Explore the vast range of titles available.

This book contains a collection of edited papers which were presented at the international conference 'Procedural Meaning. Problems and Perspectives' in Madrid.The conference brought together the most outstanding specialists in this field, making a worthwhile occasion for collecting its most significant contributions in a volume. Despite the fact that procedural meaning has become an increasingly widespread area of study by scholars from a variety of backgrounds, including researchers of semantics, pragmatics and syntax, there is to date no volume dedicated specifically to this topic,. The interest in the applications of procedural semantics has increased over the years and continues to do so; therefore, the publication of a collection of papers bringing together the variety of viewpoints from which procedural meaning is being applied will fulfil an important role in disseminating and enhancing its study and facilitating future development. The book is intended to be a reference for those interested in or already working on procedural meaning from different points of view and to identify new challenges that will determine the directions for research in future.

In computational neurolinguistics, it has been demonstrated that hierarchical models such as recurrent neural network grammars (RNNGs), which jointly generate word sequences and their syntactic structures via the syntactic composition, better explained human brain activity than sequential models such as long short-term memory networks (LSTMs). However, the vanilla RNNG has employed the top-down parsing strategy, which has been pointed out in the psycholinguistics literature as suboptimal especially for head-final/left-branching languages, and alternatively the left-corner parsing strategy has been proposed as the psychologically plausible parsing strategy. In this article, building on this line of inquiry, we investigate not only whether hierarchical models like RNNGs better explain human brain activity than sequential models like LSTMs, but also which parsing strategy is more neurobiologically plausible, by developing a novel fMRI corpus where participants read newspaper articles in a head-final/left-branching language, namely Japanese, through the naturalistic fMRI experiment. The results revealed that left-corner RNNGs outperformed both LSTMs and top-down RNNGs in the left inferior frontal and temporal-parietal regions, suggesting that there are certain brain regions that localize the syntactic composition with the left-corner parsing strategy.

Most conventional speech recognition systems have mainly concentrated on voice-driven control of personal user devices such as smartphones. Therefore, a speech recognition system used in a special environment needs to be developed in consideration of the environment. In this study, a speech recognition framework for voice-driven control of unmanned aerial vehicles (UAVs) is proposed in a collaborative environment between manned aerial vehicles (MAVs) and UAVs, where multiple MAVs and UAVs fly together, and pilots on board MAVs control multiple UAVs with their voices. Standard speech recognition systems consist of several modules, including front-end, recognition, and post-processing. Among them, this study focuses on recognition and post-processing modules in terms of in-vehicle speech recognition. In order to stably control UAVs via voice, it is necessary to handle the environmental conditions of the UAVs carefully. First, we define control commands that the MAV pilot delivers to UAVs and construct training data. Next, for the recognition module, we investigate an acoustic model suitable for the characteristics of the UAV control commands and the UAV system with hardware resource constraints. Finally, two approaches are proposed for post-processing: grammar network-based syntax analysis and transaction-based semantic analysis. For evaluation, we developed a speech recognition system in a collaborative simulation environment between a MAV and an UAV and successfully verified the validity of each module. As a result of recognition experiments of connected words consisting of two to five words, the recognition rates of hidden Markov model (HMM) and deep neural network (DNN)-based acoustic models were 98.2% and 98.4%, respectively. However, in terms of computational amount, the HMM model was about 100 times more efficient than DNN. In addition, the relative improvement in error rate with the proposed post-processing was about 65%.

A keyword-sensitive language modeling framework for spoken keyword search (KWS) is proposed to combine the advantages of conventional keyword-filler based and large vocabulary continuous speech recognition (LVCSR) based KWS systems. The proposed framework allows keyword search systems to be flexible on keyword target settings as in the LVCSR-based keyword search. In low-resource scenarios it facilitates KWS with an ability to achieve high keyword detection accuracy as in the keyword-filler based systems and to attain a low false alarm rate inherent in the LVCSR-based systems. The proposed keyword-aware grammar is realized by incorporating keyword information to re-train and modify the language models used in LVCSR-based KWS. Experimental results, on the evalpart1 data of the IARPA Babel OpenKWS13 Vietnamese tasks, indicate that the proposed approach achieves a relative improvement, over the conventional LVCSR-based KWS systems, of the actual term weighted value for about 57 % (from 0.2093 to 0.3287) and 20 % (from 0.4578 to 0.5486) on the limited-language-pack and full-language-pack tasks, respectively.

In this paper, we describe a verification method for families of distributed systems generated by a context-sensitive network grammar of a special kind. The grammar includes special non-terminal symbols, so-called quasi-terminals, which uniquely correspond to grammar terminals. These quasi-terminals specify processes that are mergings of basic system processes; in contrast, simple nonterminals specify networks of parallel compositions of these processes. The verification method is based on the model-checking technique and abstraction. An abstract representative model for a family of systems depends on their specification grammar and the system properties to be verified. This model simulates the behavior of the systems in such a way that the properties holding for the representative model are satisfied for all these systems. The properties of the representative model can be verified by the model-checking method. The properties of the system generated are specified using the universal branching time logic ∀CTL with finite deterministic automata as atomic formulas. We demonstrate the application of the proposed method to verification of some properties of a multiagent system for conflict resolution, particularly for context-dependent disambiguation in ontology population. We also suggest that this approach should be used for verification of computations on subgrids that are subgraphs of computation grids. In particular, it can be used to compute the parity of the number of active processes in a subgrid.

Introduction Based on the schema theory advanced by Rumelhart and Norman, we shed light on the individual variability in brain dynamics induced by hybridization of learning methodologies, particularly alternating unsupervised learning and supervised learning in language acquisition. The concept of “schema” implies a latent knowledge structure that a learner holds and updates as intrinsic to his or her cognitive space for guiding the processing of newly arriving information. Methods We replicated the cognitive experiment of Onnis and Thiessen on implicit statistical learning ability in language acquisition but included additional factors of prosodic variables and explicit supervised learning. Functional magnetic resonance imaging was performed to identify the functional network connections for schema updating by alternately using unsupervised and supervised artificial grammar learning tasks to segment potential words. Results Regardless of the quality of task performance, the default mode network represented the first stage of spontaneous unsupervised learning, and the wrap‐up accomplishment for successful subjects of the whole hybrid learning in concurrence with the task‐related auditory language networks. Furthermore, subjects who could easily “tune” the schema for recording a high task precision rate resorted even at an early stage to a self‐supervised learning, or “superlearning,” as a set of different learning mechanisms that act in synergy to trigger widespread neuro‐transformation with a focus on the cerebellum. Conclusions Investigation of the brain dynamics revealed by functional connectivity imaging analysis was able to differentiate the synchronized neural responses with respect to learning methods and the order effect that affects hybrid learning. Based on the schema theory advanced by Rumelhart and Norman, we shed light on the individual variability in brain dynamics induced by hybridization of learning methodologies, particularly alternating unsupervised learning and supervised learning in language acquisition. Functional magnetic resonance imaging was performed to identify the functional network connections for schema updating by alternately using unsupervised and supervised artificial grammar learning tasks to segment potential words. The default mode network represented the first stage of spontaneous unsupervised learning, and the wrap‐up accomplishment for successful subjects of the whole hybrid learning in concurrence with the task‐related auditory language networks.

This chapter contains sections titled: Introduction Evolutionary dynamics of languages Topologies of language populations Language structure Networks induced by structural similarity Conclusion Acknowledgements References

Discussion of expert systems and intelligent tutoring systems in the education field highlights an expert system that was developed to enhance the learning process in the field of grammatical constructs. Topics addressed include representing the natural language; parsing; LOGOOP (Logo in Object-Oriented Programing); and user-system interface. (11 references) (LRW)

This paper investigates the ability of artificial neural networks to judge the grammatical acceptability of a sentence, with the goal of testing their linguistic competence. We introduce the Corpus of Linguistic Acceptability (CoLA), a set of 10,657 English sentences labeled as grammatical or ungrammatical from published linguistics literature. As baselines, we train several recurrent neural network models on acceptability classification, and find that our models outperform unsupervised models by Lau et al. (2016) on CoLA. Error-analysis on specific grammatical phenomena reveals that both Lau et al.’s models and ours learn systematic generalizations like subject-verb-object order. However, all models we test perform far below human level on a wide range of grammatical constructions.

Despite their omnipresence in modern NLP, characterizing the computational power of transformer neural nets remains an interesting open question. We prove that transformers whose arithmetic precision is logarithmic in the number of input tokens (and whose feedforward nets are computable using space linear in their input) can be simulated by constant-depth logspace-uniform threshold circuits. This provides insight on the power of transformers using known results in complexity theory. For example, if ≠ (i.e., not all poly-time problems can be solved using logarithmic space), then transformers cannot even accurately solve linear equalities or check membership in an arbitrary context-free grammar with empty productions. Our result intuitively emerges from the transformer architecture’s high parallelizability. We thus speculatively introduce the idea of a fundamental : any model architecture as parallelizable as the transformer will obey limitations similar to it. Since parallelism is key to training models at massive scale, this suggests a potential inherent weakness of the scaling paradigm.