This paper introduces deep neural network (DNN)–hidden Markov model (HMM)-based methods to tackle speech recognition in heterogeneous groups of speakers including children. We target three speaker groups consisting of children, adult males and adult females. Two different kind of approaches are introduced here: approaches based on DNN adaptation and approaches relying on vocal-tract length normalisation (VTLN). First, the recent approach that consists in adapting a general DNN to domain/language specific data is extended to target age/gender groups in the context of DNN–HMM. Then, VTLN is investigated by training a DNN–HMM system by using either mel frequency cepstral coefficients normalised with standard VTLN or mel frequency cepstral coefficients derived acoustic features combined with the posterior probabilities of the VTLN warping factors. In this later, novel, approach the posterior probabilities of the warping factors are obtained with a separate DNN and the decoding can be operated in a single pass when the VTLN approach requires two decoding passes. Finally, the different approaches presented here are combined to take advantage of their complementarity. The combination of several approaches is shown to improve the baseline phone error rate performance by thirty per cent to thirty-five per cent relative and the baseline word error rate performance by about ten per cent relative.

This paper presents the improvement process of a mention detector for Basque. The system is rule-based and takes into account the characteristics of mentions in Basque. A classification of error types is proposed based on the errors that occur during mention detection. A deep error analysis distinguishing error types and causes is presented and improvements are proposed. At the final stage, the system obtains an F-measure of 74.57% under the Exact Matching protocol and of 80.57% under Lenient Matching. We also show the performance of the mention detector with gold standard data as input, in order to omit errors caused by the previous stages of linguistic processing. In this scenario, we obtain an F-measure of 85.89% with Strict Matching and of 89.06% with Lenient Matching, i.e., a difference of 11.32 and 8.49 percentage points, respectively. Finally, how improvements in mention detection affect coreference resolution is analysed.

A key challenge of the Information Extraction in Natural Language Processing is the ability to recognise and classify temporal expressions (timexes). It is a crucial source of information about when something happens, how often something occurs or how long something lasts. Timexes extracted automatically from text, play a major role in many Information Extraction systems, such as question answering or event recognition. We prepared a broad specification of Polish timexes – PLIMEX. It is based on the state-of-the-art annotation guidelines for English, mainly TIMEX2 and TIMEX3 (a part of TimeML – Markup Language for Temporal and Event Expressions). We have expanded our specification for a description of the local meaning of timexes, based on LTIMEX annotation guidelines for English. Temporal description supports further event identification and extends event description model, focussing on anchoring events in time, events ordering and reasoning about the persistence of events. We prepared the specification, which is designed to address these issues, and we annotated all documents in Polish Corpus of Wroclaw University of Technology (KPWr) using our annotation guidelines. We also adapted our Liner2 machine learning system to recognise Polish timexes and we propose two-phase method to select a subset of features for Conditional Random Fields sequence labelling method. This article presents the whole process of corpus annotation, evaluation of inter-annotator agreement, extending Liner2 system with new features and evaluation of the recognition models before and after feature selection with the analysis of statistical significance of differences. Liner2 with presented models is available as open source software under the GNU General Public License.

The specificities of the Arabic language, mainly agglutination and vocalization make the task of POS-tagging more difficult than for Indo-European languages. Consequently, POS-tagging texts with good accuracy remains a challenging problem for Arabic language processing applications. In this work, we consider the task of POS-tagging as an optimization problem modeled as a graph whose nodes correspond to all possible grammatical tags given by a morphological analyzer for words in a sentence and the goal is to find the best path (sequence of tags) in this graph. To resolve this problem, we propose a novel approach based on ant colony. Ant colony-based algorithms are among the most efficient methods to resolve optimization problems modeled as a graph. The collaboration of ants having various knowledge creates a collective intelligence and increases efficiency. We have performed experiments on both vocalized and non-vocalized texts and tested two different tagsets containing fine and coarse grained composite tags. The obtained results showed good accuracy rates and hence, the benefits of swarm intelligence for the POS-tagging problem.

Named Entity Recognition (NER) is an essential task for many natural language processing systems, which makes use of various linguistic resources. NER becomes more complicated when the language in use is morphologically rich and structurally complex, such as Arabic. This language has a set of characteristics that makes it particularly challenging to handle. In a previous work, we have proposed an Arabic NER system that follows the hybrid approach, i.e. integrates both rule-based and machine learning-based NER approaches. Our hybrid NER system is the state-of-the-art in Arabic NER according to its performance on standard evaluation datasets. In this article, we discuss a novel methodology for overcoming the coverage drawback of rule-based NER systems in order to improve their performance and allow for automated rule update. The presented mechanism utilizes the recognition decisions made by the hybrid NER system in order to identify the weaknesses of the rule-based component and derive new linguistic rules aiming at enhancing the rule base, which will help in achieving more reliable and accurate results. We used ACE 2004 Newswire standard dataset as a resource for extracting and analyzing new linguistic rules for person, location and organization names recognition. We formulate each new rule based on two distinctive feature groups, i.e. Gazetteers of each type of named entities and Part-of-Speech tags, in particular noun and proper noun. Fourteen new patterns are derived, formulated as grammar rules, and evaluated in terms of coverage. The conducted experiments exploit a POS tagged version of the ACE 2004 NW dataset. The empirical results show that the performance of the enhanced rule-based system, i.e. NERA 2.0, improves the coverage of the previously misclassified person, location and organization named entities types by 69.93 per cent, 57.09 per cent and 54.28 per cent, respectively.

There has been a trend for publications to report better and better numbers, but less and less insight. The literature is turning into a giant leaderboard, where publication depends on numbers and little else (such as insight and explanation). It is considered a feature that machine learning has become so powerful (and so opaque) that it is no longer necessary (or even relevant) to talk about how it works. Insight is not only not required any more, but perhaps, insight is no longer even considered desirable.

Transparency is good and opacity is bad. A recent best seller, Weapons of Math Destruction, is concerned that big data (and WMDs) increase inequality and threaten democracy largely because of opacity. Algorithms are being used to make lots of important decisions like who gets a loan and who goes to jail. If we tell the machine to maximize an objective function like making money, it will do exactly that, for better and for worse. Who is responsible for the consequences? Does it make it ok for machines to do bad things if no one knows what’s happening and why, including those of us who created the machines?