Towards a unified sentiment lexicon based on graphics processing units

This paper presents an approach to create what we have called a Unified Sentiment Lexicon (USL). This approach aims at aligning, unifying, and expanding the set of sentiment lexicons which are available on the web in order to increase their robustness of coverage. One problem related to the task of the automatic unification of different scores of sentiment lexicons is that there are multiple lexical entries for which the classification of positive, negative, or neutral {P, Z, N} depends on the unit of measurement used in the annotation methodology of the source sentiment lexicon. Our USL approach computes the unified strength of polarity of each lexical entry based on the Pearson correlation coefficient which measures how correlated lexical entries are with a value between 1 and -1, where 1 indicates that the lexical entries are perfectly correlated, 0 indicates no correlation, and -1 means they are perfectly inversely correlated and so is the UnifiedMetrics procedure for CPU and GPU, respectively. Another problem is the high processing time required for computing all the lexical entries in the unification task. Thus, the USL approach computes a subset of lexical entries in each of the 1344 GPU cores and uses parallel processing in order to unify 155802 lexical entries. The results of the analysis conducted using the USL approach show that the USL has 95.430 lexical entries, out of which there are 35.201 considered to be positive, 22.029 negative, and 38.200 neutral. Finally, the runtime was 10 minutes for 95.430 lexical entries; this allows a reduction of the time computing for the UnifiedMetrics by 3 times.

New trends in natural language processing: statistical natural language processing.

The field of natural language processing (NLP) has seen a dramatic shift in both research direction and methodology in the past several years. In the past, most work in computational linguistics tended to focus on purely symbolic methods. Recently, more and more work is shifting toward hybrid methods that combine new empirical corpus-based methods, including the use of probabilistic and information-theoretic techniques, with traditional symbolic methods. This work is made possible by the recent availability of linguistic databases that add rich linguistic annotation to corpora of natural language text. Already, these methods have led to a dramatic improvement in the performance of a variety of NLP systems with similar improvement likely in the coming years. This paper focuses on these trends, surveying in particular three areas of recent progress: part-of-speech tagging, stochastic parsing, and lexical semantics.

Applying semantic knowledge to the automatic processing of temporal expressions and events in natural language

This paper addresses the problem of the automatic recognition and classification of temporal expressions and events in human language. Efficacy in these tasks is crucial if the broader task of temporal information processing is to be successfully performed. We analyze whether the application of semantic knowledge to these tasks improves the performance of current approaches. We therefore present and evaluate a data-driven approach as part of a system: TIPSem. Our approach uses lexical semantics and semantic roles as additional information to extend classical approaches which are principally based on morphosyntax. The results obtained for English show that semantic knowledge aids in temporal expression and event recognition, achieving an error reduction of 59% and 21%, while in classification the contribution is limited. From the analysis of the results it may be concluded that the application of semantic knowledge leads to more general models and aids in the recognition of temporal entities that are ambiguous at shallower language analysis levels. We also discovered that lexical semantics and semantic roles have complementary advantages, and that it is useful to combine them. Finally, we carried out the same analysis for Spanish. The results obtained show comparable advantages. This supports the hypothesis that applying the proposed semantic knowledge may be useful for different languages.

The relationship between the mismatch negativity (MMN) and psycholinguistic models of spoken word processing

Background: The results from previous studies have indicated that a pre-attentive component of the event-related potential (ERP), the mismatch negativity (MMN), may be an objective measure of the automatic auditory processing of phonemes and words. Aims: This article reviews the relationship between the MMN data and psycholinguistic models of spoken word processing, in order to determine whether the MMN may be used to objectively pinpoint spoken word processing deficits in individuals with aphasia. Main Contribution: This article outlines the ways in which the MMN data support psycholinguistic models currently used in the clinical management of aphasic individuals. Furthermore, the cell assembly model of the neurophysiological mechanisms underlying spoken word processing is discussed in relation to the MMN and psycholinguistic models. Conclusions: The MMN data support current theoretical psycholinguistic and neurophysiological models of spoken word processing. Future MMN studies that include normal and aphasic populations will further elucidate the role that the MMN may play in the clinical management of aphasic individuals.

Meaning selection and the subcortex: Evidence of reduced lexical ambiguity repetition effects following subcortical lesions

Recent research indicates that individuals with nonthalamic subcortical (NS) lesions call experience difficulties processing lexical ambiguities in a variety of contexts. This study examined how prior processing of a lexical ambiguity influences subsequent meaning activation in 10 individuals with NS lesions and 10 matched healthy controls. Subjects made speeded lexical decisions oil related or unrelated targets following homophone primes. Homophones were repealed with different targets biasing the same or different meanings oil the second presentation. The effects of prime-target relatedness, interstimulus interval (200 or 1250 ms), and same vs different meaning repetition were examined Both the patient and control groups showed printing when the same homophone meaning was biased oil repetition. When a different meaning was biased on the second presentation. no priming was evident in the controls, while facilitation remained present for the NS group, consistent with aberrant meaning selection and deactivation processes. These findings are discussed in terms of age and task-related repetition effects and current conceptions of frontal-subcortical involvement in cognition.

Selective processing of masked and unmasked verbal threat material in anxiety: Influence of an immediate acute stressor

Attentional biases for threat were investigated using a computerised version of the emotional Stroop task. The study examined the influence of state and trait anxiety by employing a student sample assigned to high trait anxious (HTA; n = 32) or low trait anxious (LTA; n = 32) groups on the basis of questionnaire scores, and state anxiety was manipulated within participants through the threat of electric shock. Threatening words that were either unrelated (e.g., cancer, danger) or related to the threat of shock (e.g., electrocute, shock) were presented to participants both within and outside of awareness. In the latter condition a backward masking procedure was used to prevent awareness and exposure thresholds between the target and mask were individually set for each participant. For unmasked trials the HTA group showed significant interference in colour naming for all threat words relative to control words when performing under the threat of shock, but not in the shock safe condition. For the masked trials, despite chance performance in being able to identify the lexical status of the items, HTA participants showed facilitated colour naming for all threat words relative to control items when performing under threat of shock, but this effect was not evident in the shock safe condition. Neither valence of the items nor the threat of shock influenced colour naming latencies in either exposure mode for the LTA group.

Top-down influences on lexical selection during spoken word production: A 4T fMRI investigation of refractory effects in picture naming

Spoken word production is assumed to involve stages of processing in which activation spreads through layers of units comprising lexical-conceptual knowledge and their corresponding phonological word forms. Using high-field (4T) functional magnetic resonance imagine (fMRI), we assessed whether the relationship between these stages is strictly serial or involves cascaded-interactive processing, and whether central (decision/control) processing mechanisms are involved in lexical selection. Participants performed the competitor priming paradigm in which distractor words, named from a definition and semantically related to a subsequently presented target picture, slow picture-naming latency compared to that with unrelated words. The paradigm intersperses two trials between the definition and the picture to be named, temporally separating activation in the word perception and production networks. Priming semantic competitors of target picture names significantly increased activation in the left posterior temporal cortex, and to a lesser extent the left middle temporal cortex, consistent with the predictions of cascaded-interactive models of lexical access. In addition, extensive activation was detected in the anterior cingulate and pars orbitalis of the inferior frontal gyrus. The findings indicate that lexical selection during competitor priming is biased by top-down mechanisms to reverse associations between primed distractor words and target pictures to select words that meet the current goal of speech.

Automatic Creation of Lexical Resources for an Interlingua-based System

The Universal Networking Language (UNL) is an interlingua designed to be the base of several natural language processing systems aiming to support multilinguality in internet. One of the main components of the language is the dictionary of Universal Words (UWs), which links the vocabularies of the different languages involved in the project. As any NLP system, coverage and accuracy in its lexical resources are crucial for the development of the system. In this paper, the authors describes how a large coverage UWs dictionary was automatically created, based on an existent and well known resource like the English WordNet. Other aspects like implementation details and the evaluation of the final UW set are also depicted.

Phonological simplifications, apraxia of speech and the interaction between phonological and phonetic processing

Research on aphasia has struggled to identify apraxia of speech (AoS) as an independent deficit affecting a processing level separate from phonological assembly and motor implementation. This is because AoS is characterized by both phonological and phonetic errors and, therefore, can be interpreted as a combination of deficits at the phonological and the motoric level rather than as an independent impairment. We apply novel psycholinguistic analyses to the perceptually phonological errors made by 24 Italian aphasic patients. We show that only patients with relative high rate (>10%) of phonetic errors make sound errors which simplify the phonology of the target. Moreover, simplifications are strongly associated with other variables indicative of articulatory difficulties - such as a predominance of errors on consonants rather than vowels -but not with other measures - such as rate of words reproduced correctly or rates of lexical errors. These results indicate that sound errors cannot arise at a single phonological level because they are different in different patients. Instead, different patterns: (1) provide evidence for separate impairments and the existence of a level of articulatory planning/programming intermediate between phonological selection and motor implementation; (2) validate AoS as an independent impairment at this level, characterized by phonetic errors and phonological simplifications; (3) support the claim that linguistic principles of complexity have an articulatory basis since they only apply in patients with associated articulatory difficulties.