Wyniki wyszukiwania - BazTech

1

Idiosyncratic frequency as a measure of derivation vs. inflection

Copot Maria, Mickus Timothee, Bonami Olivier

Journal of Language Modelling

|

2022

|

Vol. 10, No. 2

193--240

EN

There is ongoing discussion about how to conceptualize the nature of the distinction between inflection and derivation. A common approach relies on qualitative differences in the semantic relationship between inflectionally versus derivationally related words: inflection yields ways to discuss the same concept in different syntactic contexts, while derivation gives rise to words for related concepts. This differential can be expected to manifest in the predictability of word frequency between words that are related derivationally or inflectionally: predicting the token frequency of a word based on information about its base form or about related words should be easier when the two words are in an inflectional relationship, rather than a derivational one. We compare prediction error magnitude for statistical models of token frequency based on distributional and frequency information of inflectionally or derivationally related words in French. The results conform to expectations: it is easier to predict the frequency of a word from properties of an inflectionally related word than from those of a derivationally related word. Prediction error provides a quantitative, continuous method to explore differences between individual processes and differences yielded by employing different predicting information, which in turn can be used to draw conclusions about the nature and manifestation of the inflection–derivation distinction.

2

Distinguishing between paradigmatic semantic relations across word classes : human ratings and distributional similarity

Schulte im Walde Sabine

Journal of Language Modelling

|

2020

|

Vol. 8, No. 1

53--101

EN

This article explores the distinction between paradigmatic semantic relations, both from a cognitive and a computational linguistic perspective. Focusing on an existing dataset of German synonyms, antonyms and hypernyms across the word classes of nouns, verbs and adjectives, we assess human ratings and a supervised classification model using window-based and pattern-based distributional vector spaces. Both perspectives suggest differences in relation distinction across word classes, but easy vs. difficult class-relation combinations differ, exhibiting stronger ties between ease and naturalness of class-dependent relations for humans than for computational models. In addition, we demonstrate that distributional information is indeed a difficult starting point for distinguishing between paradigmatic relations but that even a simple classification model is able to manage this task. The fact that the most salient vector spaces and their success vary across word classes and paradigmatic relations suggests that combining feature types for relation distinction is better than applying them in isolation.

3

A dependency-based approach to word contextualization using compositional distributional semantics

Gamallo Pablo

Journal of Language Modelling

|

2019

|

Vol. 7, No. 1

99--138

EN

We propose a strategy to build the distributional meaning of sentences mainly based on two types of semantic objects: context vectors associated with content words and compositional operations driven by syntactic dependencies. The compositional operations of a syntactic dependency make use of two input vectors to build two new vectors representing the contextualized sense of the two related words. Given a sentence, the iterative application of dependencies results in as many contextualized vectors as content words the sentence contains. At the end of the contextualization process, we do not obtain a single compositional vector representing the semantic denotation of the whole sentence (or of the root word), but one contextualized vector for each constituent word of the sentence. Our method avoids the troublesome high-order tensor representations of approaches relying on category theory, by defining all words as first-order tensors (i.e. standard vectors). Some corpus-based experiments are performed to both evaluate the quality of the contextualized vectors built with our strategy, and to compare them to other approaches on distributional compositional semantics. The experiments show that our dependency-based method performs as (or even better than) the state-of-the-art.

4

Graded hyponymy for compositional distributional semantics

Bankova D., Coecke B., Lewis M., Marsden D.

Journal of Language Modelling

|

2018

|

Vol. 6, No. 2

225--260

EN

The categorical compositional distributional model of natural language provides a conceptually motivated procedure to compute the meaning of a sentence, given its grammatical structure and the meanings of its words. This approach has outperformed other models in mainstream empirical language processing tasks, but lacks an effective model of lexical entailment. We address this shortcoming by exploiting the freedom in our abstract categorical framework to change our choice of semantic model. This allows us to describe hyponymy as a graded order on meanings, using models of partial information used in quantum computation. Quantum logic embeds in this graded order.

5

German particle verbs : compositionality at the syntax-semantics interface

Bott S., Schulte im Walde S.

Journal of Language Modelling

|

2018

|

Vol. 6, No. 1

41--86

EN

Particle verbs represent a type of multi-word expression composed of a base verb and a particle. The meaning of the particle verb is often, but not always, derived from the meaning of the base verb, sometimes in quite complex ways. In this work, we computationally assess the levels of German particle verb compositionality by applying distributional semantic models. Furthermore, we investigate properties of German particle verbs at the syntax-semantics interface that influence their degrees of compositionality: (i) regularity in semantic particle verb derivation and (ii) transfer of syntactic subcategorization from base verbs to particle verbs. Our distributional models show that both superficial window co-occurrence models as well as theoretically well-founded syntactic models are sensitive to subcategorization frame transfer and can be used to predict degrees of particle verb compositionality, with window models performing better even though they are conceptually and computationally simpler.

6

Text : now in 2D! A framework for lexical expansion with contextual similarity

Biemann C., Riedl M.

Journal of Language Modelling

|

2013

|

Vol. 1, No. 1

55--95

EN

A new metaphor of two-dimensional text for data-driven semantic modeling of natural language is proposed, which provides an entirely new angle on the representation of text: not only syntagmatic relations are annotated in the text, but also paradigmatic relations are made explicit by generating lexical expansions. We operationalize distributional similarity in a general framework for large corpora, and describe a new method to generate similar terms in context. Our evaluation shows that distributional similarity is able to produce high-quality lexical resources in an unsupervised and knowledge-free way, and that our highly scalable similarity measure yields better stores in a WordNet-based evaluation than previous measures for very large corpora. Evaluating on a lexical substitution task, we find that our contextualization method improves over a non-contextualized baseline across all parts of speech, and we show how the metaphor can be applied successfully to part-of-speech tagging. A number of ways to extend and improve the contextualization method within our Framework are discussed. As opposed to comparable approaches, our framework defines a model of lexical expansions in context that can generate the expansions as opposed to ranking a given list, and thus does not require existing lexical-semantic resources.