scholarly journals Towards computational models of multilingual sentence processing

2019 ◽  
Author(s):  
Stefan L. Frank
Keyword(s):  
Computational Linguistics ◽  
Sentence Processing ◽  
Computational Models ◽  
State Of The Art ◽  
Cognitive Models ◽  
The State ◽  
Cognitive Modelling ◽  
Current Review ◽  
Multiple Languages ◽  
Human Sentence Processing

Although computational models can simulate aspects of human sentence processing, research on this topic has remained almost exclusively limited to the single language case. The current review presents an overview of the state of the art in computational cognitive models of sentence processing, and discusses how recent sentence-processing models can be used to study bi- and multilingualism. Recent results from cognitive modelling and computational linguistics suggest that phenomena specific to bilingualism can emerge from systems that have no dedicated components for handling multiple languages. Hence, accounting for human bi-/multilingualism may not require models that are much more sophisticated than those for the monolingual case.

scholarly journals Comparing gated and simple recurrent neural network architectures as models of human sentence processing

2018 ◽  
Author(s):  
Christoph Aurnhammer ◽  
Stefan L. Frank
Keyword(s):  
Language Processing ◽  
Sentence Processing ◽  
Language Model ◽  
Cell Types ◽  
Recurrent Network ◽  
Cognitive Models ◽  
Language Models ◽  
Model Quality ◽  
Sentence Reading ◽  
Human Sentence Processing

The Simple Recurrent Network (SRN) has a long tradition in cognitive models of language processing. More recently, gated recurrent networks have been proposed that often outperform the SRN on natural language processing tasks. Here, we investigate whether two types of gated networks perform better as cognitive models of sentence reading than SRNs, beyond their advantage as language models.This will reveal whether the filtering mechanism implemented in gated networks corresponds to an aspect of human sentence processing.We train a series of language models differing only in the cell types of their recurrent layers. We then compute word surprisal values for stimuli used in self-paced reading, eye-tracking, and electroencephalography experiments, and quantify the surprisal values' fit to experimental measures that indicate human sentence reading effort.While the gated networks provide better language models, they do not outperform their SRN counterpart as cognitive models when language model quality is equal across network types. Our results suggest that the different architectures are equally valid as models of human sentence processing.

scholarly journals A Biscriptual Morphological Transducer for Crimean Tatar

2019 ◽  
Author(s):  
Francis M. Tyers ◽  
Jonathan N. Washington ◽  
Darya Kavitskaya ◽  
Memduh Gökırmak
Keyword(s):  
Computational Linguistics ◽  
Morphological Analysis ◽  
State Of The Art ◽  
Full Range ◽  
The State ◽  
Loan Words ◽  
The Core ◽  
Finite State ◽  
Morphological Modelling ◽  
Crimean Tatar

This paper describes a weighted finite-state morphological transducer for Crimean Tatar able to analyse and generate in both Latin and Cyrillic orthographies. This transducer was developed by a team including a community member and language expert, a field linguist who works with the community, a Turkologist with computational linguistics expertise, and an experienced computational linguist with Turkic expertise. Dealing with two orthographic systems in the same transducer is challenging as they employ different strategies to deal with the spelling of loan words and encode the full range of the language's phonemes and their interaction. We develop the core transducer using the Latin orthography and then design a separate transliteration transducer to map the surface forms to Cyrillic. To help control the non-determinism in the orthographic mapping, we use weights to prioritise forms seen in the corpus. We perform an evaluation of all components of the system, finding an accuracy above 90% for morphological analysis and near 90% for orthographic conversion. This comprises the state of the art for Crimean Tatar morphological modelling, and, to our knowledge, is the first biscriptual single morphological transducer for any language.

Sentiment Analysis of Code-Mixed Text: A Review

2021 ◽  
Vol 12 (3) ◽  
pp. 2469-2478
Author(s):  
Nurul Husna Mahadzir Et.al
Keyword(s):  
Information Retrieval ◽  
Text Mining ◽  
Sentiment Analysis ◽  
State Of The Art ◽  
The State ◽  
The Internet ◽  
Qualitative Comparison ◽  
Analysis Process ◽  
Active Research ◽  
Multiple Languages

In recent times, sentiment analysis has become one of the most active research and progressively popular areas in information retrieval and text mining. To date, sentiment analysis has been applied in various domains such as product, movie, sport and political reviews. Most of the previous work in this field has focused on analyzing only a single language, especially English. However, with the need of globalization and the increasing number of the Internet used worldwide; it is common to see the post written in multiple languages. Moreover, in an unstructured content like Twitter posts, people tend to mix languages in one sentence, which make sentiment analysis process even harder and more challenging. This paper reviews the state-of-the-art of sentiment analysis for code-mixed, which includes the detail discussions of each focus area, qualitative comparison and limitations of current approaches. This paper also highlights challenges along this line of research and suggests several recommendations for future works that should be explored.

scholarly journals Computational Models of Narrative: Review of a Workshop

AI Magazine ◽  
2010 ◽  
Vol 31 (2) ◽  
pp. 97 ◽  
Author(s):  
Mark A. Finlayson ◽  
Whitman Richards ◽  
Patrick Henry Winston
Keyword(s):  
Computational Modeling ◽  
Computational Models ◽  
State Of The Art ◽  
Data Bank ◽  
The State ◽  
Narrative Review ◽  
Current Work ◽  
Standard Data ◽  
Abstract Level ◽  
Different Levels

On October 8-10, 2009 an interdisciplinary group met at the Wylie Center in Beverley, Massachusetts to evaluate the state of the art in the computational modeling of narrative. Three important findings emerged: (1) current work in computational modeling is described by three different levels of representation; (2) there is a paucity of studies at the highest, most abstract level aimed at inferring the meaning or message of the narrative; and (3) there is a need to establish a standard data bank of annotated narratives, analogous to the Penn Treebank.

scholarly journals A state-of-the-art of semantic change computation

2018 ◽  
Vol 24 (5) ◽  
pp. 649-676 ◽  
Author(s):  
XURI TANG
Keyword(s):  
Data Visualization ◽  
Computational Linguistics ◽  
Comprehensive Evaluation ◽  
State Of The Art ◽  
The State ◽  
Word Sense ◽  
Semantic Change ◽  
Evaluation Data ◽  
Visualization Techniques ◽  
Core Issues

AbstractThis paper reviews the state-of-the-art of one emergent field in computational linguistics—semantic change computation. It summarizes the literature by proposing a framework that identifies five components in the field: diachronic corpus, diachronic word sense characterization, change modelling, evaluation and data visualization. Despite its potentials, the review shows that current studies are mainly focused on testifying hypotheses of semantic change from theoretical linguistics and that several core issues remain to be tackled: the need of diachronic corpora for languages other than English, the comparison and development of approaches to diachronic word sense characterization and change modelling, the need of comprehensive evaluation data and further exploration of data visualization techniques for hypothesis justification.

Revisiting the DARPA communicator data using conversation analysis

2008 ◽  
Vol 9 (3) ◽  
pp. 434-457 ◽  
Author(s):  
Peter Wallis
Keyword(s):  
Conversation Analysis ◽  
Computational Linguistics ◽  
Qualitative Methodology ◽  
State Of The Art ◽  
The State ◽  
Discourse Structure ◽  
Text Corpora ◽  
Alternative Future ◽  
Mixed Initiative ◽  
Modern Form

The state of the art in human computer conversation leaves something to be desired and, indeed, talking to a computer can be down-right annoying. This paper describes an approach to identifying “opportunities for improvement” in these systems by looking for abuse in the form of swear words. The premise is that humans swear at computers as a sanction and, as such, swear words represent a point of failure where the system did not behave as it should. Having identified where things went wrong, we can work backward through the transcripts and, using conversation analysis (CA) work out how things went wrong. Conversation analysis is a qualitative methodology and can appear quite alien — indeed unscientific — to those of us from a quantitative background. The paper starts with a description of Conversation analysis in its modern form, and then goes on to apply the methodology to transcripts of frustrated and annoyed users in the DARPA Communicator project. The conclusion is that there is at least one species of failure caused by the inability of the Communicator systems to handle mixed initiative at the discourse structure level. Along the way, I hope to demonstrate that there is an alternative future for computational linguistics that does not rely on larger and larger text corpora.

Artificial Neural Networks and Cognitive Modelling

2011 ◽  
pp. 161-166
Author(s):  
Amanda J.C. Sharkey
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Computational Models ◽  
Cognitive Models ◽  
Cognitive Modelling ◽  
Connectionist Models ◽  
Category Formation ◽  
Connectionist Approach ◽  
Artificial Neural ◽  
The Impact

In their heyday, artificial neural networks promised a radically new approach to cognitive modelling. The connectionist approach spawned a number of influential, and controversial, cognitive models. In this article, we consider the main characteristics of the approach, look at the factors leading to its enthusiastic adoption, and discuss the extent to which it differs from earlier computational models. Connectionist cognitive models have made a significant impact on the study of mind. However connectionism is no longer in its prime. Possible reasons for the diminution in its popularity will be identified, together with an attempt to identify its likely future. The rise of connectionist models dates from the publication in 1986 by Rumelhart and McClelland, of an edited work containing a collection of connectionist models of cognition, each trained by exposure to samples of the required tasks. These volumes set the agenda for connectionist cognitive modellers and offered a methodology that subsequently became the standard. Connectionist cognitive models have since been produced in domains including memory retrieval and category formation, and (in language) phoneme recognition, word recognition, speech perception, acquired dyslexia, language acquisition, and (in vision) edge detection, object and shape recognition. More than twenty years later the impact of this work is still apparent.

scholarly journals Sentence Comprehension as a Cognitive Process

2021 ◽  
Author(s):  
Shravan Vasishth ◽  
Felix Engelmann
Keyword(s):  
Computational Linguistics ◽  
Sentence Processing ◽  
Cognitive Processes ◽  
Cognitive Process ◽  
Sentence Comprehension ◽  
Computational Models ◽  
Model Comparison ◽  
Written Language ◽  
Retrieval Processes ◽  
New Research

Sentence comprehension - the way we process and understand spoken and written language - is a central and important area of research within psycholinguistics. This book explores the contribution of computational linguistics to the field, showing how computational models of sentence processing can help scientists in their investigation of human cognitive processes. It presents the leading computational model of retrieval processes in sentence processing, the Lewis and Vasishth cue-based retrieval mode, and develops a principled methodology for parameter estimation and model comparison/evaluation using benchmark data, to enable researchers to test their own models of retrieval against the present model. It also provides readers with an overview of the last 20 years of research on the topic of retrieval processes in sentence comprehension, along with source code that allows researchers to extend the model and carry out new research. Comprehensive in its scope, this book is essential reading for researchers in cognitive science.

scholarly journals Review of the PEA Method for Space Charge Measurements on HVDC Cables and Mini-Cables

Energies ◽  
2019 ◽  
Vol 12 (18) ◽  
pp. 3512 ◽  
Author(s):  
Giuseppe Rizzo ◽  
Pietro Romano ◽  
Antonino Imburgia ◽  
Guido Ala
Keyword(s):  
Space Charge ◽  
High Voltage ◽  
Direct Current ◽  
State Of The Art ◽  
The State ◽  
Cylindrical Geometry ◽  
Full Size ◽  
High Voltage Direct Current ◽  
Charge Measurement ◽  
Current Review

This review takes into account articles and standards published in recent years concerning the application of the Pulsed Electro Acoustic (PEA) method for space charge measurement on High Voltage Direct Current (HVDC) cables and mini-cables. Since the 80s, the PEA method has been implemented for space charge measurements on flat specimens in order to investigate space charge phenomena and to evaluate the ageing of dielectrics. In recent years, this technique has been adapted to cylindrical geometry. Several studies and experiments have been carried out on the use of the PEA method for full size cables and HVDC cable models. The experiments have been conducted using different arrangements of the measurement setup and focusing attention on different aspects of space charge phenomena. In this work, the importance of space charge measurement is highlighted and the state-of-the-art PEA method application to full size cables and mini-cables is described. The main aim of this paper is to offer a complete and current review of this technique. In addition, limits on the use of PEA method are examined and main possible directions of research are proposed in order to improve the applicability, reliability, and replicability of this method.

Sign in / Sign up

Export Citation Format

Share Document