My last column ended with some comments about Kuhn and word2vec. Word2vec has racked up plenty of citations because it satisifies both of Kuhn’s conditions for emerging trends: (1) a few initial (promising, if not convincing) successes that motivate early adopters (students) to do more, as well as (2) leaving plenty of room for early adopters to contribute and benefit by doing so. The fact that Google has so much to say on ‘How does word2vec work’ makes it clear that the definitive answer to that question has yet to be written. It also helps citation counts to distribute code and data to make it that much easier for the next generation to take advantage of the opportunities (and cite your work in the process).

IBM Research has over 200 people working on Unstructured Information Management (UIM) technologies with a strong focus on Natural Language Processing (NLP). These researchers are engaged in activities ranging from natural language dialog, information retrieval, topic-tracking, named-entity detection, document classification and machine translation to bioinformatics and open-domain question answering. An analysis of these activities strongly suggested that improving the organization's ability to quickly discover each other's results and rapidly combine different technologies and approaches would accelerate scientific advance. Furthermore, the ability to reuse and combine results through a common architecture and a robust software framework would accelerate the transfer of research results in NLP into IBM's product platforms. Market analyses indicating a growing need to process unstructured information, specifically multilingual, natural language text, coupled with IBM Research's investment in NLP, led to the development of middleware architecture for processing unstructured information dubbed UIMA. At the heart of UIMA are powerful search capabilities and a data-driven framework for the development, composition and distributed deployment of analysis engines. In this paper we give a general introduction to UIMA focusing on the design points of its analysis engine architecture and we discuss how UIMA is helping to accelerate research and technology transfer.

This paper is an introduction to natural language interfaces to databases (NLIDBS). A brief overview of the history of NLIDBS is first given. Some advantages and disadvantages of NLIDBS are then discussed, comparing NLIDBS to formal query languages, form-based interfaces, and graphical interfaces. An introduction to some of the linguistic problems NLIDBS have to confront follows, for the benefit of readers less familiar with computational linguistics. The discussion then moves on to NLIDB architectures, portability issues, restricted natural language input systems (including menu-based NLIDBS), and NLIDBS with reasoning capabilities. Some less explored areas of NLIDB research are then presented, namely database updates, meta-knowledge questions, temporal questions, and multi-modal NLIDBS. The paper ends with reflections on the current state of the art.

This paper identifies some linguistic properties of technical terminology, and uses them to formulate an algorithm for identifying technical terms in running text. The grammatical properties discussed are preferred phrase structures: technical terms consist mostly of noun phrases containing adjectives, nouns, and occasionally prepositions; rerely do terms contain verbs, adverbs, or conjunctions. The discourse properties are patterns of repetition that distinguish noun phrases that are technical terms, especially those multi-word phrases that constitute a substantial majority of all technical vocabulary, from other types of noun phrase.

The paper presents a terminology indentification algorithm that is motivated by these linguistic properties. An implementation of the algorithm is described; it recovers a high proportion of the technical terms in a text, and a high proportaion of the recovered strings are vaild technical terms. The algorithm proves to be effective regardless of the domain of the text to which it is applied.

By all accounts, 2016 is the year of the chatbot. Some commentators take the view that chatbot technology will be so disruptive that it will eliminate the need for websites and apps. But chatbots have a long history. So what's new, and what's different this time? And is there an opportunity here to improve how our industry does technology transfer?

In this article, we give an overview of Natural Language Generation (NLG) from an applied system-building perspective. The article includes a discussion of when NLG techniques should be used; suggestions for carrying out requirements analyses; and a description of the basic NLG tasks of content determination, discourse planning, sentence aggregation, lexicalization, referring expression generation, and linguistic realisation. Throughout, the emphasis is on established techniques that can be used to build simple but practical working systems now. We also provide pointers to techniques in the literature that are appropriate for more complicated scenarios.

GPT-3 made the mainstream media headlines this year, generating far more interest than we’d normally expect of a technical advance in NLP. People are fascinated by its ability to produce apparently novel text that reads as if it was written by a human. But what kind of practical applications can we expect to see, and can they be trusted?

Parsing unrestricted text is useful for many language technology applications but requires parsing methods that are both robust and efficient. MaltParser is a language-independent system for data-driven dependency parsing that can be used to induce a parser for a new language from a treebank sample in a simple yet flexible manner. Experimental evaluation confirms that MaltParser can achieve robust, efficient and accurate parsing for a wide range of languages without language-specific enhancements and with rather limited amounts of training data.

As users struggle to navigate the wealth of on-line information now available, the need for automated question answering systems becomes more urgent. We need systems that allow a user to ask a question in everyday language and receive an answer quickly and succinctly, with sufficient context to validate the answer. Current search engines can return ranked lists of documents, but they do not deliver answers to the user.

Question answering systems address this problem. Recent successes have been reported in a series of question-answering evaluations that started in 1999 as part of the Text Retrieval Conference (TREC). The best systems are now able to answer more than two thirds of factual questions in this evaluation.

With growing interest in Chinese Language Processing, numerous NLP tools (e.g., word segmenters, part-of-speech taggers, and parsers) for Chinese have been developed all over the world. However, since no large-scale bracketed corpora are available to the public, these tools are trained on corpora with different segmentation criteria, part-of-speech tagsets and bracketing guidelines, and therefore, comparisons are difficult. As a first step towards addressing this issue, we have been preparing a large bracketed corpus since late 1998. The first two installments of the corpus, 250 thousand words of data, fully segmented, POS-tagged and syntactically bracketed, have been released to the public via LDC (www.ldc.upenn.edu). In this paper, we discuss several Chinese linguistic issues and their implications for our treebanking efforts and how we address these issues when developing our annotation guidelines. We also describe our engineering strategies to improve speed while ensuring annotation quality.

Shannon (1948) showed that a wide range of practical problems can be reduced to the problem of estimating probability distributions of words and ngrams in text. It has become standard practice in text compression, speech recognition, information retrieval and many other applications of Shannon's theory to introduce a “bag-of-words” assumption. But obviously, word rates vary from genre to genre, author to author, topic to topic, document to document, section to section, and paragraph to paragraph. The proposed Poisson mixture captures much of this heterogeneous structure by allowing the Poisson parameter θ to vary over documents subject to a density function φ. φ is intended to capture dependencies on hidden variables such genre, author, topic, etc. (The Negative Binomial is a well-known special case where φ is a Г distribution.) Poisson mixtures fit the data better than standard Poissons, producing more accurate estimates of the variance over documents (σ2), entropy (H), inverse document frequency (IDF), and adaptation (Pr(x ≥ 2/x ≥ 1)).

Applications of speech recognition are now widespread, but user-centred evaluation methods are necessary to ensure their success. Objective evaluation techniques are fairly well established, but previous subjective techniques have been unstructured and unproven. This paper reports on the first stage in the development of a questionnaire measure for the Subjective Assessment of Speech System Interfaces (SASSI). The aim of the research programme is to produce a valid, reliable and sensitive measure of users' subjective experiences with speech recognition systems. Such a technique could make an important contribution to theory and practice in the design and evaluation of speech recognition systems according to best human factors practice. A prototype questionnaire was designed, based on established measures for evaluating the usability of other kinds of user interface, and on a review of the research literature into speech system design. This consisted of 50 statements with which respondents rated their level of agreement. The questionnaire was given to users of four different speech applications, and Exploratory Factor Analysis of 214 completed questionnaires was conducted. This suggested the presence of six main factors in users' perceptions of speech systems: System Response Accuracy, Likeability, Cognitive Demand, Annoyance, Habitability and Speed. The six factors have face validity, and a reasonable level of statistical reliability. The findings form a useful theoretical and practical basis for the subjective evaluation of any speech recognition interface. However, further work is recommended, to establish the validity and sensitivity of the approach, before a final tool can be produced which warrants general use.

We introduce an architecture and toolkit for building dialogue managers currently being developed in the TRINDI project, based on the notions of information state and dialogue move engine. The aim is to provide a framework for experimenting with implementations of different theories of information state, information state update and dialogue control. A number of dialogue managers are currently being built using the toolkit, and we present overviews of two of them. We believe that this framework will make implementation of dialogue processing theories easier, also facilitating comparison of different types of dialogue systems, thus helping to achieve a prerequisite for arriving at a best practice for the development of the dialogue management component of a spoken dialogue system.

One of the main challenges in question-answering is the potential mismatch between the expressions in questions and the expressions in texts. While humans appear to use inference rules such as ‘X writes Y’ implies ‘X is the author of Y’ in answering questions, such rules are generally unavailable to question-answering systems due to the inherent difficulty in constructing them. In this paper, we present an unsupervised algorithm for discovering inference rules from text. Our algorithm is based on an extended version of Harris’ Distributional Hypothesis, which states that words that occurred in the same contexts tend to be similar. Instead of using this hypothesis on words, we apply it to paths in the dependency trees of a parsed corpus. Essentially, if two paths tend to link the same set of words, we hypothesize that their meanings are similar. We use examples to show that our system discovers many inference rules easily missed by humans.

Natural language processing (NLP) techniques can be used to make inferences about peoples’ mental states from what they write on Facebook, Twitter and other social media. These inferences can then be used to create online pathways to direct people to health information and assistance and also to generate personalized interventions. Regrettably, the computational methods used to collect, process and utilize online writing data, as well as the evaluations of these techniques, are still dispersed in the literature. This paper provides a taxonomy of data sources and techniques that have been used for mental health support and intervention. Specifically, we review how social media and other data sources have been used to detect emotions and identify people who may be in need of psychological assistance; the computational techniques used in labeling and diagnosis; and finally, we discuss ways to generate and personalize mental health interventions. The overarching aim of this scoping review is to highlight areas of research where NLP has been applied in the mental health literature and to help develop a common language that draws together the fields of mental health, human-computer interaction and NLP.

The KIM platform provides a novel Knowledge and Information Management framework and services for automatic semantic annotation, indexing, and retrieval of documents. It provides a mature and semantically enabled infrastructure for scalable and customizable information extraction (IE) as well as annotation and document management, based on GATE.General Architecture for Text Engineering (GATE) (http://gate.ac.uk), leading NLP and IE platform developed at the University of Sheffield. Our understanding is that a system for semantic annotation should be based upon a simple model of real-world entity concepts, complemented with quasi-exhaustive instance knowledge. To ensure efficiency, easy sharing, and reusability of the metadata we introduce an upper-level ontology. Based on the ontology, a large-scale instance base of entity descriptions is maintained. The knowledge resources involved are handled by use of state-of-the-art Semantic Web technology and standards, including RDF(S) repositories, ontology middleware and reasoning. From a technical point of view, the platform allows KIM-based applications to use it for automatic semantic annotation, for content retrieval based on semantic queries, and for semantic repository access. As a framework, KIM also allows various IE modules, semantic repositories and information retrieval engines to be plugged into it. This paper presents the KIM platform, with an emphasis on its architecture, interfaces, front-ends, and other technical issues.

In recent years, the interest among the research community in sentiment analysis (SA) has grown exponentially. It is only necessary to see the number of scientific publications and forums or related conferences to understand that this is a field with great prospects for the future. On the other hand, the Twitter boom has boosted investigation in this area due fundamentally to its potential applications in areas such as business or government intelligence, recommender systems, graphical interfaces and virtual assistance. However, to fully understand this issue, a profound revision of the state of the art is first necessary. It is for this reason that this paper aims to represent a starting point for those investigations concerned with the latest references to Twitter in SA.

To respond correctly to a free form factual question given a large collection of text data, one needs to understand the question to a level that allows determining some of the constraints the question imposes on a possible answer. These constraints may include a semantic classification of the sought after answer and may even suggest using different strategies when looking for and verifying a candidate answer. This work presents a machine learning approach to question classification. Guided by a layered semantic hierarchy of answer types, we develop a hierarchical classifier that classifies questions into fine-grained classes. This work also performs a systematic study of the use of semantic information sources in natural language classification tasks. It is shown that, in the context of question classification, augmenting the input of the classifier with appropriate semantic category information results in significant improvements to classification accuracy. We show accurate results on a large collection of free-form questions used in TREC 10 and 11.

Finite state cascades represent an attractive architecture for parsing unrestricted text. Deterministic parsers specified by finite state cascades are fast and reliable. They can be extended at modest cost to construct parse trees with finite feature structures. Finally, such deterministic parsers do not necessarily involve trading off accuracy against speed — they may in fact be more accurate than exhaustive search stochastic context free parsers.

This paper addresses the problem of distribution of words and phrases in text, a problem of great general interest and of importance for many practical applications. The existing models for word distribution present observed sequences of words in text documents as an outcome of some stochastic processes; the corresponding distributions of numbers of word occurrences in the documents are modelled as mixtures of Poisson distributions whose parameter values are fitted to the data. We pursue a linguistically motivated approach to statistical language modelling and use observable text characteristics as model parameters. Multi-word technical terms, intrinsically content entities, are chosen for experimentation. Their occurrence and the occurrence dynamics are investigated using a 100-million word data collection consisting of a variety of about 13,000 technical documents. The derivation of models describing word distribution in text is based on a linguistic interpretation of the process of text formation, with the probabilities of word occurrence being functions of observable and linguistically meaningful text characteristics. The adequacy of the proposed models for the description of actually observed distributions of words and phrases in text is confirmed experimentally. The paper has two focuses: one is modelling of the distributions of content words and phrases among different documents; and another is word occurrence dynamics within documents and estimation of corresponding probabilities. Accordingly, among the application areas for the new modelling paradigm are information retrieval and speech recognition.