Robust, applied morphological generation

Minnen, Guido; Carroll, John; Pearce, Darren

doi:10.3115/1118253.1118281

Cited by 46 publications

(32 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…That is, does it make a difference whether we use the words in the sentence, the words in the noun groups, the words in the verb groups, or the words in the respective heads of the groups to determine coherence? (The units are obtained by processing the documents using the LT-TTT2 tools (Grover and Tobin, 2006); the lemmatizer used by LT-TTT2 is morpha (Minnen and Pearce, 2000).) We also consider whether lemmatization is beneficial in each of the granularities.…”

Section: Methodsmentioning

confidence: 99%

Domain-independent shallow sentence ordering

Nahnsen

2009

Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Com

View full text Add to dashboard Cite

We present a shallow approach to the sentence ordering problem. The employed features are based on discourse entities, shallow syntactic analysis, and temporal precedence relations retrieved from VerbOcean. We show that these relatively simple features perform well in a machine learning algorithm on datasets containing sequences of events, and that the resulting models achieve optimal performance with small amounts of training data. The model does not yet perform well on datasets describing the consequences of events, such as the destructions after an earthquake.

show abstract

Section: Methodsmentioning

confidence: 99%

Domain-independent shallow sentence ordering

Nahnsen

2009

Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Com

View full text Add to dashboard Cite

show abstract

“…We performed part-of-speech tagging (Tsuruoka and Tsujii 2005) and lemmatization (Minnen et al 2000) of the text before extracting the reciprocal verb pairs. Our data contain 1,608 unique verbs.…”

Section: Data Collectionmentioning

confidence: 99%

Modeling reciprocity in social interactions with probabilistic latent space models

Gîrju¹,

Paul²

2011

Nat. Lang. Eng.

View full text Add to dashboard Cite

Reciprocity is a pervasive concept that plays an important role in governing people's behavior, judgments, and thus their social interactions. In this paper we present an analysis of the concept of reciprocity as expressed in English and a way to model it. At a larger structural level the reciprocity model will induce representations and clusters of relations between interpersonal verbs. In particular, we introduce an algorithm that semi-automatically discovers patterns encoding reciprocity based on a set of simple yet effective pronoun templates. Using the most frequently occurring patterns we queried the web and extracted 13,443 reciprocal instances, which represent a broad-coverage resource. Unsupervised clustering procedures are performed to generate meaningful semantic clusters of reciprocal instances. We also present several extensions (along with observations) to these models that incorporate metaattributes like the verbs' affective value, identify gender differences between participants, consider the textual context of the instances, and automatically discover verbs with certain presuppositions. The pattern discovery procedure yields an accuracy of 97 per cent, while the clustering procedures -clustering with pairwise membership and clustering with transitionsindicate accuracies of 91 per cent and 64 per cent, respectively. Our affective value clustering can predict an unknown verb's affective value (positive, negative, or neutral) with 51 per cent accuracy, while it can discriminate between positive and negative values with 68 per cent accuracy. The presupposition discovery procedure yields an accuracy of 97 per cent.

show abstract

“…Perez Aguiar has used an intuitive pattern-matching approach for developing morphological generator to Spanish language. Guido Minnen and his team have developed a morphological generator based on Finite state techniques and it is implemented using the widely available Unix Flex utility [5].…”

Section: Related Workmentioning

confidence: 99%

A Novel Data Driven Algorithm for Tamil Morphological Generator

Kumar¹,

Rekha²,

Soman³

et al. 2010

IJCA

View full text Add to dashboard Cite

Tamil is a morphologically rich language with agglutinative nature. Being agglutinative language most of the word features are postpositionally affixed to the root word. The morphological generator takes lemma, POS category and morpho-lexical description as input and gives a word-form as output. It is a reverse process of morphological analyzer. In any natural language generation system, morphological generator is an essential component in post processing stage. Morphological generator system implemented here is based on a new algorithm, which is simple, efficient and does not require any rules and morpheme dictionary. A paradigm classification is done for noun and verb based on Dr.S.Rajendran's paradigm classification. Tamil verbs are classified into 32 paradigms with 1884 inflected forms. Like verbs, nouns are classified into 25 paradigms with 325 word forms. This approach requires only minimum amount of data. So this approach can be easily implemented to less resourced and morphologically rich languages.

show abstract

Robust, applied morphological generation

Cited by 46 publications

References 13 publications

Domain-independent shallow sentence ordering

Domain-independent shallow sentence ordering

Modeling reciprocity in social interactions with probabilistic latent space models

A Novel Data Driven Algorithm for Tamil Morphological Generator

Contact Info

Product

Resources

About