Papers reviewed and determined not to be word norm studies. Use the flag icon to report errors or suggest re-inclusion.
18625 papers
This article focuses on the user-friendliness of lexical information sources. Whereas our previous study on user-friendliness (Euralex 1998) emphasized the context-sensitive needs of dictionary users, our present study goes one step further and suggests that it would be possible to compile interactive lexical databases that would be both context- and user-sensitive. We approach the function of lexical databases from two perspectives: from their role as primary information sources and from their role as lexical interfaces to other knowledge bases. Our approach is generally based on frame-semantics.We apply semantic frames to capture the different ways of conceptualization used when searching a knowledge base for social and health care services.
This paper describes the methodology that is being used to augment the Penn Treebank annotation with sense tags and other types of semantic information. Inspired by the results of SENSEVAL, and the high inter-annotator agreement that was achieved there, similar methods were used for a pilot study of 5000 words of running text from the Penn Treebank. Using the same techniques of allowing the annotators to discuss difficult tagging cases and to revise WordNet entries if necessary, comparable inter-annotator rates have been achieved. The criteria for determining appropriate revisions and ensuring clear sense distinctions are described. We are also using hand correction of automatic predicate argument structure information to provide additional thematic role labeling. 1.
We present a method for automatically detecting errors in a manually marked corpus using anomaly detection. Anomaly detection is a method for determining which elements of a large data set do not conform to the whole. This method fits a probability distribution over the data and applies a statistical test to detect anomalous elements. In the corpus error detection problem, anomalous elements are typically marking errors. We present the results of applying this method to the tagged portion of the Penn Treebank corpus.
The present study investigated the relationship between daily diary affect ratings and ambulatory cardiovascular activity in 117 male Vietnam combat veterans (61 with posttraumatic stress disorder [PTSD] and 56 without PTSD). Participants completed 12-14 hr of ambulatory monitoring and daily diary affect ratings. Compared with veterans without PTSD, veterans with PTSD reported higher negative affect and lower positive affect in daily diary ratings. No differences were detected for mean laboratory initial recordings or mean ambulatory heart rate (HR), systolic blood pressure (SBP), or diastolic blood pressure (DBP). However, compared with veterans without PTSD, veterans with PTSD demonstrated higher SBP and DBP variability and a higher proportion of HR activity (compared with initial recording values) during daily activity. There was a significant Time of Day x Group interaction for mean HR, with a trend for PTSD participants to maintain HR levels during evening hours.
This paper proposes a new error-driven HMM-based text chunk tagger with context-dependent lexicon. Compared with standard HMM-based tagger, this tagger uses a new Hidden Markov Modelling approach which incorporates more contextual information into a lexical entry. Moreover, an error-driven learning approach is adopted to decrease the memory requirement by keeping only positive lexical entries and makes it possible to further incorporate more context-dependent lexical entries. Experiments show that this technique achieves overall precision and recall rates of 93.40% and 93.95% for all chunk types, 93.60% and 94.64% for noun phrases, and 94.64% and 94.75% for verb phrases when trained on PENN WSJ TreeBank section 00-19 and tested on section 20-24, while 25-fold validation experiments of PENN WSJ TreeBank show overall precision and recall rates of 96.40% and 96.47% for all chunk types, 96.49% and 96.99% for noun phrases, and 97.13% and 97.36% for verb phrases.
In this paper, we present a neural-networks-based knowledge discovery and data mining (KDDM) methodology based on granular computing, neural computing, fuzzy computing, linguistic computing, and pattern recognition. The major issues include 1) how to make neural networks process both numerical and linguistic data in a data base, 2) how to convert fuzzy linguistic data into related numerical features, 3) how to use neural networks to do numerical-linguistic data fusion, 4) how to use neural networks to discover granular knowledge from numerical-linguistic data bases, and 5) how to use discovered granular knowledge to predict missing data. In order to answer the above concerns, a granular neural network (GNN) is designed to deal with numerical-linguistic data fusion and granular knowledge discovery in numerical-linguistic databases. From a data granulation point of view, the GNN can process granular data in a database. From a data fusion point of view, the GNN makes decisions based on different kinds of granular data. From a KDDM point of view, the GNN is able to learn internal granular relations between numerical-linguistic inputs and outputs, and predict new relations in a database. The GNN is also capable of greatly compressing low-level granular data to high-level granular knowledge with some compression error and a data compression rate. To do KDDM in huge data bases, parallel GNN and distributed GNN will be investigated in the future.
`Linguistic annotation' covers any descriptive or analytic notations applied to raw language data. The basic data may be in the form of time functions - audio, video and/or physiological recordings - or it may be textual. The added notations may include transcriptions of all sorts (from phonetic features to discourse structures), part-of-speech and sense tagging, syntactic analysis, `named entity' identification, co-reference annotation, and so on. While there are several ongoing efforts to provide formats and tools for such annotations and to publish annotated linguistic databases, the lack of widely accepted standards is becoming a critical problem. Proposed standards, to the extent they exist, have focused on file formats. This paper focuses instead on the logical structure of linguistic annotations. We survey a wide variety of existing annotation formats and demonstrate a common conceptual core, the annotation graph. This provides a formal framework for constructing, maintaining and searching linguistic annotations, while remaining consistent with many alternative data structures and file formats.
The paper asks how much structural detail it is reasonable to include in a detailed general-purpose grammar annotation scheme. I argue that there is no principled answer to that question; even grammatical distinctions which in general are clear and linguistically central will often be “distinctions without a difference ” in particular examples. The discipline which offers the closest intellectual precedent for linguistic treebank-compilation activity, biological systematics, is disanalogous from our work in that respect. * Detailed v. skeleton analytic schemes Any scheme for structural annotation of corpora must embody decisions about how much detail to include. Some groups explicitly aim at “skeleton parsing”, marking much less grammatical detail than linguists recognize a language as containing. In many circumstances, this will be a sensible
Lexical functions (LFs), as developed by I. Mel'icuk in the Meaning-Text Theory are a formal means for the representation of collocations. LFs allow for a fine-grained description of collocations with respect to their syntactic and semantic characteristics. However, it has repeatedly been pointed out that the definition of LFs is far from being transparent for linguists and lexicographers not trained in this theoretical framework. Especially problematic from this perspective is the combinatorial capacity of LFs. In this paper, we suggest some criteria for the encoding of collocations in terms of LFs. These criteria draw on LF definitions, i.e., both the syntactic and semantic properties of LFs. The research reported on in the paper is part of an ongoing project within which an on-line collocational dictionary of Spanish is compiled. Our objective is to incorporate a heuristic model the backbone of which are the criteria for the encoding of LFs into an interface of the lexical database. The interface will support the identification of (combinations of) LFs and permit the verification of proposed formulations.
This document describes the bracketing guidelines for the Penn Chinese Treebank Project. The goal of the project is the creation of a 100-thousand-word corpus of Mandarin Chinese text with syntactic bracketing. The Chinese Treebank has been released via the Linguistic Data Consortium (LDC) and is available to the public.\nThis document can be divided into six parts. Section I discusses six fundamental grammatical relations that are represented in the Treebank. Section II introduces the bracketing tagset, which includes 23 syntactic labels, 26 functional tags, and 7 tags for null elements. Section III, IV and V specify our annotation schemata for noun phrases, verbs phrases, and other minor categories, respectively. Section VI describes our treatment for empty categories, such as trace for syntactic movement, PRO for control, and pro for argument drop. Section VII and VIII cover the coordinated clauses and subordinating clauses. Section IX, X and XI specify the way we handle punctuation, ambiguity, and some problematic cases.
The paper describes an example-based parser for Chinese: Tree structure whose size is equal or smaller than the sentence to be parsed are retrieved from a treebank and aligned with the sentence. Subsequent structural adaptations handle unknown words, type shifting and metaphorical extensions of words. Derivational adaptations reanalyze awkward subtrees in order to auto-correct badly matched trees and insert unmatched, previously deleted words. This strategy is crucial for parsing long sentences. We try to illustrate the function of the parser through the analysis of one example sentence in different parsing models. The main concern is to find an optimal strategy for the retrieval of appropriate tree structures and to demonstrate the advantages of fuzzy matches. 1. Introduction The Academia Sinica possesses rich linguistic resources of modern Mandarin Chinese; among them, a manually tagged corpus of about 10 million characters [1] and a lexicon containing about 80,000 words which des...
Structure preserving grammar compaction (SPC) is a simple CFG compaction technique originally described in (van Genabith et al., 1999a, 1999b). It works by generalising category labels and in so doing plugs holes in the grammar. To date the method has been tested on small corpra only. In the present research we apply SPC to a large grammar extracted from the Penn Treebank and examine its effects on rule treebank grammar size and on rule accession rates (as an indicator of grammar completeness). 1 Introduction Tree banks and resources compiled from treebanks are potentially very useful in NLP. Grammars extracted from treebanks --- so called treebank grammars (Charniak, 1996) --- can form the basis of large coverage NLP systems. Such treebank grammars, however, can suffer from several shortcomings: they commonly feature a large number of flat, highly specific rules that may be rarely used, with ensuing costs for processing (load) under the grammar. Furthermore, the observ...
This paper describes the design criteria and annotation guidelines of Sinica Treebank. The three design criteria are: Maximal Resource Sharing, Minimal Structural Complexity, and Optimal Semantic Information. One of the important design decisions following these criteria is the encoding of thematic role information. An on-line interface facilitating empirical studies of Chinese phrase structure is also described.
Structural ambiguity, particularly attachment of prepositional phrases, is a serious type of global ambiguity in Natural Language. The disambiguation becomes crucial when a syntactic analyzer must make the correct decision among at least two equally grammatical parse-trees for the same sentence. This paper attempts to find answers to the problem of how attachment ambiguity can be resolved by utilizing Machine Learning (ML) techniques. ML is founded on the assumption that the performance in cognitive tasks is based on the similarity of new situations (testing) to stored representations of earlier experiences (training). Therefore, a large amount of training data is an important prerequisite for providing a solution to the problem. A combination of unsupervised and restricted supervised acquisition of such data will be reported. Training is performed both on a subset of the content of the Gothenburg Lexical Database (GLDB), and on instances of large corpora annotated with coarse-grained semantic information. Testing is performed on corpora instances using a range of different algorithms and metrics. The application language is written Swedish.
We present an implementation of a chart-based head-corner parsing algorithm for lexicalized Tree Adjoining Grammars. We report on some practical experiments where we parse 2250 sentences from the Wall Street Journal using this parser. In these experiments the parser is run without any statistical pruning; it produces all valid parses for each sentence in the form of a shared derivation forest. The parser uses a large Treebank Grammar with 6789 tree templates with about 120# 000 lexicalized trees. The results suggest that the observed complexity of parsing for LTAG is dominated by factors other than sentence length. 1. Motivation The particular experiments that we report on in this paper were chosen to discover certain facts about LTAG parsing in a practical setting. Specifically, we wanted to discover the importance of the worst-case results for LTAG parsing in practice. Let us take Schabes' Earleystyle TAG parsing algorithm (Schabes, 1994) which is the usual candidate for a practica...
This volume contains the papers presented at the workshop on Recent Advances in Natural Language Processing and Information Retrieval, held on 8 October 2000 in conjunction with the 38 th Annual Meeting of the Association for Computational Linguistics (ACL).The aim of the workshop was to foster the interaction between researchers in the areas of Natural Language Processing (NLP) and Information Retrieval (IR), and furthermore, to promote discussion on the current and potential benefits of common approaches to related research challenges. In putting the workshop together, our goal was to bring these two communities together to establish opportunity for communication. We hope there will be similar workshops at IR related conferences so that a gradual closing of the existing gaps will occur. This workshop is not the first on the topic, but one which reflects what we believe are increasing trends as each field reaches its limits.The growing research and application possibilities provided by the increased amount of networked information have motivated new attempts to explore the relationship between NLP and IR. For researchers in IR, a compelling challenge is to move from (monolingual) document retrieval within controlled text collections, to actually retrieving information, rather than individual documents, from multilingual, heterogeneous and dynamic webs of interlinked documents and online services. The reciprocal challenge for NLP research is to scale up, adapt and possibly reshape techniques and resources to help bridge the gap between document and information retrieval in practical applications.The central topic of the workshop was the application of language technologies to information retrieval, including•the role of lexical-syntactic information in mono- and multilingual IR, including morphology, phrase detection and treatment, word sense disambiguation adapted to IR needs, acquisition and use of lexical resources, etc.•empirical evidence regarding the use of NL techniques in different retrieval scenarios, typification of such scenarios, and the discussion of evaluation measures beyond precision/recall variants.•interaction between NLP and IR techniques in topics related to both areas such as Cross-Language and Interactive Text Retrieval, Question Answering, Information Extraction, Text Summarization, Text Data Mining, etc.The original call for papers resulted in 25 submissions, from which 10 papers were selected on the basis of a thorough reviewing process. A majority of the papers contained in this volume study how to improve retrieval processes using syntactic and semantic information, including lexical expansions for web querying, semantic indexing, phrasal indexing in different languages, acquisition and use of lexical databases, etc. The remaining papers combine NL techniques from related areas - summarization, information extraction - to extend search capabilities and presentation of results, including summarization of search engine hit lists and summarization for text categorization, and a search interface that accepts template-like general constraints and is able to return specific information items such as locations, people or companies that satisfy user's constraints. Although none of these papers deal directly with cross-language issues (well covered in the Cross-Language Evaluation Forum held at Lisbon two weeks earlier), the monolingual systems presented here cover five different languages (English, Japanese, Korean, Italian and Czech).
Grammars are core elements of many NLP applications. Grammars can be developed in two ways: built by hand or extracted from corpora. In this paper, we compare a handcrafted grammar with a Treebank grammar. We contend that recognizing substructures of the grammars' basic units is necessary not only because it allows grammars to be compared at a higher level, but also because it provides the building blocks for consistent and efficient integration of the grammars.
Burnout was tested for in 754 mental health workers and related to self-image as assessed with Structural Analysis of Social Behavior (SASB, Benjamin 1974). A positive relation was found between burnout and negative self-image, and between the experience of personal accomplishment and positive self-image. Compared to self-image, gender, age and work setting did not explain any variance in burnout. Highly burned-out persons had a significantly more negative self-image than staff who had rated themselves as low burnout. Finally, the relation between self-image and burnout was studied in 210 subjects who had completed their self-image ratings one year before burnout was measured, with the same results: a negative self-image was related to higher burnout one year later. One general conclusion is that a tendency in staff to treat themselves in negative ways may function as a negative filter for coping with difficulties at work and thus be a risk factor for burnout.
This paper presents a method for the assignment of grammatical relation labels in a sentence structure. The method has been implemented in the software tool AGRA (Automatic Grammatical Relation Assigner), which is part of a project for the development of a treebank of Italian sentences, and a knowledge base of Italian subcategorization frames. The annotation schema implements a notion of underspecification, that arranges grammatical relations from generic to specific one onto a hierarchy; the software tool works with hand-coded rules, which apply heuristic knowledge (on syntactic and semantic cues) to distinguish between complements and modifiers. 1. Introduction Recent work in corpus-based linguistic analysis has pointed out the necessity of including predicateargument structures in treebank annotation schemata (Marcus et al. 1994) (Skut et al. 1997). This permits the collection of large data bases of subcategorization frames and their relative statistics, that are of valuable...
In this paper, a granular-neural-network-based Knowledge Discovery and Data Mining (KDDM) method based on granular computing, neural computing, fuzzy computing, linguistic computing and pattern recognition is presented. The major issues include (1) how to use neural networks to discover granular knowledge from numerical-linguistic databases, and (2) how to use discovered granular knowledge to predict missing data. A Granular Neural Network (GNN) is designed to deal with numerical-linguistic data fusion and granular knowledge discovery in numerical-linguistic databases. From a data granulation point of view, the GNN can process granular data in a database. From a data fusion point of view, the GNN makes decisions based on different kinds of granular data. From a KDDM point of view, the GNN is able to learn internal granular relations between numerical-linguistic inputs and outputs, and predict new relations in a database.
Pastiche is central to the resistant politics of Kathy Acker's writing--yet she would appear to agree with Fredric Jameson's influential critique of pastiche as "the wearing of a linguistic mask, speech in a dead language" (17). Her 1986 novel Don Quixote is all about having to speak "in a dead language" in the absence of a more "healthy" norm. It begins with the death of the protagonist, a female version of Cervantes's knight, who then goes on to narrate much of the subsequent story. Acker explains, "BEING DEAD, DON QUIXOTE COULD NO LONGER SPEAK. BEING BORN INTO AND PART OF A MALE WORLD, SHE HAD NO SPEECH OF HER OWN. ALL SHE COULD DO WAS READ MALE TEXTS WHICH WEREN'T HERS" (39). The novel then proceeds by plagiarism and pastiche, as Quixote goes on a quest--for a heterosexual love unsullied by patriarchal power relations--through fragments of numerous existing texts. Quixote rereads and pieces together a whole range of textual scraps, from Machiavelli's The Prince to a Godzilla movie. What becomes clear in her eccentric survey of (primarily) Western culture is that the lost, healthy linguistic norm is more than unhealthy for female readers--indeed, it is deadly.
The availability of semantically tagged corpora is becoming a very important and urgent need for training and evaluation within a large number of applications but also they are the natural application and accompaniment of semantic lexicons of which they constitute both a useful testbed to evaluate their adequacy and a repository of corpus examples for the attested senses. It is therefore essential that sound criteria are defined for their construction and a specific methodology is set up for the treatment of various semantic phenomena relevant to this level of description. In this paper we present some observations and results concerning an experiment of manual lexical-semantic tagging of a small Italian corpus performed within the framework of the ELSNET project. The ELSNET experimental project has to be considered as a feasibility study. It is part of a preparatory and training phase, started with the Romanseval/Senseval experiment (Calzolari et al., 1998), and ending up with the lexical-semantic annotation of larger quantities of semantically annotated texts such as the syntactic-semantic Treebank which is going to be annotated within an Italian National Project (SI-TAL). Indeed, the results of the ELSNET experiment have been of utmost importance for the definition of the technical guidelines for the lexical-semantic level of description of the Treebank.
The question of whether to adapt the language and style of opera librettos to current linguistic norms is proposed to be similar to the problem of whether to perform an opera in the original language or in translation. It is argued that any adjustment or modernization is inappropriate, and that original language and diction should be preserved. DvoÅák's tragic opera Vanda to a libretto by Václav BeneÅ¡-Å umavský and FrantiÅ¡ek Zákrejs is considered as an example.
1.1 Tagging criteria....................................... 4 1.2 POS tagset......................................... 5 1.3 Size of the POS tagset................................... 6
The accuracy of statistical parsing models can be improved with the use of lexical information. Statistical parsing using Lexicalized tree adjoining grammar (LTAG), a kind of lexicalized grammar, has remained relatively unexplored. We believe that is largely in part due to the absence of large corpora accurately bracketed in terms of a perspicuous yet broad coverage LTAG. Our work attempts to alleviate this difficulty. We extract different LTAGs from the Penn Treebank. We show that certain strategies yield an improved extracted LTAG in terms of compactness, broad coverage, and supertagging accuracy. Furthermore, we perform a preliminary investigation in smoothing these grammars by means of an external linguistic resource, namely, the tree families of an XTAG grammar, a hand built grammar of English.
This paper presents the first-ever results of applying statistical parsing models to the newly-available Chinese Treebank. We have employed two models, one extracted and adapted from BBN's SIFT System (Miller et al., 1998) and a TAG-based parsing model, adapted from (Chiang, 2000). On sentences with ≤40 words, the former model performs at 69% precision, 75% recall, and the latter at 77% precision and 78% recall.
REVIEWS Get access Christiane Fellbaum (ed.) WordNet: An Electronic Lexical Database. Cambridge, Mass.: MIT Press. 1998. xxii + 423 pages. ISBN 0-262-06197-X. $50. Geoffrey Sampson Geoffrey Sampson University of Sussex Search for other works by this author on: Oxford Academic Google Scholar International Journal of Lexicography, Volume 13, Issue 1, March 2000, Pages 54–59, https://doi.org/10.1093/ijl/13.1.54 Published: 01 March 2000
In this paper we introduce an example-based parser for Chinese. One strong point of the parsers is its high reliability. We propose a formal definition for reliability and derive from it K as a metric for the evaluation of parsers. In a row of experiments we try to identify some factors which support the reliability of the parser. It is suggested that these factors are independent of the parsing approach and can be realized in TAGs. 1. Introduction Example-based parsers adhere to the lazy learning algorithm while converting tree-bank entries into a parser. So-called treebank grammars, (Bod, 1992; Charniak, 1996) are eager learners, i.e. they abstract knowledge structures or statistical information from the treebank and reason on the basis of these abstractions. Explanation-based parsing is a different eager learning approach aiming at the extraction of specialized grammars out of a general-purpose grammars on the bases of parsing examples (Rayner & Christer, 1994; Srivinas & Joshi, 1...
This dissertation describes a natural language processing research in the field of nominal compounds in general and technical English. The starting point for the studies presented was INTEX, a tool for automatic treatment of large corpora.<br />While analyzing the problem of large coverage listing and describing of compounds, we addressed the following issues:<br />1) Which methods of compound description should be used?<br />2) For what kind of applications is this description useful?<br />The first issue is treated in the context of electronic lexical databases such as they are admitted in the INTEX system. We analyze the inflectional morphology of compounds in French, English and Polish. We propose a method of automatic generation of their inflected forms. We describe the construction of two electronic dictionaries: one for general English compounds, and the other for simple and compound terms of the computer science technical English. We also present a library of finite-state automata and transducers for the recognition of English cardinal and ordinal numerals.<br />The utility of large coverage compound dictionaries is verified through their application to two kinds of natural language processing tasks. First, we describe a method of acquisition of terms based on initial terminological resources. Secondly, we propose an automatic spelling checking algorithm of simple and compound words in a finite-state automaton dictionary.
It is generally recognized that the common nonterminal labels for syntactic constituents (NP, VP, etc.) do not exhaust the syntactic and semantic information one would like about parts of a syntactic tree. For example, the Penn Treebank gives each constituent zero or more &apos;function tags&apos; indicating semantic roles and other related information not easily encapsulated in the simple constituent labels. We present a statistical algorithm for assigning these function tags that, on text already parsed to a simplelabel level, achieves an F-measure of 87%, which rises to 99% when considering &apos;no tag&apos; as a valid choice.
In this paper, we propose a new ambiguity representation scheme; Structure Preference Relation (SPR), which consists of useful quantitative distribution information for ambiguous structures. Two automatic acquisition algorithms, the first acquired from a treebank, and the second acquired from raw texts, are introduced, and some experimental results which prove the availability of the algorithms are also given. Finally, we introduce some SPR applications in linguistics and natural language processing, such as preference-based parsing and the discovery of representative ambiguous structures, and propose some future research directions.
1.1 Notion of word....................................... 4 1.2 Tests of wordhood..................................... 5 1.3 Compatibility with other guidelines............................ 6
This research was designed to contribute to the development of new training systems to convey shape to the visually impaired. This dissertation consisted of two experiments which addressed the similarities and differences of visually impaired persons' and sighted persons' impressions of outlines of real objects perceived under auditory and touch display conditions, as well as tactile impressions of actual real objects, wood cutouts of those objects, tactor-pin diagrams of those objects, and raised-line drawings of those objects. Experiment 1 examined auditory and tactile perceptual equivalence, as well as sighted and visually impaired perceptual equivalence. Within each sight level group, Experiment 1 demonstrated a lack of equivalence for auditory and tactile perceptual structures. Experiment 1 demonstrated both similarities and differences in the perceptual structure comparisons between the sighted and the visually impaired. Experiment 2 examined the impact of sight level and four stimulus types on tactile percent correct identifications, response latencies, and familiarity ratings. Experiment 2 demonstrated sighted and visually impaired participants performed equally on a percent correct identification task. This Experiment also revealed the best performances were exhibited when real objects were presented, followed by wood cutouts, followed by tactor-pins, and performance with raised-line drawing (RLD) presentation was poorest. Experiment 2 also examined the exploratory procedures utilized during tactile identification of the four stimulus types. Experiment 2 revealed wood cutout presentation was associated with the largest percentage of different exploratory procedures being utilized, followed by real objects and tactor-pins which were equivalent, but utilized a larger percentage than the RLDs. Wood cutouts were the only other objects beside the real objects to use all exploratory procedures. The results of Experiment 1 and Experiment 2 indicate the utility of changing current industry standards for displaying shape information.
A BILINGUAL LEXICAL DATABASE FOR FRAME SEMANTICS Get access Thierry Fontenelle Thierry Fontenelle 19 Rue du Merschgrund (L-8373 Hobscheid, Luxembourg)University of Liège(B-4000 Liege, Belgium) (fontenel@pt_lu) Search for other works by this author on: Oxford Academic Google Scholar International Journal of Lexicography, Volume 13, Issue 4, December 2000, Pages 232–248, https://doi.org/10.1093/ijl/13.4.232 Published: 01 December 2000
This paper presents a novel methodology of disambiguating prepositional phrase attachments. We create patterns of attachments by classifying a collection of prepositional relations derived from Treebank parses. As a by-product, the arguments of every prepositional relation are semantically disambiguated. Attachment decisions are generated as the result of a learning process, that builds upon some of the most popular current statistical and machine learning techniques. We have tested this methodology on (1) Wall Street Journal articles, (2) textual definitions of concepts from a dictionary and (3) an ad hoc corpus of Web documents, used for conceptual indexing and information extraction.
I have been developing a computer program named RebLin. RebLin has special functions other than searching electronic dictionaries. In this paper, I will show how multi-functional RebLin expands the possibility of electronic dictionaries. First, I will compare RebLin with other computer programs which handle electronic dictionaries, analyzing how each of the software deal with inflected forms and derivatives. Then, I will explain how RebLin retrieves useful information out of other electronic resources such as those on the internet, digitized movies and a lexical database. Finally, I will analyze a log file which records words which users input in the search field of RebLin, and show how they make use of the various electronic resources which RebLin provides them with.
The popularity of applying machine learning methods to computational linguistics problems has produced a large supply of trainable natural language processing systems. Most problems of interest have an array of off-the-shelf products or downloadable code implementing solutions using various techniques. Where these solutions are developed independently, it is observed that their errors tend to be independently distributed. This thesis is concerned with approaches for capitalizing on this situation in a sample problem domain, Penn Treebank-style parsing. The machine learning community provides techniques for combining outputs of classifiers, but parser output is more structured and interdependent than classifications. To address this discrepancy, two novel strategies for combining parsers are used: learning to control a switch between parsers and constructing a hybrid parse from multiple parsers' outputs. Off-the-shelf parsers are not developed with an intention to perform well in a collaborative ensemble. Two techniques are presented for producing an ensemble of parsers that collaborate. All of the ensemble members are created using the same underlying parser induction algorithm, and the method for producing complementary parsers is only loosely constrained by that chosen algorithm.
An algorithm for analyzing ordinal scaling results is described. Frequency data on ordinal categories are modeled for unidimensional psychological attributes according to Thurstone’s judgment scaling model. The algorithm applies maximum likelihood estimation of model parameters. The Cramér-Rao bounds of the standard errors of the estimated parameters are calculated, and a stress measure and a goodness-of-fit measure are supplied.
The Translational English Corpus (TEC) held at the Centre for Translation Studies at UMIST is a full-text, synchronic, general, monolingual, written, single, translational corpus of English. It is also a direct, multi-source-language, mono-translation-mode (written mode), mono-translation-method (human translation), largely into-mother-tongue, professional, published corpus. At the time of writing TEC represents four text categories: newspapers, biography, fiction, and inflight magazines. Hatim (1999) has argued that so far in translation studies an important distinction has been ignored. This distinction is between what is "in" and what is "of" the text. "In" refers to the language itself, which can be ana-lyzed through text analysis, while "of" refers to the text in its entirety, its overall effect in terms of ideology. In this paper, I will argue that TEC can indeed be a valuable, self-contained, single resource for studying precisely the "of" of translational language, that is, its ideological impact in the target language and culture. To this purpose, I will discuss some methodological issues as well as the methods for carrying out critical linguistic analy-sis. I will also suggest ways of investigating norms of lexical use in TEC and their possible ideological implications through the lexico-grammatical and collocational analysis of a set of key words relating to Europe in translated newspaper articles.
QUAID (question-understanding aid) is a software tool that assists survey methodologists, social scientists, and designers of questionnaires in improving the wording, syntax, and semantics of questions. The tool identifies potential problems that respondents might have in comprehending the meaning of questions on questionnaires. These problems can be scrutinized by researchers when they revise questions to improve question comprehension and, thereby, enhance the reliability and validity of answers. QUAID was designed to identify nine classes of problems, but only five of these problems are addressed in this article: unfamiliar technical term, vague or imprecise relative term, vague or ambiguous noun phrase, complex syntax, and working memory overload. We compared the output of QUAID with ratings of language experts who evaluated a corpus of questions on the five classes of problems. The corpus consisted of 505 questions on 11 surveys developed by the U.S. Census Bureau. Analyses of hit rates, false alarm rates,d′ scores, recall scores, and precision scores revealed that QUAID was able to identify these five problems with questions, although improvements in QUAID’s performance are anticipated in future research and development.