Articles

Language can describe our visual world at many levels, including not only what is lit- erally there but also the sentiment that it in- vokes. In this paper, we study visual language, both literal and sentimental, that describes the overall appearance and style of virtual char- acters. Sentimental properties, including …...

Feature and context aggregation play a large role in current NER systems, allowing significant opportunities for research into op- timizing these features to cater to different domains. This work strives to reduce the noise introduced into aggregated features from dis- parate and generic training data in order to al- low …...

This paper presents a general, statistical framework for modeling phrase translation via Markov random fields. The model al- lows for arbituary features extracted from a phrase pair to be incorporated as evidence. The parameters of the model are estimated using a large-scale discriminative training approach that is based on stochastic …...

This paper describes an approach to improve summaries for a collection of Twitter posts cre- ated using the Phrase Reinforcement (PR) Al- gorithm (Sharifi et al., 2010a). The PR algo- rithm often generates summaries with excess text and noisy speech. We parse these sum- maries using a dependency parser and …...

We provide an approximation algorithm for PCFG parsing, which asymptotically im- proves time complexity with respect to the in- put grammar size, and prove upper bounds on the approximation quality. We test our algo- rithm on two treebanks, and get significant im- provements in parsing speed. 1...

Advances in sentiment analysis have enabled extraction of user relations implied in online textual exchanges such as forum posts. How- ever, recent studies in this direction only con- sider direct relation extraction from text. As user interactions can be sparse in online dis- cussions, we propose to apply collaborative filtering …...

We consider the problem of part-of-speech tagging for informal, online conversational text. We systematically evaluate the use of large-scale unsupervised word clustering and new lexical features to improve tagging accuracy. With these features, our system achieves state-of-the-art tagging results on both Twitter and IRC POS tagging tasks; Twitter tagging is …...

We describe a new self-learning framework for parser lexicalisation that requires only a plain-text corpus of in-domain text. The method first creates augmented versions of de- pendency graphs by applying a series of mod- ifications designed to directly capture higher- order lexical path dependencies. Scores are assigned to each edge …...

Online learning algorithms such as perceptron and MIRA have become popular for many NLP tasks thanks to their simpler architec- ture and faster convergence over batch learn- ing methods. However, while batch learning such as CRF is easily parallelizable, online learning is much harder to parallelize: previ- ous efforts often …...

The rise of social media has brought compu- tational linguistics in ever-closer contact with bad language: text that defies our expecta- tions about vocabulary, spelling, and syntax. This paper surveys the landscape of bad lan- guage, and offers a critical review of the NLP community’s response, which has largely fol- …...

Modern Standard Arabic (MSA) has a wealth of natural language processing (NLP) tools and resources. In comparison, resources for dialectal Arabic (DA), the unstandardized spo- ken varieties of Arabic, are still lacking. We present ELISSA, a machine translation (MT) system for DA to MSA. ELISSA employs a rule-based approach that …...

Until recently, the application of discrimina- tive training to log linear-based statistical ma- chine translation has been limited to tuning the weights of a limited number of features or training features with a limited number of pa- rameters. In this paper, we propose to scale up discriminative training of (He …...

Recent work has shown that word aligned data can be used to learn a model for reordering source sentences to match the target order. This model learns the cost of putting a word immediately before another word and finds the best reordering by solving an instance of the Traveling Salesman …...

Translation models in statistical machine translation can be scaled to large corpora and arbitrarily-long phrases by looking up translations of source phrases “on the fly” in an indexed parallel corpus using suffix arrays. However, this can be slow because on-demand extraction of phrase tables is computationally expensive. We address this …...

This paper describes the annotation process and linguistic properties of the Persian syn- tactic dependency treebank. The treebank consists of approximately 30,000 sentences annotated with syntactic roles in addition to morpho-syntactic features. One of the unique features of this treebank is that there are al- most 4800 distinct verb lemmas …...

Multi-Sentence Compression (MSC) is the task of generating a short single sentence sum- mary from a cluster of related sentences. This paper presents an N-best reranking method based on keyphrase extraction. Compression candidates generated by a word graph-based MSC approach are reranked according to the number and relevance of keyphrases …...

Language variations are generally known to have a severe impact on the performance of Human Language Technology Systems. In or- der to predict or improve system performance, a thorough investigation into these variations, similarities and dissimilarities, is required. Distance measures have been used in several applications of speech processing to …...

We here present and compare two unsuper- vised approaches for inducing the main con- ceptual information in rather stereotypical summaries in two different languages. We evaluate the two approaches in two differ- ent information extraction settings: mono- lingual and cross-lingual information extrac- tion. The extraction systems are trained on auto-annotated …...

Measuring term informativeness is a funda- mental NLP task. Existing methods, mostly based on statistical information in corpora, do not actually measure informativeness of a term with regard to its semantic context. This pa- per proposes a new lightweight feature-free approach to encode term informativeness in context by leveraging web …...

We introduce a new large-scale discrimina- tive learning algorithm for machine translation that is capable of learning parameters in mod- els with extremely sparse features. To ensure their reliable estimation and to prevent over- fitting, we use a two-phase learning algorithm. First, the contribution of individual sparse fea- tures is …...