Finally, we compare our proposal with the state of the art estimators (both parametric and nonparametric) on large standard corpora; apart from showing the favorable performance of our estimator, we also see that the classical Good-Turing estimator consistently underestimates the vocabulary size.

We then compared the performance of the proposed estimator with that of the state of the art estimators on large corpora.

In this study we consider state of the art parametric estimators, as surveyed by (Baroni and Evert, 2005).

While compared with other vocabulary size estimates, we see that our estimator performs at least as well as some of the state of the art estimators.

A good survey of the state of the art is available in (Gandolfi and Sastri, 2004).

0 From the Figure 1, we see that our estimator compares quite favorably with the best of the state of the art estimators.

The best of the state of the art estimator is a parametric one (ZM), while ours is a nonparametric estimator.

Further, it compares very favorably to the state of the art estimators (both parametric and nonparametric).

We have presented a simple model that outperforms the prior state of the art on FrameNet-style frame-semantic parsing, and performs at par with one of the previous-best single-parser systems on PropBank SRL.

For FrameNet, the WSABIE EMBEDDING model we propose strongly outperforms the baselines on all metrics, and sets a new state of the art .

In comparison to prior work on FrameNet, even our baseline models outperform the previous state of the art .

This would be a standard NLP approach for the frame identification problem, but is surprisingly competitive with the state of the art .

(2014) describe the state of the art

While comparing with prior state of the art on the same corpus, we noted that Das et al.

First, we show that for frame identification on the FrameNet corpus (Baker et al., 1998; Fillmore et al., 2003), we outperform the prior state of the art (Das et al., 2014).

Second, we present results on PropBank-style semantic role labeling (Palmer et al., 2005; Meyers et al., 2004; Marquez et al., 2008), that approach strong baselines, and are on par with prior state of the art (Punyakanok et al., 2008).

(2010) improved performance, and later set the current state of the art on this task (Das et al., 2014).

We evaluate these models on two cross-lingual document classification tasks, outperforming the prior state of the art .

Coupled with very simple composition functions, vectors learned with this method outperform the state of the art on the task of cross-lingual document classification.

Our models outperform the prior state of the art , with the BI models performing slightly better than the ADD models.

We compare our embeddings with the SENNA embeddings, which achieve state of the art performance on a number of tasks (Collobert et al., 2011).

First, we show that for cross-lingual document classification on the Reuters RCVIRCV2 corpora (Lewis et al., 2004), we outperform the prior state of the art (Klementiev et al., 2012).

They have received a lot of attention in recent years (Collobert and Weston, 2008; Mnih and Hinton, 2009; Mikolov et al., 2010, inter alia) and have achieved state of the art performance in language modelling.

We present a survey of the state of the art in automatic keyphrase extraction, examining the major sources of errors made by existing systems and discussing the challenges ahead.

We have presented a survey of the state of the art in automatic keyphrase extraction.

n: A Survey of the State of the Art

4.2 The State of the Art

Our goal in this paper is to survey the state of the art in keyphrase extraction, examining the major sources of errors made by existing systems and discussing the challenges ahead.

State of the art performance on this set has been reported by Hassan and Mi-halcea (2011) using a technique that exploits the Wikipedia linking structure and word sense disambiguation techniques.

The current state of the art is reached by Halawi et al.

Current state of the art was reached by the window-based count model of Baroni and Lenci (2010).

Indeed, the predictive models achieve an impressive overall performance, beating the current state of the art in several cases, and approaching it in many more.

We report experimental results in AA data sets that confirm that LHs over character n-grams are more helpful for AA than the usual global histograms, yielding results far superior to state of the art approaches.

Our experimental results showed that LHs outperform traditional bag-of-words formulations and state of the art techniques in balanced, imbalanced, and reduced data sets.

The BOLH formulation outperforms state of the art approaches by a considerable margin that ranges from 10% to 27%.

c We report experimental results that are superior to state of the art approaches (Plakias and Stamatatos, 2008b; Plakias and Stamatatos, 2008a), with improvements ranging from 2% — 6% in balanced data sets and from 14% — 30% in imbalanced data sets.

We show that modeling user intent significantly improves entity type resolution for head queries over the state of the art , on several metrics, without degradation in tail query performance.

Jointly modeling the interplay between the underlying user intents and entity types in web search queries shows significant improvements over the current state of the art on the task of resolving entity types in head queries.

We show that jointly modeling user intent and entity type significantly outperforms the current state of the art on the task of entity type resolution in queries.

0 We empirically show that our models outperform the state of the art and that modeling latent intent contributes significantly to these results.

PARMA achieves state of the art results on an existing and a new dataset.

PARMA achieves state of the art performance on three datasets for predicate argument alignment.

We demonstrate the effectiveness of this approach by achieving state of the art performance on the data of Roth and Frank despite having little relevant training data.

On RF, compared to Roth and Frank, the best published method for this task, we also improve, making PARMA the state of the art system for this task.

We will use this gold information also in Section 6.1 to show that our system aligns well to the state of the art on the ACE 2004 benchmark.

To compare our model against the state of the art we use the ACE 2004 data.

We first show that our system aligns well with the state of the art on the ACE 2004 benchmark.

Table 3 shows that our system (bottom) aligns well with the state of the art .

Our ASR system is based on the 2007 IBM Speech transcription system for the GALE Distillation Go/No-go Evaluation (Chen et al., 2006) with state of the art discriminative acoustic models.

(2010), a state of the art broadcast news (BN) parser, with phrase structures converted to labeled dependencies by the Stanford converter.

Discriminative models, which directly distinguish correct from incorrect hypothesis, are particularly attractive because they allow the inclusion of arbitrary features (Kuo et al., 2002; Roark et al., 2007; Collins et al., 2005); these models with syntactic information have obtained state of the art results.

Table 5 summarizes the performance of our models on the chosen tasks, and compares it to the state of the art reported in previous work, as well as to various strong baselines.

For anvanl, plf is just below the state of the art , which is based on disambiguating the verb vector in context (Kartsaklis and Sadrzadeh, 2013), and If outperforms the baseline, which consists in using the verb vector only as a proxy to sentence similarity.5 On anvan2, plf outperforms the best model

5 We report state of the art from Kartsaklis and Sadrzadeh

When compared against current state of the art methods, our model yields significantly simpler output that is both grammatical and meaning preserving.

To evaluate performance, we compare our approach with three other state of the art systems using the test set provided by Zhu et al.

When compared against current state of the art methods (Zhu et al., 2010; Woodsend and Lapata, 2011; Wubben et al., 2012), our model yields significantly simpler output that is both grammatical and meaning preserving.

— Overall, our models compare favourably with the state of the art .

With an additional, unsupervised training step we achieved results beyond the current state of the art on this task, too.

We show that this combination of state of the art machine learning and an advanced linguistic formalism translates into concise models with competitive performance on a variety of tasks.

In addition, we present results for a full system using additional features which achieves close to state of the art performance without resorting to gold syntactic parses or to context outside the relation.

(2009), who used mostly similar features, for comparison and temporal and is competitive with the most recent state of the art systems for contingency and expansion without using any syntactic or context features.

In addition, we present a system which combines these word pairs with additional features to achieve near state of the art performance without the use of syntactic parse features and of context outside the arguments of the relation.

Section 5 explores how the new alignments lead to consistent and significant improvement in a state of the art phrase base machine translation by using posterior decoding rather than Viterbi decoding.

In particular we fix a state of the art machine translation system1 and measure its performance when we vary the supplied word alignments.

These values are competitive with other state of the art systems (Liang et al., 2006).

Using our proposed approach we obtain better scores than the state of the art on the English-Finnish translation task (Luong et al., 2010): from 14.82% BLEU to 15.09%, while using a

Both of these approaches beat the state of the art on the English-Finnish translation task.

Our proposed approaches are significantly better than the state of the art , achieving the highest reported BLEU scores on the English-Finnish Europarl version 3 dataset.

We use this experiment to compare the various topic models as well as the best model with the known state of the art approaches to selectional preferences.

We first compare the three LDA-based approaches to each other and two state of the art similarity based systems (Erk, 2007) (using mutual information and J accard similarity respectively).

Our experiments demonstrate that LDA-SP significantly outperforms state of the art approaches obtaining an 85% increase in recall at precision 0.9 on the standard pseudo-disambiguation task.

Experiments show that our approach improves the state of the art .

Our empirical results improve the state of the art .

Experiments show that our approach improves the state of the art .

Supervised learning algorithms still represent the state of the art approach for inferring dependency parsers from data (McDonald et al., 2005a; McDonald and Pereira, 2006; Wang et al., 2007).

Consequently, most previous work that has attempted semi-supervised or unsupervised approaches to parsing have not produced results beyond the state of the art supervised results (Klein and Manning, 2002; Klein and Manning, 2004).

In recent years, SVMs have demonstrated state of the art results in many supervised learning tasks.

We assess the current state of the art in speech summarization, by comparing a typical summarizer on two different domains: lecture data and the SWITCHBOARD corpus.

The purpose of this paper is not so much to introduce a new way of summarizing speech, as to critically reappraise how well the current state of the art really works.

These four results provide us with valuable insight into the current state of the art in speech summarization: it is not summarization, the aspiration to measure the relative merits of knowledge sources has masked the prominence of some very simple baselines, and the Zechner & Waibel pipe-ASR-output—into-text-summarizer model is still very competitive — what seems to matter more than having access to the raw spoken data is simply knowing that it is spoken data, so that the most relevant, still textually available features can be used.

By letting one model generate features for the other, we consistently improve accuracy for both models, resulting in a significant improvement of the state of the art when evaluated on data sets from the CoNLL-X shared task.

Our experimental results show that both models consistently improve their accuracy when given access to features generated by the other model, which leads to a significant advancement of the state of the art in data-driven dependency parsing.

Finally, given that the two base models had the previously best performance for these data sets, the guided models achieve a substantial improvement of the state of the art .