Artificial Sentences Research Articles

Automatic Generation of Literary Sentences in French

In this paper, we describe a model for the automatic generation of literary sentences in French. Although there has been much recent effort directed towards automatic text generation in general, the generation of creative, literary sentences that is not restricted to a specific genre, which we approached in this work, is a difficult task that is not commonly treated in the scientific literature. In particular, our present model has not been previously applied to the generation of sentences in the French language. Our model was based on algorithms that we previously used to generate sentences in Spanish and Portuguese and on a new corpus, which we constructed and present here, consisting of literary texts in French, called MegaLitefr. Our automatic text generation algorithm combines language models, shallow parsing, the canned text method, and deep learning artificial neural networks. We also present a manual evaluation protocol that we propose and implemented to assess the quality of the artificial sentences generated by our algorithm, by testing if they fulfil four simple criteria. We obtained encouraging results from the evaluators for most of the desired features of our artificially generated sentences.

The Emergence of Argument Structure in Artificial Languages

Abstract Computational approaches to the study of language emergence can help us understand how natural languages are shaped by cognitive and sociocultural factors. Previous work focused on tasks where agents refer to a single entity. In contrast, we study how agents predicate, that is, how they express that some relation holds between several entities. We introduce a setup where agents talk about a variable number of entities that can be partially observed by the listener. In the presence of a least-effort pressure, they tend to discuss only entities that are not observed by the listener. Thus we can obtain artificial phrases that denote a single entity, as well as artificial sentences that denote several entities. In natural languages, if we ignore the verb, phrases are usually concatenated, either in a specific order or by adding case markers to form sentences. Our setup allows us to quantify how much this holds in emergent languages using a metric we call concatenability. We also measure transitivity, which quantifies the importance of word order. We demonstrate the usefulness of this new setup and metrics for studying factors that influence argument structure. We compare agents having access to input representations structured into pre-segmented objects with properties, versus unstructured representations. Our results indicate that the awareness of object structure yields a more natural sentence organization.

Semantic key generation based on natural language

In recent years, the public has become more aware of security concerns, and the demand for convenient and efficient encryption technology has increased. Biological data is used in identity authentication and key generation as the innate characteristic information of people. Biological key have the advantage of convenience and fast application without carrying any document; however, they also have the disadvantage of biological characteristic leaks and the inability to change. Based on the advantages and disadvantages of biological key, we propose the concept of semantic key. Language, a medium that fills the lives of people, has similar characteristics of convenience and fast application as biological key; however, semantic key will not reveal biological information. As the amount of semantic information is large, it can be changed at any time. Compared with biological key, it provides better security and flexibility. Therefore, we propose a semantic key generation framework of semantic extraction + feature stabilization + fuzzy extraction that improves the existing semantic extraction model and feature stabilization model and design the semantic key extraction model. In terms of artificial sentence formation, semantic key can be extracted with an accuracy of more than 99%, and an error rate of less than 0.5%.

Neural machine translation of clinical texts between long distance languages.

To analyze techniques for machine translation of electronic health records (EHRs) between long distance languages, using Basque and Spanish as a reference. We studied distinct configurations of neural machine translation systems and used different methods to overcome the lack of a bilingual corpus of clinical texts or health records in Basque and Spanish. We trained recurrent neural networks on an out-of-domain corpus with different hyperparameter values. Subsequently, we used the optimal configuration to evaluate machine translation of EHR templates between Basque and Spanish, using manual translations of the Basque templates into Spanish as a standard. We successively added to the training corpus clinical resources, including a Spanish-Basque dictionary derived from resources built for the machine translation of the Spanish edition of SNOMED CT into Basque, artificial sentences in Spanish and Basque derived from frequently occurring relationships in SNOMED CT, and Spanish monolingual EHRs. Apart from calculating bilingual evaluation understudy (BLEU) values, we tested the performance in the clinical domain by human evaluation. We achieved slight improvements from our reference system by tuning some hyperparameters using an out-of-domain bilingual corpus, obtaining 10.67 BLEU points for Basque-to-Spanish clinical domain translation. The inclusion of clinical terminology in Spanish and Basque and the application of the back-translation technique on monolingual EHRs significantly improved the performance, obtaining 21.59 BLEU points. This was confirmed by the human evaluation performed by 2 clinicians, ranking our machine translations close to the human translations. We showed that, even after optimizing the hyperparameters out-of-domain, the inclusion of available resources from the clinical domain and applied methods were beneficial for the described objective, managing to obtain adequate translations of EHR templates. We have developed a system which is able to properly translate health record templates from Basque to Spanish without making use of any bilingual corpus of clinical texts or health records.

Distributed representation of word by using Elman network

This paper presents a novel training method for Elman network to encode the words in literary works. This network has been used in studying limited simple artificial sentences with varying degrees of success. This paper shows how to use it to process real-world works. Both word codes and network weights can be accomplished by the method. Each trained code is a distributed representation of its word. The training error can be drastically reduced by iteratively re-encoding the representations. Several distinct findings and results during the training process are reported.

Semantics boosts syntax in artificial grammar learning tasks with recursion.

Center-embedded recursion (CER) in natural language is exemplified by sentences such as "The malt that the rat ate lay in the house." Parsing center-embedded structures is in the focus of attention because this could be one of the cognitive capacities that make humans distinct from all other animals. The ability to parse CER is usually tested by means of artificial grammar learning (AGL) tasks, during which participants have to infer the rule from a set of artificial sentences. One of the surprising results of previous AGL experiments is that learning CER is not as easy as had been thought. We hypothesized that because artificial sentences lack semantic content, semantics could help humans learn the syntax of center-embedded sentences. To test this, we composed sentences from 4 vocabularies of different degrees of semantic content due to 3 factors (familiarity, meaning of words, and semantic relationship between words). According to our results, these factors have no effect one by one but they make learning significantly faster when combined. This leads to the assumption that there were different mechanisms at work when CER was parsed in natural and in artificial languages. This finding questions the suitability of AGL tasks with artificial vocabularies for studying the learning and processing of linguistic CER.

Parsing recursive sentences with a connectionist model including a neural stack and synaptic gating

It is supposed that humans are genetically predisposed to be able to recognize sequences of context-free grammars with centre-embedded recursion while other primates are restricted to the recognition of finite state grammars with tail-recursion. Our aim was to construct a minimalist neural network that is able to parse artificial sentences of both grammars in an efficient way without using the biologically unrealistic backpropagation algorithm. The core of this network is a neural stack-like memory where the push and pop operations are regulated by synaptic gating on the connections between the layers of the stack. The network correctly categorizes novel sentences of both grammars after training. We suggest that the introduction of the neural stack memory will turn out to be substantial for any biological ‘hierarchical processor’ and the minimalist design of the model suggests a quest for similar, realistic neural architectures.

Negation

The paper is concerned with negation in artificial and natural languages. "Negation" is an ambiguous word. It can mean three different things: An operation(negating), an operator (a sign of negation), the result of an operation. The threethings, however, are intimately linked. An operation such as negation, is realizedthrough an operator of negation, i.e. consists in adding a symbol of negation to an entity to obtain an entity of the same type; and which operation it is dependson what it applies to and on what results from its application. I argue that negation is not an operation on linguistic acts but rather anoperation on the objects of linguistic acts, namely sentences. And I assume that the negation of a sentence is a sentence that contradicts it. If so, the negation of a sentence may be obtained, in case the sentence is molecular, by applying the operation of negation not to the sentence itself but to a constituent sentence. To put it in a succinct and paradoxically sounding way we could say that in order to negate a sentence it is sufficient but not necessary to negate it. However that negation applies to sentences is true only for artificial languages, in which the sign of negation is a monadic sentential connective. In natural language, negation applies to expressions other than sentences, namely word sand non-sentential phrases. Still words and not sentential phrases are interesting and valuable only as ultimate or immediate constituents of sentences, as a means of saying (something that can be true or false) and the concern with negation is ultimately the concern with the negation of sentences. So the problem is what sub-sentential and non sentential expressions negation should apply to in order to obtain the negation of the containing sentence. The standard answer is that the negation of a natural language sentence is equivalent to the negation of its predicate. Yet, I argue, predicate negation is necessary but not sufficient, due to the existence of molecular sentences. Finally I notice that if to apply negation to an artificial sentence is to put the negation sign in front of it, to negate the predicate of a natural language sentencemay or may not be to put the negation sign in front of it.

Neural Network Simulation of Infant Familiarization to Artificial Sentences: Rule-Like Behavior Without Explicit Rules and Variables.

A fundamental issue in cognitive science is whether human cognitive processing is better explained by symbolic rules or by subsymbolic neural networks. A recent study of infant familiarization to sentences in an artificial language seems to have produced data that can only be explained by symbolic rule learning and not by unstructured neural networks (Marcus, Vijayan, Bandi Rao, & Vishton, 1999). Here we present successful unstructured neural network simulations of the infant data, showing that these data do not uniquely support a rule-based account. In contrast to other simulations of these data, these simulations cover more aspects of the data with fewer assumptions about prior knowledge and training, using a more realistic coding scheme based on sonority of phonemes. The networks show exponential decreases in attention to a repeated sentence pattern, more recovery to novel sentences inconsistent with the familiar pattern than to novel sentences consistent with the familiar pattern, occasional familiarity preferences, more recovery to consistent novel sentences than to familiarized sentences, and extrapolative generalization outside the range of the training patterns. A variety of predictions suggest the utility of the model in guiding future psychological work. The evidence, from these and other simulations, supports the view that unstructured neural networks can account for the existing infant data.

Le traitement d'un langage artificiel

Summary In current experiments in psycholinguistics, it is very difficult if not impossible to differentiate the role of syntax from the role of semantics. In the present experiment, the use of artificial elements that do not convey any particular meaning enables us to study separately the influence of the formai complexity of the sentence on the processing duration. The material is composed of embedded structures and passive forms. Some of these structures are isomorphic to natural language sentences. The results show that durations for processing artificial sentences are ordered in the same fashion as durations for processing natural sentences. The results validate a model of the subject based on relation operations and inversion operations.

Development of a Synthetic Sentence-Identification Task in Spanish

The use of a closed-message set of synthetic or artificial sentences has been explored in studies on speech intelligibility in English for the past 4 yr. Each alternative sentence was constructed as an approximation to a real sentence by selecting each successive word on the basis of the conditional probabilities of word sequences. This method for generating test materials can, in theory, be generalized to any language that is characterized by rules of syntax. This paper describes the development and evaluation of synthetic sentence message sets in the Spanish language. Performance-intensity functions in quiet and in the presence of a competing speech message will be described and compared with similar data for English sentences. The advantages of the synthetic sentences for assessing speech-discrimination scores for hearing-impaired Spanish-speaking listeners will be described.