Abstract The paper reviews the state of the art of natural language engineering (NLE) around 1995, when this journal first appeared, and makes a critical comparison with the current state of the art in 2018, as we prepare the 25th Volume. Specifically the then state of the art in parsing, information extraction, chatbots, and dialogue systems, speech processing and machine translation are briefly reviewed. The emergence in the 1980s and 1990s of machine learning (ML) and statistical methods (SM) is noted. Important trends and areas of progress in the subsequent years are identified. In particular, the move to the use of n-grams or skip grams and/or chunking with part of speech tagging and away from whole sentence parsing is noted, as is the increasing dominance of SM and ML. Some outstanding issues which merit further research are briefly pointed out, including metaphor processing and the ethical implications of NLE.

This paper describes a new approach to detection and tracking of potential cyberattacks from analyzing large quantities of cyber-related webpage text, using ontological knowledge about such attacks combined with composable causal models represented in Probabilistic Soft Logic. The stages of a cyberattack kill chain are viewed as a sequence of both observed and unobserved events (e.g., reconnaissance, weaponize, exploit, install) and explicit mentions of, or related to, such events are examined as potential signals for a future attack. Using a suite of natural language processing techniques, sentences from input news texts are automatically classified according to the described cyberattack event, then enriched with named entity recognition for the rapid detection of key elements that might be associated with potential cyberattacks. We present our work as a framework for rapid and flexible predictive analysis of the ever-increasing amount of cyber-related text data, with initial experiments indicating that event detection using parsing and named entity recognition combined with statistical relational learning show promise in time-series prediction from news text.

This Blue Sky presentation focuses on a major shift toward a notion of “ambient intelligence” that transcends general applications targeted at the general population. The focus is on highly personalized agents that accommodate individual differences and changes over time. This notion of Extended Ambient Intelligence (EAI) concerns adaptation to a person’s preferences and experiences, as well as changing capabilities, most notably in an environment where conversational engagement is central. An important step in moving this research forward is the accommodation of different degrees of cognitive capability (including speech processing) that may vary over time for a given user—whether through improvement or through deterioration. We suggest that the application of divergence detection to speech patterns may enable adaptation to a speaker’s increasing or decreasing level of speech impairment over time. Taking an adaptive approach toward technology development in this arena may be a first step toward empowering those with special needs so that they may live with a high quality of life. It also represents an important step toward a notion of ambient intelligence that is personalized beyond what can be achieved by mass-produced, one-size-fits-all software currently in use on mobile devices.

CLAROS (Classical Art Research Online Services; www.clarosweb.org) is an international interdisciplinary research initiative led by the University of Oxford (Humanities and Mathematics and Physical Sciences), hosted by the Oxford e-Research Centre (OeRC, www.oerc.ox.ac.uk), and inspired by the Beazley Archive (www.beazley.ox.ac.uk) participating in EU R&D projects. During 2009, a pump-priming grant from the University's Fell Fund enabled CLAROS to integrate on line more than two million records and images held in research centres in Oxford, Paris, Cologne and Berlin. CLAROS uses CIDOC CRM (http://cidoc.ics.forth.gr/), developed under UNESCO's ICOM (http://icom.museum/), to map across datasets and a portfolio of Open Source software to deliver them swiftly to a broad range of global users. Data web applications for integration are being developed by Zoology (http://ibrg.zoo.ox.ac.uk/), image recognition by Engineering Science (www.robots.ox.ac.uk/~vgg/), and artificial intelligence by the Oxford Internet Institute (www.oii.ox.ac.uk). CLAROS will welcome new institutional members and engage with the public to document art and disseminate results.

The title of this piece refers to Newton’s only known modest remark: “If I have seen farther than other men, it was because I was standing on the shoulders of giants.” Since he himself was so much greater than his predecessors, he was in fact standing on the shoulders of dwarfs, a much less attractive metaphor. I intend no comparisons with Newton inwhat follows: NLP/CL has noNewtons and noNobel Prizes so far, and quite rightly. I intend only to draw attention to a tendency in our field to ignore its intellectual inheritance and debt; I intend to discharge a little of this debt in this article, partly as an encouragement to others to improve our lack of scholarship and knowledge of our own roots, often driven by the desire for novelty and to name our own systems. Roger Schank used to argue that it was crucial to name your own NLP system and then have lots of students to colonize all major CS departments, although time has not been kind to his many achievements and originalities, even though he did build just such an Empire. But to me one of the most striking losses from our corporate memory is the man who is to me the greatest of the first generation and still with us: Vic Yngve. This is the man who gave us COMIT, the first NLP programming language; the first random generation of sentences; and the first direct link from syntactic structure to parsing processes and storage (the depth hypothesis). I find students now rarely recognize his name, and find that incredible. This phenomenon is more than corporate bad memory, or being too busy with engineering to do the scholarship. It is something endemic in the wider field of Computer Science and Artificial Intelligence, although bottom-up wiki techniques are now filling many historical gaps for those who know where to look, as the generation of pioneers has time to reminisce in retirement.1 There are costs to us from this general lack of awareness, though: a difficulty of “standing on the shoulders” of others and acknowledging debts, let alone passing on software packages. Alan Bundy used to highlight this in theAISB Quarterlywith a regular columnwhere he located and pilloried reinventions in the field of AI; he also recommended giving obituaries for one’s own work, and this paper could be seen in that way, too.

In this paper we present results from the METER (MEasuring TExt Reuse) project whose aim is to explore issues pertaining to text reuse and derivation, especially in the context of newspapers using newswire sources. Although the reuse of text by journalists has been studied in linguistics, we are not aware of any investigation using existing computational methods for this particular task. We investigate the classification of newspaper articles according to their degree of dependence upon, or derivation from, a newswire source using a simple 3-level scheme designed by journalists. Three approaches to measuring text similarity are considered: n-gram overlap, Greedy String Tiling, and sentence alignment. Measured against a manually annotated corpus of source and derived news text, we show that a combined classifier with features automatically selected performs best overall for the ternary classification achieving an average F1-measure score of 0.664 across all three categories.

No abstract available.

Amilcare is a tool for Adaptive Information Extraction (IE) designed for supporting active annotation of documents for the Semantic Web (SW). It can be used either for unsupervised document annotation or as a support for human annotation. Amilcare is portable to new applications/domains without any knowledge of IE, as it just requires users to annotate a small training corpus with the information to be extracted. It is based on (LP)2, a supervised learning strategy for IE able to cope with different texts types, from newspaper-like texts, to rigidly formatted Web pages and even a mixture of them[1][5].Adaptation starts with the definition of a tag set for annotation, possibly organized as an ontology. Then users have to manually annotate a small training corpus. Amilcare provides a default mouse-based interface called Melita, where annotations are inserted by first selecting a tag from the ontology and then identifying the text area to annotate with the mouse. Differently from similar annotation tools [4, 5], Melita actively supports training corpus annotation. While users annotate texts, Amilcare runs in the background learning how to reproduce the inserted annotation. Induced rules are silently applied to new texts and their results are compared with the user annotation. When its rules reach a (user-defined) level of accuracy, Melita presents new texts with a preliminary annotation derived by the rule application. In this case users have just to correct mistakes and add missing annotations. User corrections are inputted back to the learner for retraining. This technique focuses the slow and expensive user activity on uncovered cases, avoiding requiring annotating cases where a satisfying effectiveness is already reached. Moreover validating extracted information is a much simpler task than tagging bare texts (and also less error prone), speeding up the process considerably. At the end of the corpus annotation process, the system is trained and the application can be delivered. MnM [6] and Ontomat annotizer [7] are two annotation tools adopting Amilcare's learner.In this demo we simulate the annotation of a small corpus and we show how and when Amilcare is able to support users in the annotation process, focusing on the way the user can control the tool's proactivity and intrusivity. We will also quantify such support with data derived from a number of experiments on corpora. We will focus on training corpus size and correctness of suggestions when the corpus is increased.

We discuss robustness in LE systems from the perspective of engineering, and the predictability of both outputs and construction process that this entails. We present an architectural system that contributes to engineering robustness and low-overhead systems development (GATE, a General Architecture for Text Engineering). To verify our ideas we present results from the development of a multi-purpose cross-genre Named Entity recognition system. This system aims be robust across diverse input types, and to reduce the need for costly and timeconsuming adaptation of systems to new applications, with its capability to process texts from widely differing domains and genres.

Word sense disambiguation (WSD) is a computational linguistics task likely to benefit from the tradition of combining different knowledge sources in articial intelligence research. An important step in the exploration of this hypothesis is to determine which linguistic knowledge sources are most useful and whether their combination leads to improved results. We present a sense tagger which uses several knowledge sources. Tested accuracy exceeds 94% on our evaluation corpus. Our system attempts to disambiguate all content words in running text rather than limiting itself to treating a restricted vocabulary of words. It is argued that this approach is more likely to assist the creation of practical systems.

This paper is in a form unconventional in modern journals but traditional for the discussion of foundational questions: a dialogue. It is a form that makes it possible to contrast two deeply held but incompatible views, each with its standard forms of defence, in order to seek common ground and make the differences more precise. In artificial intelligence, or at least in the major part of it still committed to symbolic representations, there is a long history of discussion of the origin and nature of the symbols we use in representations, symbols which normally look like words, English words in fact, but which most researchers deny are such words, since to concede that would put in question the abstract nature of the representation. In what follows, we examine our common ground and then diverge over five specific questions on the issue of representations. The discussion focuses on symbol use in representations of language, because there the similarity is most acute—between the representation and the represented—but the issues are general and apply to symbolic AI as such.

In this paper we present results concerning the large scale automatic extraction of pragmatic content from email by a system based on a phrase matching approach to speech act detection combined with empirical detection of speech act patterns in corpora. The results show that most speech acts that occur in this corpus can be recognized by the approach. This investigation is supported by analysis of a corpus consisting of 1000 emails.

Treebanks, such as the Penn Treebank, provide a basis for the automatic creation of broad coverage grammars. In the simplest case, rules can simply be ‘read off’ the parse-annotations of the corpus, producing either a simple or probabilistic context-free grammar. Such grammars, however, can be very large, presenting problems for the subsequent computational costs of parsing under the grammar. In this paper, we explore ways by which a treebank grammar can be reduced in size or ‘compacted’, which involve the use of two kinds of technique: (i) thresholding of rules by their number of occurrences; and (ii) a method of rule-parsing, which has both probabilistic and non-probabilistic variants. Our results show that by a combined use of these two techniques, a probabilistic context-free grammar can be reduced in size by 62% without any loss in parsing performance, and by 71% to give a gain in recall, but some loss in precision.

We describe a software environment to support research and development in natural language (NL) engineering. This environment-GATE (General Architecture for Text Engineering)-aims to advance research in the area of machine processing of natural languages by providing a software infrastructure on top of which heterogeneous NL component modules may be evaluated and refined individually or may be combined into larger application systems. Thus, GATE aims to support both researchers and developers working on component technologies (e.g. parsing, tagging, morphological analysis) and those working on developing end-user applications (e.g. information extraction, text summarisation, document generation, machine translation, and second language learning). GATE will promote reuse of component technology, permit specialisation and collaboration in large-scale projects, and allow for the comparison and evaluation of alternative technologies. The first release of GATE is now available.

We describe a method for obtaining subject-dependent word sets relative to some (subject) domain. Using the subject classifications given in the machine-redable version of Longman's Dictionary of Contemporary English, we established subject-dependent co-occurrence links between words of the defining vocabulary to construct these "neighborhoods". Here, we describe the application of these neighborhoods to information retrieval, and present a method of word sense disambiguation based on these co-occurrences, an extension of previous work.

The paper describes a system of belief representation in which inner, nested, beliefs (what an individual A believes an individual B believes about C are not normally shared permanently with the component belief sets (e.g., the system's view of A, etc.). It is argued that this process is consistent with a general Least Effort Theory of Understanding, and that any assumption that such nested beliefs are already shared and computed, awaiting access, is implausible. This view is also contrasted with a theory of relevance of Sperber and Wilson which claims that dialogue inferences can be computed without the need to separate, or nest, sets of beliefs corresponding to distinct individuals.