Entailment recognition is a primary generic task in natural language inference, whose focus is to detect whether the meaning of one expression can be inferred from the meaning of the other. Accordingly, many NLP applications would benefit from high coverage knowledgebases of paraphrases and entailment rules. To this end, learning such knowledgebases from the Web is especially appealing due to its huge size as well as its highly heterogeneous content, allowing for a more scalable rule extraction of various domains. However, the scalability of state-of-the-art entailment rule acquisition approaches from the Web is still limited. We present a fully unsupervised learning algorithm for Web-based extraction of entailment relations. We focus on increased scalability and generality with respect to prior work, with the potential of a large-scale Web-based knowledgebase. Our algorithm takes as its input a lexical–syntactic template and searches the Web for syntactic templates that participate in an entailment relation with the input template. Experiments show promising results, achieving performance similar to a state-of-the-art unsupervised algorithm, operating over an offline corpus, but with the benefit of learning rules for different domains with no additional effort.

We investigate language-agnostic algorithms for the construction of unsupervised distributional semantic models using web-harvested corpora. Specifically, a corpus is created from web document snippets, and the relevant semantic similarity statistics are encoded in a semantic network. We propose the notion of semantic neighborhoods that are defined using co-occurrence or context similarity features. Three neighborhood-based similarity metrics are proposed, motivated by the hypotheses of attributional and maximum sense similarity. The proposed metrics are evaluated against human similarity ratings achieving state-of-the-art results.

The language model is one of the most important knowledge sources for statistical machine translation. In this article, we present two extensions to standard n-gram language models in statistical machine translation: a backward language model that augments the conventional forward language model, and a mutual information trigger model which captures long-distance dependencies that go beyond the scope of standard n-gram language models. We introduce algorithms to integrate the two proposed models into two kinds of state-of-the-art phrase-based decoders. Our experimental results on Chinese/Spanish/Vietnamese-to-English show that both models are able to significantly improve translation quality in terms of BLEU and METEOR over a competitive baseline.

Shift-reduce parsing has been studied extensively for diverse grammars due to the simplicity and running efficiency. However, in the field of constituency parsing, shift-reduce parsers lag behind state-of-the-art parsers. In this paper we propose a semi-supervised approach for advancing shift-reduce constituency parsing. First, we apply the uptraining approach (Petrov, S. et al. 2010. In Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing (EMNLP), Cambridge, MA, USA, pp. 705–713) to improve part-of-speech taggers to provide better part-of-speech tags to subsequent shift-reduce parsers. Second, we enhance shift-reduce parsing models with novel features that are defined on lexical dependency information. Both stages depend on the use of large-scale unlabeled data. Experimental results show that the approach achieves overall improvements of 1.5 percent and 2.1 percent on English and Chinese data respectively. Moreover, the final parsing accuracies reach 90.9 percent and 82.2 percent respectively, which are comparable with the accuracy of state-of-the-art parsers.

This paper presents a study on the interpretation and bracketing of noun compounds (‘NCs’) based on lexical semantics. Our primary goal is to develop a method to automatically interpret NCs through the use of semantic relations. Our NC interpretation method is based on lexical similarity with tagged NCs, based on lexical similarity measures derived from WordNet. We apply the interpretation method to both two- and three-term NC interpretation based on semantic roles. Finally, we demonstrate that our NC interpretation method can boost the coverage and accuracy of NC bracketing.

We discuss the problem of interpreting noun compounds such as colon cancer tumor suppressor protein, which pose major challenges for the automatic interpretation of English written text. We present an overview of the more general process of compounding and of noun compounds in particular, as well as of their syntax and semantics from both theoretical and computational linguistics viewpoint with an emphasis on the latter. Our main focus is on computational approaches to the syntax and semantics of noun compounds: we describe the problems, present the challenges, and discuss the most important lines of research. We also show how understanding noun compound syntax and semantics could help solve textual entailment problems, which would be potentially useful for a number of NLP applications, and which we believe to be an important direction for future research.

Many English noun pairs suggest an almost limitless array of semantic interpretation. A fruit bowl might be described as a bowl for fruit, a bowl that contains fruit, a bowl for holding fruit, or even (perhaps in a modern sculpture class), a bowl made out of fruit. These interpretations vary in syntax, semantic denotation, plausibility, and level of semantic detail. For example, a headache pill is usually a pill for preventing headaches, but might, perhaps in the context of a list of side effects, be a pill that can cause headaches (Levi, J. N. 1978. The Syntax and Semantics of Complex Nominals. New York: Academic Press.). In addition to lexical ambiguity, both relational ambiguity and relational vagueness make automatic semantic interpretation of these combinations difficult. While humans parse these possibilities with ease, computational systems are only recently gaining the ability to deal with the complexity of lexical expressions of semantic relations. In this paper, we describe techniques for paraphrasing the semantic relations that can hold between nouns in a noun compound, using a semi-supervised probabilistic method to rank candidate paraphrases of semantic relations, and describing a new method for selecting plausible relational paraphrases at arbitrary levels of semantic specification. These methods are motivated by the observation that existing semantic relation classification schemes often exhibit a highly skewed class distribution, and that lexical paraphrases of semantic relations vary widely in semantic precision.

The noun compound – a sequence of nouns which functions as a single noun – is very common in English texts. No language processing system should ignore expressions like steel soup pot cover if it wants to be serious about such high-end applications of computational linguistics as question answering, information extraction, text summarization, machine translation – the list goes on. Processing noun compounds, however, is far from trouble-free. For one thing, they can be bracketed in various ways: is it steel soup, steel pot, or steel cover? Then there are relations inside a compound, annoyingly not signalled by any words: does potcontainsoup or is it for cookingsoup? These and many other research challenges are the subject of this special issue.

Nominations are now open for the 2013 Annual Karen Spärck Jones Award – awarded to outstanding researchers in Natural Language Processing and Information Retrieval who have been awarded their PhD in the past ten years. The panel especially welcomes nominations for researchers who have a significant experimental component in their work.

This paper presents a classification-based approach to noun–noun compound interpretation within the statistical learning framework of kernel methods. In this framework, the primary modelling task is to define measures of similarity between data items, formalised as kernel functions. We consider the different sources of information that are useful for understanding compounds and proceed to define kernels that compute similarity between compounds in terms of these sources. In particular, these kernels implement intuitive notions of lexical and relational similarity and can be computed using distributional information extracted from text corpora. We report performance on classification experiments with three semantic relation inventories at different levels of granularity, demonstrating in each case that combining lexical and relational information sources is beneficial and gives better performance than either source taken alone. The data used in our experiments are taken from general English text, but our methods are also applicable to other domains and potentially to other languages where noun–noun compounding is frequent and productive.

In recent studies it has been shown that syntax-based semantic space models outperform models in which the context is represented as a bag-of-words in several semantic analysis tasks. This has been generally attributed to the fact that syntax-based models employ corpora that are syntactically annotated by a parser and a computational grammar. However, if the corpora processed contain words which are unknown to the parser and the grammar, a syntax-based model may lose its advantage since the syntactic properties of such words are unavailable. On the other hand, bag-of-words models do not face this issue since they operate on raw, non-annotated corpora and are thus more robust. In this paper, we compare the performance of syntax-based and bag-of-words models when applied to the task of learning the semantics of unknown words. In our experiments, unknown words are considered the words which are not known to the Alpino parser and grammar of Dutch. In our study, the semantics of an unknown word is defined by finding its most similar word in cornetto, a Dutch lexico-semantic hierarchy. We show that for unknown words the syntax-based model performs worse than the bag-of-words approach. Furthermore, we show that if we first learn the syntactic properties of unknown words by an appropriate lexical acquisition method, then in fact the syntax-based model does outperform the bag-of-words approach. The conclusion we draw is that, for words unknown to a given grammar, a bag-of-words model is more robust than a syntax-based model. However, the combination of lexical acquisition and syntax-based semantic models is best suited for learning the semantics of unknown words.

This paper introduces a model for capturing the meaning of negated statements by identifying the negated concepts and revealing the implicit positive meanings. A negated sentence may be represented logically in different ways depending on what is the scope and focus of negation. The novel approach introduced here identifies the focus of negation and thus eliminates erroneous interpretations. Furthermore, negation is incorporated into a framework for composing semantic relations, proposed previously, yielding a richer semantic representation of text, including hidden inferences. Annotations of negation focus were performed over PropBank, and learning features were identified. The experimental results show that the models introduced here obtain a weighted f-measure of 0.641 for predicting the focus of negation and 78 percent accuracy for incorporating negation into composition of semantic relations.

This paper addresses the task of automatic extraction of definitions by thoroughly exploring an approach that solely relies on machine learning techniques, and by focusing on the issue of the imbalance of relevant datasets. We obtained a breakthrough in terms of the automatic extraction of definitions, by extensively and systematically experimenting with different sampling techniques and their combination, as well as a range of different types of classifiers. Performance consistently scored in the range of 0.95–0.99 of area under the receiver operating characteristics, with a notorious improvement between 17 and 22 percentage points regarding the baseline of 0.73–0.77, for datasets with different rates of imbalance. Thus, the present paper also represents a contribution to the seminal work in natural language processing that points toward the importance of exploring the research path of applying sampling techniques to mitigate the bias induced by highly imbalanced datasets, and thus greatly improving the performance of a large range of tools that rely on them.

We consider a dependency-parsed text corpus as an instance of a labeled directed graph, where nodes represent words and weighted directed edges represent the syntactic relations between them. We show that graph walks, combined with existing techniques of supervised learning that model local and global information about the graph walk process, can be used to derive a task-specific word similarity measure in this graph. We also propose and evaluate a new learning method in this framework, a path-constrained graph walk variant, in which the walk process is guided by high-level knowledge about meaningful edge sequences (paths) in the graph. Empirical evaluation on the tasks of named entity coordinate term extraction and general word synonym extraction show that this framework is preferable to, or competitive with, vector-based models when learning is applied, and using small to moderate size text corpora.