In order to compare the performance of the learned policy with hand-coded REG policies, three simple rule-based policies were built.

The results show that using our RL framework, REG policies can be learned using data-driven simulations, and that such a policy can predict and adapt to a user’s knowledge pattern more accurately than policies trained using hand-coded rule-based simulations and hand-coded baseline policies.

Rule-based and superVised learning approaches to user adaptation in SDS have been proposed earlier (Cawsey, 1993; Akiba and Tanaka, 1994).

We also compared the performance of policies learned using a hand-coded rule-based simulation and a data-driven statistical simulation and show that data-driven simulations produce better policies than rule-based ones.

Rule-based and supervised learning approaches have been proposed to learn and adapt during the conversation dynamically.

It is also not clear how supervised and rule-based approaches choose between when to seek more information and when to adapt.

Earlier, we reported a proof-of-concept work using a hand-coded rule-based user simulation (J anarthanam and Lemon, 2009c).

We used two kinds of action selection models: corpus-driven statistical model and hand-coded rule-based model.

5.2 Rule-based action selection model

We also built a rule-based simulation using the above models but where some of the parameters were set manually instead of estimated from the data.

Another line of work has produced handcrafted rule-based systems to control specific stylistic dimensions, such as politeness and personality.

We compare our performance to a rule-based generator in the same domain.

Q3: How does PERSONAGE-PE compare to PERSONAGE, a psychologically-informed rule-based generator for projecting extreme personality?

comparison with rule-based results in Section 3.3 suggests that this is not because conscientiousness cannot be exhibited in our domain or manifested in a single utterance, so perhaps this arises from differing perceptions of conscientiousness between the expert and naive judges.

3.3 Comparison with Rule-Based Generation PERSONAGE is a rule-based personality generator based on handcrafted parameter settings derived from psychological studies.

Langkilde and Knight (1998) first applied SLMs to statistical natural language generation (SNLG), showing that high quality paraphrases can be generated from an underspecified representation of meaning, by first applying a very undercon-strained, rule-based overgeneration phase, whose outputs are then ranked by an SLM scoring phase.

In previous work, we presented PERSONAGE, a psychologically-informed rule-based generator based on the Big Five personality model, and we showed that PERSONAGE can project extreme personality on the extraversion scale, i.e.

Section 3.2 shows that humans accurately perceive the intended variation, and Section 3.3 compares PERSONAGE-PE (trained) with PERSONAGE ( rule-based ; Mairesse and Walker, 2007).

We test a Naive Bayes classifier (NB), a j48 decision tree (J48), a nearest-neighbor classifier using one neighbor (NN), a Java implementation of the RIPPER rule-based learner (J RIP), the AdaBoost boosting algorithm (ADA), and a support vector machines classifier with a linear kernel (SVM).

This paper describes a rule-based framework for inducing derivational families (i.e., clusters of lemmas in derivational relationships) and its application to create a high-coverage German resource, DERIVBASE, mapping over 280k lemmas into more than 17k non-singleton clusters.

In this paper, we present DERIVBASE, a derivational resource for German based on a rule-based framework.

In this section, we describe our rule-based model of derivation, its operation to define derivational families, and the application of the model to German.

As German is a morphologically complex language, we analyzed its derivation processes before implementing our rule-based model.

3.2 A Rule-based Derivation Model

Instead, we employ a rule-based framework to define derivation rules that cover both suffixation and prefixation and describes stem changes.

Unsupervised approaches operate at the level of word-forms and have complementary strengths and weaknesses to rule-based approaches.

Its R-SU4 score is also significantly (p < 0.01) better than extractive methods, rule-based and sequence-based compression methods on both DUC 2006 and 2007.

For grammatical relation evaluation, our head-driven tree-based system obtains statistically significantly (p < 0.01) better Fl score (Rel-F1 than all the other systems except the rule-based system).

Below we describe the sentence compression approaches developed in this research: RULE-BASED COMPRESSION, SEQUENCE—BASED COMPRESSION, and TREE-BASED COMPRESSION.

4.1 Rule-based Compression

Our rule-based approach extends existing work (Conroy et al., 2006; Toutanova et al., 2007) to create the linguistically-motivated compression rules of Table 2.

Rule-Based Features

0 GUTime (Mani and Wilson, 2000), a widely used, older rule-based system.

o SUTime (Chang and Manning, 2012), a more recent rule-based system for English.

o UC3M (Vicente-Diez et al., 2010), a rule-based system for Spanish.

Many approaches to this problem make use of rule-based methods, combining regular-expression matching and handwritten interpretation functions.

dynamically back off to a rule-based system in the case of low confidence parses.

A rule-based number recognizer was used for each language to recognize and ground numeric expressions, including information on whether the number was an ordinal (e.g., two versus second).

In this section we compare our statistical methods with the preprocessing method and the rule-based methods for measure word generation in a translation task.

We also compared our method with a well-known rule-based machine translation system —SYSTRAN3.

Most existing rule-based English-to-Chinese MT systems have a dedicated module handling measure word generation.

In general a rule-based method uses manually constructed rule patterns to predict measure words.

These methods reach a level comparable to or better than the state-of—the-art rule-based systems (e.g.

On the other hand, rule-based methods derived from theoretical background such as Centering Theory (Grosz et al., 1995) only deal with the salient discourse entities at each point of the discourse status.

Early methods for zero-anaphora resolution were developed with rule-based approaches in mind.

Theory-oriented rule-based methods (Kameyama, 1986; Walker et al., 1994), for example, focus on the Centering Theory (Grosz et al., 1995) and are designed to collect the salient candidate antecedents in the forward-looking center (Cf) list, and then choose the most salient candidate, Cp, as an antecedent of a zero-pronoun according to heuristic rules (e.g.

Rule-based methods: Rule-based PG methods build on a set of paraphrase rules or patterns, which are either hand crafted or automatically collected.

In the early rule-based PG research, the paraphrase rules are generally manually written (McKeown, 1979; Zong et al., 2001), which is expensive and arduous.

Some researchers then tried to automatically extract paraphrase rules (Lin and Pantel, 2001; Barzilay and Lee, 2003; Zhao et al., 2008b), which facilitates the rule-based PG methods.

As information extraction (IE) becomes more central to enterprise applications, rule-based IE engines have become increasingly important.

In this paper, we describe SystemT, a rule-based IE system whose basic design removes the expressivity and performance limitations of current systems based on cascading grammars.

In recent years, these systemic requirements have led to renewed interest in rule-based IE systems (Doan et al., 2008; SAP, 2010; IBM, 2010; SAS, 2010).

Until recently, rule-based IE systems (Cunningham et al., 2000; Boguraev, 2003; Drozdzynski et al., 2004) were predominantly based on the cascading grammar formalism exemplified by the

\ P l R \ F Rule-based baseline 0.85 0.10 0.18 Supervised 0.62 0.28 0.39

For a baseline, we consider a rule-based model that simply learns all ngram segmentations seen in the training data, and marks any occurrence of a matching token sequence as a motif; without taking neighbouring context into account.

However, the rule-based method has a very row recall due to lack of generalization capabilities.

Also, it achieves the best ever performance on a common testbed, beating the top-performer of the 2007 CMC Challenge, a handcrafted rule-based system.

Our second baseline is a symbolic system, designed to evaluate the quality of our rule-based components when used alone.

Table 3: Micro-averaged Fl-scores for statistical and symbolic baselines, the proposed LT-HMM approach, and the best CMC handcrafted rule-based system.

Several teams, including the winner, built pure symbolic (i.e., handcrafted rule-based ) systems (e.g., (Goldstein et al., 2007)).

In order to reduce the confounding variables, we kept the ordering of content in all systems the same, by adopting the ordering of the rule-based system.

Rule-based System: generates summaries based on Content Selection rules derived by working with a L&T expert and a student (Gkatzia et al., 2013).

Development of time-series generation systems (Section 4.2, Section 5.3): ML system, RL system, Rule-based and Random system 5.

from left to right: ML system, RL, rule-based and randor.

3.1 Rule-Based Segmentation Algorithm

Algorithm 1 Rule-based segmentation.

For each sentiment, the Triple Extractor (TE) extracts candidate dependency relation triples using a novel rule-based approach.

While rule-based approaches provide a natural way to express expert knowledge, it is relatively difficult to en-

general, many different rule-based systems, e.g.

However, rule-based approaches dominated in resolution; none of the top performers attempted to learn to do resolution.

Work on rule-based natural language generation (NLG) has explored a number of ways to combine these decisions in an architecture, ranging from integrated systems where all decisions happen jointly (Appelt, 1982) to strictly sequential pipelines (Reiter and Dale, 1997).

Such a system is reminiscent of earlier work in rule-based generation that implements an interactive or revision-based feedback between discourse-level planning and linguistic realisation (Hovy, 1988; Robin, 1993).

In rule-based , strictly sequential generators these interactions can lead to a so-called generation gap, where a downstream module cannot realize a text or sentence plan generated by the preceding modules (Meteer, 1991; Wanner, 1994).

For that we perform subjectivity and polarity classification using rule-based classifiers6 on the test data E-TEST, S-TEST and R-TEST.

We consider how the various lexicons perform for rule-based classifiers for both subjectivity and polarity.

6Similar approach to a rule-based classification using terms from he MPQA lexicon (Riloff and Wiebe, 2003).

RULE-BASED : The method that regards only nuclei satisfying the constraint in Table l as problem nuclei.

The rule-based method achieved relatively high precision despite of the low recall, demonstrating the importance of problem and aid nuclei formulations described in Section 1.

RULE-BASED : The method that judges only problem-aid nuclei combinations with opposite excitation polarities as proper matches.

First, we compare the automatically learned verb classes to a preexisting ontology and handcrafted verb patterns from TABARI,1 an open-source and widely used rule-based event extraction system for this domain.

Beginning in the mid-19808, political scientists began experimenting with automated rule-based extraction systems (Schrodt and Gerner, 1994).

These efforts culminated in the open-source program, TABARI, which uses pattern matching from extensive hand-developed phrase dictionaries, combined with basic part of speech tagging (Schrodt, 2001); a rough analogue in the information extraction literature might be the rule-based , finite-state FASTUS system for MUC IE (Hobbs et al., 1997), though TABARI is restricted to single sentence analysis.

With the advent of machine learning and the availability of annotated corpora in the mid 1990s the research focus shifted from rule-based approaches to supervised machine learning techniques.

Quite recently, however, rule-based approaches regained popularity due to Stanford’s multi-pass sieve approach which exhibits state-of-the-art performance on many standard coreference data sets (Raghunathan et al., 2010) and also won the CoNLL-2011 shared task on coreference resolution (Lee et al., 2011; Pradhan et al., 2011).

These results show that carefully crafted rule-based systems which employ suitable inference schemes can achieve competitive performance.

The small size of our corpus, with around 375 bilingual sentences, posed a large challenge to the use of statistical methods; on the other hand, having no access to a LIS speaker prevented us from simply relying on a rule-based approach.

Still, it is a very small corpus, hence the main project shied away from statistical NLP techniques, relying instead on rule-based approaches developed with the help of a native ItaliarflLIS bilingual speaker; a similar approach is taken e.g.

Because the translation pipeline we plan to integrate with is rule-based , we chose a Decision Tree as our classifier: this allows rules to be easily extracted from the classification model.

It follows that approaches to document planning are rule-based as well and, concomitantly, are usually domain specific.

Further, statistical approaches should be more adaptable to different domains than their rule-based equivalents (Angeli et al., 2012).

This is an encouraging result considering that no experts were involved in the development of the system -a key contrast to many other existing (especially rule-based ) NLG systems.

Previous work on speaker identification includes both rule-based and machine-learning approaches.

The rule-based methods are typically characterized by low coverage, and are too brittle to be reliably applied to different domains and changing styles.

(2010) implement a rule-based system to enrich German cabinet protocols with automatic speaker attribution.

Our study reached two important conclusions: first, given the same data as input, an unsupervised probabilistic model can outperform a handcrafted rule-based SCF extractor with a predefined inventory.

As with tGRs, the closed-class tags can be lexicalized, but there are no corresponding feature sets for param (since they are already built from POS tags) or lim (since there is no similar rule-based approach).

Table 4: Task-based evaluation of leXicons acquired with each of the eight feature types, and the state-of-the-art rule-based VALEX lexicon.

We will argue that the automatic identification of generic expressions should be cast as a machine learning problem instead of a rule-based approach, as there is (i) no transparent marking of genericity in English (as in most other European languages) and (ii) the phenomenon is highly context dependent.

Suh (2006) applied a rule-based approach to automatically identify generic noun phrases.

Lexical semantic factors, such as the semantic type of the clause predicate (5.c,e), or “well-established” kinds (5.g) may favour a generic reading, but such lexical factors are difficult to capture in a rule-based setting.

Compared to the within-event-type rules, the cross-event model yields much more improvement for trigger classification: rule-based propagation gains 1.7% improvement while the cross-event model achieves a further 7.3% improvement.

For argument and role classification, the cross-event model also gains 3% and 2.3% above that obtained by the rule-based propagation process.

Ji and Grishman (2008) were inspired from the hypothesis of “One Sense Per Discourse” (Yarowsky, 1995); they extended the scope from a single document to a cluster of topic-related documents and employed a rule-based approach