Traditionally, vector-based semantic space models use word co-occurrence counts from large corpora to represent lexical meaning. In this article we present a novel framework for constructing semantic spaces that take syntactic relations into account. We introduce a formalization for this class of models which allows linguistic knowledge to guide the construction process. We evaluate our framework on a range of tasks relevant for cognitive science and natural language processing: semantic priming, synonymy detection and word sense disambiguation. In all cases, our framework obtains results that are comparable or superior to the state of the art. 1.

We present a novel approach to the automatic acquisition of taxonomic relations. The main difference to earlier approaches is that we do not only consider one single source of evidence, i.e. a specific algorithm or approach, but examine the possibility of learning taxonomic relations by considering various and heterogeneous forms of evidence. In particular, we derive these different evidences by using well-known NLP techniques and resources and combine them via two simple strategies. Our approach shows very promising results compared to other results from the literature. The main aim of the work presented in this paper is (i) to gain insight into the behaviour of different approaches to learn taxonomic relations, (ii) to provide a first step towards combining these different approaches, and (iii) to establish a baseline for further research.

A collocation is a habitual word combination. Collocational knowledge is essential for many tasks in natural language processing. We present a method for extracting collocations from text corpora. By comparison with the SUSANNE corpus, we show that both high precision and broad coverage can be achieved with our method. Finally, we describe an application of the automatically extracted collocations for computing word similarities.

This paper proposes a framework for representing the meaning of phrases and sentences in vector space. Central to our approach is vector composition which we operationalize in terms of additive and multiplicative functions. Under this framework, we introduce a wide range of composition models which we evaluate empirically on a sentence similarity task. Experimental results demonstrate that the multiplicative models are superior to the additive alternatives when compared against human judgments.

this paper is similar to the unification procedure in TELEGRAM (Appelt 1983), which employs a unification gram- mar

There have been many proposals to compute similarities between words based on their distributions in contexts. However, these approaches do not distinguish between synonyms and antonyms. We present two methods for identifying synonyms among distributionally similar words. 1

. In this paper, we describe the Machine Learning system, asium 1 , which learns Subcaterorization Frames of verbs and ontologies from the syntactic parsing of technical texts in natural language. The restrictions of selection in the subcategorization frames are filled by the ontology's concepts. Applications requiring such knowledge are crucial and numerous. The most direct applications are semantic control of texts and syntactic parsing disambiguation. This knowledge acquisition task cannot be fully automatically performed. Instead,we propose a cooperative ML method which provides the user with a global view of the acquisition task and also with acquisition tools like automatic concepts splitting, example generation, and an ontology view with attachments to the verbs. Validation steps using these features are intertwined with learning steps so that the user validates the concepts as they are learned. Experiments performed on two different corpora (cooking domain and patents) give ...

This paper describes a semi-automated procedure for collecting the co-occurrence patterns from a sample of texts in a domain, and then using these patterns as the basis for selectional constraints in analyzing further texts. We discuss some of the difficulties in automating the collection process, and describe two experiments that measure the completeness of these patterns and their effectiveness compared with manually-prepared patterns. We then describe and evaluate a procedure for selectional constraint relaxation, intended to compensate for gaps in the set of patterns. Finally, we suggest how these procedures could be combined with a system that queries a domain expert, in order to produce a more efficient discovery procedure

Techniques that exploit knowledge of distributional similarity between words have been proposed in many areas of Natural Language Processing. For example, in language modeling, the sparse data problem can be alleviated by estimating the probabilities of unseen co-occurrences of events from the probabilities of seen co-occurrences of similar events. In other applications, distributional similarity is taken to be an approximation to semantic similarity. However, due to the wide range of potential applications and the lack of a strict definition of the concept of distributional similarity, many methods of calculating distributional similarity have been proposed or adopted. In this work, a flexible, parameterized framework for calculating distributional similarity is proposed. Within this framework, the problem of finding distributionally similar words is cast as one of co-occurrence retrieval (CR) for which precision and recall can be measured by analogy with the way they are measured in document retrieval. As will be shown, a number of popular existing measures of distributional similarity are simulated with parameter settings within the CR framework. In this article, the CR framework is then used to systematically investigate three fundamental questions concerning distributional similarity. First, is the relationship of lexical similarity necessarily symmetric, or are there advantages to be gained from considering it as an asymmetric relationship? Second, are some co-occurrences inherently more salient than others in the calculation of distributional similarity? Third, is it necessary to consider the difference in the extent to which each word occurs in each co-occurrence type? Two application-based tasks are used for evaluation: automatic thesaurus generation and pseudo-disambiguation. It is possible to achieve significantly better results on both these tasks by varying the parameters within the CR framework rather than using other existing distributional similarity measures; it will also be shown that any single unparameterized measure is unlikely to be able to do better on both tasks. This is due to an inherent asymmetry in lexical substitutability and therefore also in lexical distributional similarity. 1.

This work investigates the variation in a word's distributionally nearest neighbours with respect to the similarity measure used. We identify one type of variation as being the relative frequency of the neighbour words with respect to the frequency of the target word. We then demonstrate a three-way connection between relative frequency of similar words, a concept of distributional gnerality and the semantic relation of hyponymy. Finally, we consider the impact that this has on one application of distributional similarity methods (judging the compositionality of collocations).