Automatically Extracting Procedural Knowledge from Instructional Texts using Natural Language Processing

Procedural knowledge is the knowledge required to perform certain tasks, and forms an important part of expertise. A major source of procedural knowledge is natural language instructions. While these readable instructions have been useful learning resources for human, they are not interpretable by machines. Automatically acquiring procedural knowledge in machine interpretable formats from instructions has become an increasingly popular research topic due to their potential applications in process automation. However, it has been insufficiently addressed. This paper presents an approach and an implemented system to assist users to automatically acquire procedural knowledge in structured forms from instructions. We introduce a generic semantic representation of procedures for analysing instructions, using which natural language techniques are applied to automatically extract structured procedures from instructions. The method is evaluated in three domains to justify the generality of the proposed semantic representation as well as the effectiveness of the implemented automatic system.

Conversational interaction in the scanner:mentalizing during language processing as revealed by MEG

Humans are especially good at taking another's perspective-representing what others might be thinking or experiencing. This "mentalizing" capacity is apparent in everyday human interactions and conversations. We investigated its neural basis using magnetoencephalography. We focused on whether mentalizing was engaged spontaneously and routinely to understand an utterance's meaning or largely on-demand, to restore "common ground" when expectations were violated. Participants conversed with 1 of 2 confederate speakers and established tacit agreements about objects' names. In a subsequent "test" phase, some of these agreements were violated by either the same or a different speaker. Our analysis of the neural processing of test phase utterances revealed recruitment of neural circuits associated with language (temporal cortex), episodic memory (e.g., medial temporal lobe), and mentalizing (temporo-parietal junction and ventromedial prefrontal cortex). Theta oscillations (3-7 Hz) were modulated most prominently, and we observed phase coupling between functionally distinct neural circuits. The episodic memory and language circuits were recruited in anticipation of upcoming referring expressions, suggesting that context-sensitive predictions were spontaneously generated. In contrast, the mentalizing areas were recruited on-demand, as a means for detecting and resolving perceived pragmatic anomalies, with little evidence they were activated to make partner-specific predictions about upcoming linguistic utterances.

Informational Model of Natural Language Processing

The formal model of natural language processing in knowledge-based information systems is considered. The components realizing functions of offered formal model are described.

SEQUENTIAL DECISIONS AND PREDICTIONS IN NATURAL LANGUAGE PROCESSING

Natural language processing has achieved great success in a wide range of ap- plications, producing both commercial language services and open-source language tools. However, most methods take a static or batch approach, assuming that the model has all information it needs and makes a one-time prediction. In this disser- tation, we study dynamic problems where the input comes in a sequence instead of all at once, and the output must be produced while the input is arriving. In these problems, predictions are often made based only on partial information. We see this dynamic setting in many real-time, interactive applications. These problems usually involve a trade-off between the amount of input received (cost) and the quality of the output prediction (accuracy). Therefore, the evaluation considers both objectives (e.g., plotting a Pareto curve). Our goal is to develop a formal understanding of sequential prediction and decision-making problems in natural language processing and to propose efficient solutions. Toward this end, we present meta-algorithms that take an existent batch model and produce a dynamic model to handle sequential inputs and outputs. Webuild our framework upon theories of Markov Decision Process (MDP), which allows learning to trade off competing objectives in a principled way. The main machine learning techniques we use are from imitation learning and reinforcement learning, and we advance current techniques to tackle problems arising in our settings. We evaluate our algorithm on a variety of applications, including dependency parsing, machine translation, and question answering. We show that our approach achieves a better cost-accuracy trade-off than the batch approach and heuristic-based decision- making approaches. We first propose a general framework for cost-sensitive prediction, where dif- ferent parts of the input come at different costs. We formulate a decision-making process that selects pieces of the input sequentially, and the selection is adaptive to each instance. Our approach is evaluated on both standard classification tasks and a structured prediction task (dependency parsing). We show that it achieves similar prediction quality to methods that use all input, while inducing a much smaller cost. Next, we extend the framework to problems where the input is revealed incremen- tally in a fixed order. We study two applications: simultaneous machine translation and quiz bowl (incremental text classification). We discuss challenges in this set- ting and show that adding domain knowledge eases the decision-making problem. A central theme throughout the chapters is an MDP formulation of a challenging problem with sequential input/output and trade-off decisions, accompanied by a learning algorithm that solves the MDP.

Towards Unstructured Knowledge Integration in Natural Language Processing

In the last decades, Artificial Intelligence has witnessed multiple breakthroughs in deep learning. In particular, purely data-driven approaches have opened to a wide variety of successful applications due to the large availability of data. Nonetheless, the integration of prior knowledge is still required to compensate for specific issues like lack of generalization from limited data, fairness, robustness, and biases. In this thesis, we analyze the methodology of integrating knowledge into deep learning models in the field of Natural Language Processing (NLP). We start by remarking on the importance of knowledge integration. We highlight the possible shortcomings of these approaches and investigate the implications of integrating unstructured textual knowledge. We introduce Unstructured Knowledge Integration (UKI) as the process of integrating unstructured knowledge into machine learning models. We discuss UKI in the field of NLP, where knowledge is represented in a natural language format. We identify UKI as a complex process comprised of multiple sub-processes, different knowledge types, and knowledge integration properties to guarantee. We remark on the challenges of integrating unstructured textual knowledge and bridge connections with well-known research areas in NLP. We provide a unified vision of structured knowledge extraction (KE) and UKI by identifying KE as a sub-process of UKI. We investigate some challenging scenarios where structured knowledge is not a feasible prior assumption and formulate each task from the point of view of UKI. We adopt simple yet effective neural architectures and discuss the challenges of such an approach. Finally, we identify KE as a form of symbolic representation. From this perspective, we remark on the need of defining sophisticated UKI processes to verify the validity of knowledge integration. To this end, we foresee frameworks capable of combining symbolic and sub-symbolic representations for learning as a solution.

Examining second language development using event-related potentials: a cross-sectional study on the processing of gender and number agreement

This cross-sectional study examines the role of L1-L2 differences and structural distance in the processing of gender and number agreement by English-speaking learners of Spanish at three different levels of proficiency. Preliminary results show that differences between the L1 and L2 impact L2 development, as sensitivity to gender agreement violations, as opposed to number agreement violations, emerges only in learners at advanced levels of proficiency. Results also show that the establishment of agreement dependencies is impacted by the structural distance between the agreeing elements for native speakers and for learners at intermediate and advanced levels of proficiency but not for low proficiency. The overall pattern of results suggests that the linguistic factors examined here impact development but do not constrain ultimate attainment; for advanced learners, results suggest that second language processing is qualitatively similar to native processing.

Investigation of auditory processing disorder and language impairment using the speech-evoked auditory brainstem response

This study investigated whether there are differences in the Speech-Evoked Auditory Brainstem Response among children with Typical Development (TD), (Central) Auditory Processing Disorder (C) APD, and Language Impairment (LI). The speech-evoked Auditory Brainstem Response was tested in 57 children (ages 6-12). The children were placed into three groups: TD (n = 18), (C)APD (n = 18) and LI (n = 21). Speech-evoked ABR were elicited using the five-formant syllable/da/. Three dimensions were defined for analysis, including timing, harmonics, and pitch. A comparative analysis of the responses between the typical development children and children with (C)APD and LI revealed abnormal encoding of the speech acoustic features that are characteristics of speech perception in children with (C)APD and LI, although the two groups differed in their abnormalities. While the children with (C)APD might had a greater difficulty distinguishing stimuli based on timing cues, the children with LI had the additional difficulty of distinguishing speech harmonics, which are important to the identification of speech sounds. These data suggested that an inefficient representation of crucial components of speech sounds may contribute to the difficulties with language processing found in children with LI. Furthermore, these findings may indicate that the neural processes mediated by the auditory brainstem differ among children with auditory processing and speech-language disorders. (C) 2012 Elsevier B.V. All rights reserved.

Biologically Plausible Connectionist Prediction of Natural Language Thematic Relations

In Natural Language Processing (NLP) symbolic systems, several linguistic phenomena, for instance, the thematic role relationships between sentence constituents, such as AGENT, PATIENT, and LOCATION, can be accounted for by the employment of a rule-based grammar. Another approach to NLP concerns the use of the connectionist model, which has the benefits of learning, generalization and fault tolerance, among others. A third option merges the two previous approaches into a hybrid one: a symbolic thematic theory is used to supply the connectionist network with initial knowledge. Inspired on neuroscience, it is proposed a symbolic-connectionist hybrid system called BIO theta PRED (BIOlogically plausible thematic (theta) symbolic-connectionist PREDictor), designed to reveal the thematic grid assigned to a sentence. Its connectionist architecture comprises, as input, a featural representation of the words (based on the verb/noun WordNet classification and on the classical semantic microfeature representation), and, as output, the thematic grid assigned to the sentence. BIO theta PRED is designed to ""predict"" thematic (semantic) roles assigned to words in a sentence context, employing biologically inspired training algorithm and architecture, and adopting a psycholinguistic view of thematic theory.

The Coefficient of Variance as an index of L2 lexical processing skill

The Coefficient of Variance (mean standard deviation/mean Response time) is a measure of response time variability that corrects for differences in mean Response time (RT) (Segalowitz & Segalowitz, 1993). A positive correlation between decreasing mean RTs and CVs (rCV-RT) has been proposed as an indicator of L2 automaticity and more generally as an index of processing efficiency. The current study evaluates this claim by examining lexical decision performance by individuals from three levels of English proficiency (Intermediate ESL, Advanced ESL and L1 controls) on stimuli from four levels of item familiarity, as defined by frequency of occurrence. A three-phase model of skill development defined by changing rCV-RT.values was tested. Results showed that RTs and CVs systematically decreased as a function of increasing proficiency and frequency levels, with the rCV-RT serving as a stable indicator of individual differences in lexical decision performance. The rCV-RT and automaticity/restructuring account is discussed in light of the findings. The CV is also evaluated as a more general quantitative index of processing efficiency in the L2.

Subcortical brain mechanisms in speech and language

This paper reviews current research and contemporary theories of subcortical participation in the motor control of speech production and language processing. As a necessary precursor to the discussion of the functional roles of the basal ganglia and thalamus, the neuroanatomy of the basal ganglial-thalamocortical circuitry is described. Contemporary models of hypokinetic and hyperkinetic movement disorders based on recent neuroanatomical descriptions of the multi-segmented circuits that characterise basal ganglion anatomy are described. Reported effects of surgically induced lesions in the globus pallidus and thalamus on speech production are reviewed. In addition, contemporary models proposed to explain the possible contribution of various subcortical structures to language processing are described and discussed in the context of evidence gained from observation of the effects of circumscribed surgically induced lesions in the basal ganglia and thalamus on language function. The potential of studies based on examination of the speech/language outcomes of patients undergoing pallidotomy and thalamotomy to further inform the debate relating to the role of subcortical structures in speech motor control and language processing is highlighted. Copyright (C) 2001 S. Karger AG, Basel.

Regional and hemispheric determinants of language laterality: Implications for preoperative fMRI.

Language is typically a function of the left hemisphere but the right hemisphere is also essential in some healthy individuals and patients. This inter-subject variability necessitates the localization of language function, at the individual level, prior to neurosurgical intervention. Such assessments are typically made by comparing left and right hemisphere language function to determine "language lateralization" using clinical tests or fMRI. Here, we show that language function needs to be assessed at the region and hemisphere specific level, because laterality measures can be misleading. Using fMRI data from 82 healthy participants, we investigated the degree to which activation for a semantic word matching task was lateralized in 50 different brain regions and across the entire cortex. This revealed two novel findings. First, the degree to which language is lateralized across brain regions and between subjects was primarily driven by differences in right hemisphere activation rather than differences in left hemisphere activation. Second, we found that healthy subjects who have relatively high left lateralization in the angular gyrus also have relatively low left lateralization in the ventral precentral gyrus. These findings illustrate spatial heterogeneity in language lateralization that is lost when global laterality measures are considered. It is likely that the complex spatial variability we observed in healthy controls is more exaggerated in patients with brain damage. We therefore highlight the importance of investigating within hemisphere regional variations in fMRI activation, prior to neuro-surgical intervention, to determine how each hemisphere and each region contributes to language processing. Hum Brain Mapp, 2010. © 2010 Wiley-Liss, Inc.

NQL, Natural Query Language

Desarrollo de un sistema capaz de procesar consultas en lenguaje natural introducidas por el usuario mediante el teclado. El sistema es capaz de responder a consultas en castellano, relacionadas con un dominio de aplicación representado mediante una base de datos relacional.

Towards the automatic merging of language resources

Language Resources are a critical component for Natural Language Processing applications. Throughout the years many resources were manually created for the same task, but with different granularity and coverage information. To create richer resources for a broad range of potential reuses, nformation from all resources has to be joined into one. The hight cost of comparing and merging different resources by hand has been a bottleneck for merging existing resources. With the objective of reducing human intervention, we present a new method for automating merging resources. We have addressed the merging of two verbs subcategorization frame (SCF) lexica for Spanish. The results achieved, a new lexicon with enriched information and conflicting information signalled, reinforce our idea that this approach can be applied for other task of NLP.