We present an annotated corpus of English cooking recipe procedures, and describe and evaluate computational methods for learning these annotations. The corpus consists of 300 recipes written by members of the public, which we have annotated with domain-specific linguistic and semantic structure. Each recipe is annotated with (1) ‘recipe named entities’ (r-NEs) specific to the recipe domain, and (2) a flow graph representing in detail the sequencing of steps, and interactions between cooking tools, food ingredients and the products of intermediate steps. For these two kinds of annotations, inter-annotator agreement ranges from 82.3 to 90.5 F1, indicating that our annotation scheme is appropriate and consistent. We experiment with producing these annotations automatically. For r-NE tagging we train a deep neural network NER tool; to compute flow graphs we train a dependency-style parsing procedure which we apply to the entire sequence of r-NEs in a recipe. In evaluations, our systems achieve 71.1 to 87.5 F1, demonstrating that our annotation scheme is learnable.

We present a linguistic analysis of a set of English and Spanish verb+noun combinations (VNCs), and a method to use this information to improve VNC identification. Firstly, a sample of frequent VNCs are analysed in-depth and tagged along lexico-semantic and morphosyntactic dimensions, obtaining satisfactory inter-annotator agreement scores. Then, a VNC identification experiment is undertaken, where the analysed linguistic data is combined with chunking information and syntactic dependencies. A comparison between the results of the experiment and the results obtained by a basic detection method shows that VNC identification can be greatly improved by using linguistic information, as a large number of additional occurrences are detected with high precision.

BACKGROUND: Electronic medical records (EMRs) are revolutionizing health-related research. One key issue for study quality is the accurate identification of patients with the condition of interest. Information in EMRs can be entered as structured codes or unstructured free text. The majority of research studies have used only coded parts of EMRs for case-detection, which may bias findings, miss cases, and reduce study quality. This review examines whether incorporating information from text into case-detection algorithms can improve research quality. METHODS: A systematic search returned 9659 papers, 67 of which reported on the extraction of information from free text of EMRs with the stated purpose of detecting cases of a named clinical condition. Methods for extracting information from text and the technical accuracy of case-detection algorithms were reviewed. RESULTS: Studies mainly used US hospital-based EMRs, and extracted information from text for 41 conditions using keyword searches, rule-based algorithms, and machine learning methods. There was no clear difference in case-detection algorithm accuracy between rule-based and machine learning methods of extraction. Inclusion of information from text resulted in a significant improvement in algorithm sensitivity and area under the receiver operating characteristic in comparison to codes alone (median sensitivity 78% (codes + text) vs 62% (codes), P = .03; median area under the receiver operating characteristic 95% (codes + text) vs 88% (codes), P = .025). CONCLUSIONS: Text in EMRs is accessible, especially with open source information extraction algorithms, and significantly improves case detection when combined with codes. More harmonization of reporting within EMR studies is needed, particularly standardized reporting of algorithm accuracy metrics like positive predictive value (precision) and sensitivity (recall).

Manually labeling documents for training a text classifier is expensive and time-consuming. Moreover, a classifier trained on labeled documents may suffer from overfitting and adaptability problems. Dataless text classification (DLTC) has been proposed as a solution to these problems, since it does not require labeled documents. Previous research in DLTC has used explicit semantic analysis of Wikipedia content to measure semantic distance between documents, which is in turn used to classify test documents based on nearest neighbours. The semantic-based DLTC method has a major drawback in that it relies on a large-scale, finely-compiled semantic knowledge base, which is difficult to obtain in many scenarios. In this paper we propose a novel kind of model, descriptive LDA (DescLDA), which performs DLTC with only category description words and unlabeled documents. In DescLDA, the LDA model is assembled with a describing device to infer Dirichlet priors from prior descriptive documents created with category description words. The Dirichlet priors are then used by LDA to induce category-aware latent topics from unlabeled documents. Experimental results with the 20Newsgroups and RCV1 datasets show that: (1) our DLTC method is more effective than the semantic-based DLTC baseline method; and (2) the accuracy of our DLTC method is very close to state-of-the-art supervised text classification methods. As neither external knowledge resources nor labeled documents are required, our DLTC method is applicable to a wider range of scenarios.

Although the distributional hypothesis has been applied successfully in many natural language processing tasks, systems using distributional information have been limited to a single domain because the distribution of a word can vary between domains as the word’s predominant meaning changes. However, if it were possible to predict how the distribution of a word changes from one domain to another, the predictions could be used to adapt a system trained in one domain to work in another. We propose an unsupervised method to predict the distribution of a word in one domain, given its distribution in another domain. We evaluate our method on two tasks: cross-domain part-of-speech tagging and cross-domain sentiment classification. In both tasks, our method significantly outperforms competitive baselines and returns results that are statistically comparable to current state-of-the-art methods, while requiring no task-specific customisations.

Automatic classification of sentiment is important for numerous applications such as opinion mining, opinion summarization, contextual advertising, and market analysis. Typically, sentiment classification has been modeled as the problem of training a binary classifier using reviews annotated for positive or negative sentiment. However, sentiment is expressed differently in different domains, and annotating corpora for every possible domain of interest is costly. Applying a sentiment classifier trained using labeled data for a particular domain to classify sentiment of user reviews on a different domain often results in poor performance because words that occur in the train (source) domain might not appear in the test (target) domain. We propose a method to overcome this problem in cross-domain sentiment classification. First, we create a sentiment sensitive distributional thesaurus using labeled data for the source domains and unlabeled data for both source and target domains. Sentiment sensitivity is achieved in the thesaurus by incorporating document level sentiment labels in the context vectors used as the basis for measuring the distributional similarity between words. Next, we use the created thesaurus to expand feature vectors during train and test times in a binary classifier. The proposed method significantly outperforms numerous baselines and returns results that are comparable with previously proposed cross-domain sentiment classification methods on a benchmark data set containing Amazon user reviews for different types of products. We conduct an extensive empirical analysis of the proposed method on single- and multisource domain adaptation, unsupervised and supervised domain adaptation, and numerous similarity measures for creating the sentiment sensitive thesaurus. Moreover, our comparisons against the SentiWordNet, a lexical resource for word polarity, show that the created sentiment-sensitive thesaurus accurately captures words that express similar sentiments.

We introduce dependency parsing schemata, a formal framework based on Sikkel's parsing schemata for constituency parsers, which can be used to describe, analyze, and compare dependency parsing algorithms. We use this framework to describe several well-known projective and non-projective dependency parsers, build correctness proofs, and establish formal relationships between them. We then use the framework to define new polynomial-time parsing algorithms for various mildly non-projective dependency formalisms, including well-nested structures with their gap degree bounded by a constant k in time O(n5+2k), and a new class that includes all gap degree k structures present in several natural language treebanks (which we call mildly ill-nested structures for gap degree k) in time O(n4+3k). Finally, we illustrate how the parsing schema framework can be applied to Link Grammar, a dependency-related formalism.

Zarri's book summarizes more than a decade of his research on knowledge representation for narrative text.The centerpiece of Zarri's work is the Narrative Knowledge Representation Language (NKRL), which he describes and compares to other competing theories.In addition, he discusses how to model the meaning of narrative text by giving many real-world examples.NKRL provides three different components or capabilities: (a) a representation system, (b) inferencing, and (c) an implementation.It is implemented via a Java-based system that shows how a representational theory can be applied to narrative texts.The book consists of five chapters and two appendices.Chapter 1 introduces the basic principles of NKRL.The chapter first defines the focus on nonfiction narratives by contrasting the domain with fictional narratives, for example, a novel.Zarri chooses n-ary predicates in order to represent events formally.He argues for a neo-Davidsonian knowledge representation following Schank (1980), Schubert (1976), and others, and at the same time he sets his approach apart from the knowledge representation proposals one can find in Semantic Web representation languages such as RDF and OWL.However, Zarri emphasizes that NKRL, despite its similarity to conceptual graphs (Sowa 1999), is more focused on practical applications.The chapter concludes by introducing so-called templates in an attempt to demonstrate the practical usefulness of NKRL.Chapter 2 provides an in-depth description of NKRL.Four connected components are introduced: r The definitional component provides a hierarchy of abstract concepts (e.g., artifact, company, activity) called HClass (hierarchy of classes).r The descriptive component is a hierarchy of event types called HTemp (hierarchy of templates) commonly found in the domain of non-fiction narratives (e.g., moving an object, producing a task or activity).r The factual component describes the concrete instantiation of an event.For example, the sentence Berlex Laboratories have performed an evaluation of a given compound would be represented as [

There has been a great deal of recent research into word sense disambiguation, particularly since the inception of the Senseval evaluation exercises. Because a word often has more than one meaning, resolving word sense ambiguity could benefit applications that need some level of semantic interpretation of language input. A major problem is that the accuracy of word sense disambiguation systems is strongly dependent on the quantity of manually sense-tagged data available, and even the best systems, when tagging every word token in a document, perform little better than a simple heuristic that guesses the first, or predominant, sense of a word in all contexts. The success of this heuristic is due to the skewed nature of word sense distributions. Data for the heuristic can come from either dictionaries or a sample of sense-tagged data. However, there is a limited supply of the latter, and the sense distributions and predominant sense of a word can depend on the domain or source of a document. (The first sense of “star” for example would be different in the popular press and scientific journals). In this article, we expand on a previously proposed method for determining the predominant sense of a word automatically from raw text. We look at a number of different data sources and parameterizations of the method, using evaluation results and error analyses to identify where the method performs well and also where it does not. In particular, we find that the method does not work as well for verbs and adverbs as nouns and adjectives, but produces more accurate predominant sense information than the widely used SemCor corpus for nouns with low coverage in that corpus. We further show that the method is able to adapt successfully to domains when using domain specific corpora as input and where the input can either be hand-labeled for domain or automatically classified.

We describe the new release of the RASP (robust accurate statistical parsing) system, designed for syntactic annotation of free text. The new version includes a revised and more semantically-motivated output representation, an enhanced grammar and part-of-speech tagger lexicon, and a more flexible and semi-supervised training method for the structural parse ranking model. We evaluate the released version on the WSJ using a relational evaluation scheme, and describe how the new release allows users to enhance performance using (in-domain) lexical information.

For one aspect of grammatical annotation, part-of-speech tagging, we investigate experimentally whether the ceiling on accuracy stems from limits to the precision of tag definition or limits to analysts' ability to apply precise definitions, and we examine how analysts' performance is affected by alternative types of semi-automatic support. We find that, even for analysts very well-versed in a part-of-speech tagging scheme, human ability to conform to the scheme is a more serious constraint than precision of scheme definition. We also find that although semi-automatic techniques can greatly increase speed relative to manual tagging, they have little effect on accuracy, either positively (by suggesting valid candidate tags) or negatively (by lending an appearance of authority to incorrect tag assignments). On the other hand, it emerges that there are large differences between individual analysts with respect to usability of particular types of semi-automatic support.

In word sense disambiguation (WSD), the heuristic of choosing the most common sense is extremely powerful because the distribution of the senses of a word is often skewed. The problem with using the predominant, or first sense heuristic, aside from the fact that it does not take surrounding context into account, is that it assumes some quantity of hand-tagged data. Whilst there are a few hand-tagged corpora available for some languages, one would expect the frequency distribution of the senses of words, particularly topical words, to depend on the genre and domain of the text under consideration. We present work on the use of a thesaurus acquired from raw textual corpora and the WordNet similarity package to find predominant noun senses automatically. The acquired predominant senses give a precision of 64% on the nouns of the SENSEVAL-2 English all-words task. This is a very promising result given that our method does not require any hand-tagged text, such as SemCor. Furthermore, we demonstrate that our method discovers appropriate predominant senses for words from two domain-specific corpora.

Selectional preferences have been used by word sense disambiguation (WSD) systems as one source of disambiguating information. We evaluate WSD using selectional preferences acquired for English adjective—noun, subject, and direct object grammatical relationships with respect to a standard test corpus. The selectional preferences are specific to verb or adjective classes, rather than individual word forms, so they can be used to disambiguate the co-occurring adjectives and verbs, rather than just the nominal argument heads. We also investigate use of the one-senseper-discourse heuristic to propagate a sense tag for a word to other occurrences of the same word within the current document in order to increase coverage. Although the preferences perform well in comparison with other unsupervised WSD systems on the same corpus, the results show that for many applications, further knowledge sources would be required to achieve an adequate level of accuracy and coverage. In addition to quantifying performance, we analyze the results to investigate the situations in which the selectional preferences achieve the best precision and in which the one-sense-per-discourse heuristic increases performance.

The RAGS proposals for generic specification of NLG systems includes a detailed account of data representation, but only an outline view of processing aspects. In this paper we introduce a modular processing architecture with a concrete implementation which aims to meet the RAGS goals of transparency and reusability. We illustrate the model with the RICHES system -- a generation system built from simple linguistically-motivated modules.

We describe two newly developed computational tools for morphological processing: a program for analysis of English inflectional morphology, and a morphological generator, automatically derived from the analyser. The tools are fast, being based on finite-state techniques, have wide coverage, incorporating data from various corpora and machine readable dictionaries, and are robust, in that they are able to deal effectively with unknown words. The tools are freely available. We evaluate the accuracy and speed of both tools and discuss a number of practical applications in which they have been put to use.

In practical natural language generation systems it is often advantageous to have a separate component that deals purely with morphological processing. We present such a component: a fast and robust morphological generator for English based on finite-state techniques that generates a word form given a specification of the lemma, part-of-speech, and the type of inflection required. We describe how this morphological generator is used in a prototype system for automatic simplification of English newspaper text, and discuss practical morphological and orthographic issues we have encountered in generation of unrestricted text within this application.

This paper describes new and improved techniques which help a unification-based parser to process input efficiently and robustly. In combination these methods result in a speed-up in parsing time of more than an order of magnitude. The methods are correct in the sense that none of them rule out legal rule applications.

The paper demonstrates that exponential complexities with respect to grammar size and input length have little impact on the performance of three unification-based parsing algorithms, using a wide-coverage grammar. The results imply that the study and optimisation of unification-based parsing must rely on empirical data until complexity theory can more accurately predict the practical behaviour of such parsers1.

A formalism is presented for lexical specification in unification-based grammars which exploits defeasible multiple inheritance to express regularity, sub-regularity, and exceptions in classifying the properties of words. Such systems are in the general case intractable; the present proposal represents an attempt to reduce complexity while retaining sufficient expressive power for the task at hand. Illustrative examples are given of morphological analyses from English and German.

Recent developments in generation algorithms have enabled work in unification-based computational linguistics to approach more closely the ideal of grammars as declarative statements of linguistic facts, neutral between analysis and synthesis. From this perspective, however, the situation is still far from perfect; all known methods of generation impose constraints on the grammars they assume.We briefly consider a number of proposals for generation, outlining their consequences for the form of grammars, and then report on experience arising from the addition of a generator to an existing unification environment. The algorithm in question (based on that of Shieber et al. (1989)), though among the most permissive currently available, excludes certain classes of parsable analyses.

We describe a methodology and associated software system for the construction of a large lexicon from an existing machine-readable (published) dictionary. The lexicon serves as a component of an English morphological and syntactic analyser and contains entries with grammatical definitions compatible with the word and sentence grammar employed by the analyser. We describe a software system with two integrated components. One of these is capable of extracting syntactically rich, theory-neutral lexical templates from a suitable machine-readable source. The second supports interactive and semi-automatic generation and testing of target lexical entries in order to derive a sizeable, accurate and consistent lexicon from the source dictionary which contains partial (and occasionally in-accurate) information. Finally, we evaluate the utility of the Longman Dictionary of Contemporary English as a suitable source dictionary for the target lexicon.