind of incremental process- ing required by ontology-based querying. Crucially, this algorithm avoids …...

Automatically inferring new relations from already existing ones is a way to improve the quality of a lexical network by relation densification and error de- tection. In this paper, we devise such an approach for the JeuxDeMots lexi- cal network, which is a freely avalaible lexical network for French. We …...

We present a French to English transla- tion system for Wikipedia biography ar- ticles. We use training data from out- of-domain corpora and adapt the system for biographies. We propose two forms of domain adaptation. The first biases the system towards words likely in biogra- phies and encourages repetition of …...

This paper presents a methodology to in- fer implicit semantic relations from verb- argument structures. An annotation effort shows implicit relations boost the amount of meaning explicitly encoded for verbs. Experimental results with automatically obtained parse trees and verb-argument structures demonstrate that inferring im- plicit relations is a doable task. …...

We introduce three techniques for improv- ing constituent parsing for morphologi- cally rich languages. We propose a novel approach to automatically find an optimal preterminal set by clustering morphologi- cal feature values and we conduct exper- iments with enhanced lexical models and feature engineering for rerankers. These techniques are specially …...

Statistical parsers trained on labeled data suffer from sparsity, both grammatical and lexical. For parsers based on strongly lexicalized grammar formalisms (such as CCG, which has complex lexical cate- gories but simple combinatory rules), the problem of sparsity can be isolated to the lexicon. In this paper, we show that …...

Automatically inducing the syntactic part- of-speech categories for words in text is a fundamental task in Computational Linguistics. While the performance of unsupervised tagging models has been slowly improving, current state-of-the-art systems make the obviously incorrect as- sumption that all tokens of a given word type must share a single …...

In this paper, we present a series of experiments in which we analyze the usage of graffiti style features for signaling personal gang identification in a large, online street gangs forum, with an accuracy as high as 83% at the gang alliance level and 72% for the specific gang. We …...

We propose a Bayesian method of esti- mating a conditional distribution of data given metadata (e.g., the usage of a di- alectal variant given a location) based on queries from a big data/social me- dia source, such as Twitter. This distri- bution is structurally equivalent to those built from traditional …...

Structured perceptron becomes popular for various NLP tasks such as tagging and parsing. Practical studies on NLP did not pay much attention to its regularization. In this paper, we study three simple but effec- tive task-independent regularization meth- ods: (1) one is to average weights of dif- ferent trained models …...

This paper presents a simple, robust and (almost) unsupervised dictionary-based method, qwn-ppv (Q-WordNet as Person- alized PageRanking Vector) to automati- cally generate polarity lexicons. We show that qwn-ppv outperforms other automat- ically generated lexicons for the four ex- trinsic evaluations presented here. It also shows very competitive and robust results …...

Aspect-based sentiment analysis estimates the sentiment expressed for each particu- lar aspect (e.g., battery, screen) of an en- tity (e.g., smartphone). Different words or phrases, however, may be used to re- fer to the same aspect, and similar as- pects may need to be aggregated at coarser or finer granularities …...

We present an unsupervised method for in- ducing semantic frames from verb uses in giga-word corpora. Our semantic frames are verb-specific example-based frames that are distinguished according to their senses. We use the Chinese Restau- rant Process to automatically induce these frames from a massive amount of verb in- stances. …...

Scripts representing common sense knowledge about stereotyped sequences of events have been shown to be a valu- able resource for NLP applications. We present a hierarchical Bayesian model for unsupervised learning of script knowledge from crowdsourced descriptions of human activities. Events and constraints on event ordering are induced jointly in …...