An overview of the Applications of Natural Language to Information Systems

This introduction provides an overview of the state-of-the-art technology in Applications of Natural Language to Information Systems. Specifically, we analyze the need for such technologies to successfully address the new challenges of modern information systems, in which the exploitation of the Web as a main data source on business systems becomes a key requirement. It will also discuss the reasons why Human Language Technologies themselves have shifted their focus onto new areas of interest very directly linked to the development of technology for the treatment and understanding of Web 2.0. These new technologies are expected to be future interfaces for the new information systems to come. Moreover, we will review current topics of interest to this research community, and will present the selection of manuscripts that have been chosen by the program committee of the NLDB 2011 conference as representative cornerstone research works, especially highlighting their contribution to the advancement of such technologies.

How to make a natural language interface to query databases accessible to everyone: An example

Natural Language Interfaces to Query Databases (NLIDBs) have been an active research field since the 1960s. However, they have not been widely adopted. This article explores some of the biggest challenges and approaches for building NLIDBs and proposes techniques to reduce implementation and adoption costs. The article describes {AskMe*}, a new system that leverages some of these approaches and adds an innovative feature: query-authoring services, which lower the entry barrier for end users. Advantages of these approaches are proven with experimentation. Results confirm that, even when {AskMe*} is automatically reconfigurable against multiple domains, its accuracy is comparable to domain-specific NLIDBs.

Tackling redundancy in text summarization through different levels of language analysis

One of the main challenges to be addressed in text summarization concerns the detection of redundant information. This paper presents a detailed analysis of three methods for achieving such goal. The proposed methods rely on different levels of language analysis: lexical, syntactic and semantic. Moreover, they are also analyzed for detecting relevance in texts. The results show that semantic-based methods are able to detect up to 90% of redundancy, compared to only the 19% of lexical-based ones. This is also reflected in the quality of the generated summaries, obtaining better summaries when employing syntactic- or semantic-based approaches to remove redundancy.

Detecting implicit expressions of affect in text using EmotiNet and its extensions

In the past years, an important volume of research in Natural Language Processing has concentrated on the development of automatic systems to deal with affect in text. The different approaches considered dealt mostly with explicit expressions of emotion, at word level. Nevertheless, expressions of emotion are often implicit, inferrable from situations that have an affective meaning. Dealing with this phenomenon requires automatic systems to have “knowledge” on the situation, and the concepts it describes and their interaction, to be able to “judge” it, in the same manner as a person would. This necessity motivated us to develop the EmotiNet knowledge base — a resource for the detection of emotion from text based on commonsense knowledge on concepts, their interaction and their affective consequence. In this article, we briefly present the process undergone to build EmotiNet and subsequently propose methods to extend the knowledge it contains. We further on analyse the performance of implicit affect detection using this resource. We compare the results obtained with EmotiNet to the use of alternative methods for affect detection. Following the evaluations, we conclude that the structure and content of EmotiNet are appropriate to address the automatic treatment of implicitly expressed affect, that the knowledge it contains can be easily extended and that overall, methods employing EmotiNet obtain better results than traditional emotion detection approaches.

Lightweight Internet Traffic Classification - A Subject Based Solution with Word Embeddings

Internet traffic classification is a relevant and mature research field, anyway of growing importance and with still open technical challenges, also due to the pervasive presence of Internet-connected devices into everyday life. We claim the need for innovative traffic classification solutions capable of being lightweight, of adopting a domain-based approach, of not only concentrating on application-level protocol categorization but also classifying Internet traffic by subject. To this purpose, this paper originally proposes a classification solution that leverages domain name information extracted from IPFIX summaries, DNS logs, and DHCP leases, with the possibility to be applied to any kind of traffic. Our proposed solution is based on an extension of Word2vec unsupervised learning techniques running on a specialized Apache Spark cluster. In particular, learning techniques are leveraged to generate word-embeddings from a mixed dataset composed by domain names and natural language corpuses in a lightweight way and with general applicability. The paper also reports lessons learnt from our implementation and deployment experience that demonstrates that our solution can process 5500 IPFIX summaries per second on an Apache Spark cluster with 1 slave instance in Amazon EC2 at a cost of $ 3860 year. Reported experimental results about Precision, Recall, F-Measure, Accuracy, and Cohen's Kappa show the feasibility and effectiveness of the proposal. The experiments prove that words contained in domain names do have a relation with the kind of traffic directed towards them, therefore using specifically trained word embeddings we are able to classify them in customizable categories. We also show that training word embeddings on larger natural language corpuses leads improvements in terms of precision up to 180%.

Evaluation of unsupervised semantic mapping of natural language with Leximancer concept mapping

The Leximancer system is a relatively new method for transforming lexical co-occurrence information from natural language into semantic patterns in an unsupervised manner. It employs two stages of co-occurrence information extraction-semantic and relational-using a different algorithm for each stage. The algorithms used are statistical, but they employ nonlinear dynamics and machine learning. This article is an attempt to validate the output of Leximancer, using a set of evaluation criteria taken from content analysis that are appropriate for knowledge discovery tasks.

A unification-based natural language interface to a database.

An implementation of a Lexical Functional Grammar (LFG) natural language front-end to a database is presented, and its capabilities demonstrated by reference to a set of queries used in the Chat-80 system. The potential of LFG for such applications is explored. Other grammars previously used for this purpose are briefly reviewed and contrasted with LFG. The basic LFG formalism is fully described, both as to its syntax and semantics, and the deficiencies of the latter for database access application shown. Other current LFG implementations are reviewed and contrasted with the LFG implementation developed here specifically for database access. The implementation described here allows a natural language interface to a specific Prolog database to be produced from a set of grammar rule and lexical specifications in an LFG-like notation. In addition to this the interface system uses a simple database description to compile metadata about the database for later use in planning the execution of queries. Extensions to LFG's semantic component are shown to be necessary to produce a satisfactory functional analysis and semantic output for querying a database. A diverse set of natural language constructs are analysed using LFG and the derivation of Prolog queries from the F-structure output of LFG is illustrated. The functional description produced from LFG is proposed as sufficient for resolving many problems of quantification and attachment.

Collocation:applications and implications

All aspects of the concept of collocation – the phenomenon whereby words naturally tend to occur in the company of a restricted set of other words – are covered in this book. It deals in detail with the history of the word collocation, the concepts associated with it and its use in a linguistic context. The authors show the practical means by which the collocational behaviour of words can be explored using illustrative computer programs and examine applications in teaching, lexicography and natural language processing that use collocation in formation. The book investigates the place that collocation occupies in theories of language and provides a thoroughly comprehensive and up-to-date survey of the current position of collocation in language studies and applied linguistics. This text presents a comprehensive description of collocation, covering both the theoretical and practical background and the implications and applications of the concept as language model and analytical tool. It provides a definitive survey of currently available techniques and a detailed description of their implementation.

A weakly-supervised Bayesian model for violence detection from social media

Social streams have proven to be the mostup-to-date and inclusive information on cur-rent events. In this paper we propose a novelprobabilistic modelling framework, called violence detection model (VDM), which enables the identification of text containing violent content and extraction of violence-related topics over social media data. The proposed VDM model does not require any labeled corpora for training, instead, it only needs the in-corporation of word prior knowledge which captures whether a word indicates violence or not. We propose a novel approach of deriving word prior knowledge using the relative entropy measurement of words based on the in-tuition that low entropy words are indicative of semantically coherent topics and therefore more informative, while high entropy words indicates words whose usage is more topical diverse and therefore less informative. Our proposed VDM model has been evaluated on the TREC Microblog 2011 dataset to identify topics related to violence. Experimental results show that deriving word priors using our proposed relative entropy method is more effective than the widely-used information gain method. Moreover, VDM gives higher violence classification results and produces more coherent violence-related topics compared toa few competitive baselines.

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.