A key challenge at the core of many Natural Language Processing (NLP) tasks is the ability to determine which conclusions can be inferred from a given natural language text. This problem, called the Recognition of Textual Entailment (RTE), has initiated the development of a range of algorithms, methods, and technologies. Unfortunately, research on Textual Entailment (TE), like semantics research more generally, is fragmented into studies focussing on various aspects of semantics such as world knowledge, lexical and syntactic relations, or more specialized kinds of inference. This fragmentation has problematic practical consequences. Notably, interoperability among the existing RTE systems is poor, and reuse of resources and algorithms is mostly infeasible. This also makes systematic evaluations very difficult to carry out. Finally, textual entailment presents a wide array of approaches to potential end users with little guidance on which to pick. Our contribution to this situation is the novel EXCITEMENT architecture, which was developed to enable and encourage the consolidation of methods and resources in the textual entailment area. It decomposes RTE into components with strongly typed interfaces. We specify (a) a modular linguistic analysis pipeline and (b) a decomposition of the ‘core’ RTE methods into top-level algorithms and subcomponents. We identify four major subcomponent types, including knowledge bases and alignment methods. The architecture was developed with a focus on generality, supporting all major approaches to RTE and encouraging language independence. We illustrate the feasibility of the architecture by constructing mappings of major existing systems onto the architecture. The practical implementation of this architecture forms the EXCITEMENT open platform. It is a suite of textual entailment algorithms and components which contains the three systems named above, including linguistic-analysis pipelines for three languages (English, German, and Italian), and comprises a number of linguistic resources. By addressing the problems outlined above, the platform provides a comprehensive and flexible basis for research and experimentation in textual entailment and is available as open source software under the GNU General Public License.

Graph structures naturally model connections. In natural language processing (NLP) connections are ubiquitous, on anything between small and web scale. We find them between words – as grammatical, collocation or semantic relations – contributing to the overall meaning, and maintaining the cohesive structure of the text and the discourse unity. We find them between concepts in ontologies or other knowledge repositories – since the early ages of artificial intelligence, associative or semantic networks have been proposed and used as knowledge stores, because they naturally capture the language units and relations between them, and allow for a variety of inference and reasoning processes, simulating some of the functionalities of the human mind. We find them between complete texts or web pages, and between entities in a social network, where they model relations at the web scale. Beyond the more often encountered ‘regular’ graphs, hypergraphs have also appeared in our field to model relations between more than two units.

Aliases play an important role in online environments by facilitating anonymity, but also can be used to hide the identity of cybercriminals. Previous studies have investigated this alias matching problem in an attempt to identify whether two aliases are shared by an author, which can assist with identifying users. Those studies create their training data by randomly splitting the documents associated with an alias into two sub-aliases. Models have been built that can regularly achieve over 90% accuracy for recovering the linkage between these ‘random sub-aliases’. In this paper, random sub-alias generation is shown to enable these high accuracies, and thus does not adequately model the real-world problem. In contrast, creating sub-aliases using topic-based splitting drastically reduces the accuracy of all authorship methods tested. We then present a methodology that can be performed on non-topic controlled datasets, to produce topic-based sub-aliases that are more difficult to match. Finally, we present an experimental comparison between many authorship methods to see which methods better match aliases under these conditions, finding that local n-gram methods perform better than others.

The Journal of Natural Language Engineering (JNLE) has enjoyed another very successful year. Two years after being accepted into Thomson Reuters Citation Index and being indexed in many of their products (including both the Science and the Social Science editions of the Journals Citation Rankings (JCR)), the journal further established itself as a leading forum for high-quality articles covering all aspects of Natural Language Processing research, including, but not limited to, the engineering of natural language methods and applications. I am delighted to report an increased number of submissions reaching a total of 92 between January–September 2014.

This paper describes the Kestrel text normalization system, a component of the Google text-to-speech synthesis (TTS) system. At the core of Kestrel are text-normalization grammars that are compiled into libraries of weighted finite-state transducers (WFSTs). While the use of WFSTs for text normalization is itself not new, Kestrel differs from previous systems in its separation of the initial tokenization and classification phase of analysis from verbalization. Input text is first tokenized and different tokens classified using WFSTs. As part of the classification, detected semiotic classes – expressions such as currency amounts, dates, times, measure phases, are parsed into protocol buffers (https://code.google.com/p/protobuf/). The protocol buffers are then verbalized, with possible reordering of the elements, again using WFSTs. This paper describes the architecture of Kestrel, the protocol buffer representations of semiotic classes, and presents some examples of grammars for various languages. We also discuss applications and deployments of Kestrel as part of the Google TTS system, which runs on both server and client side on multiple devices, and is used daily by millions of people in nineteen languages and counting.

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.

Graphs are a powerful representation formalism that can be applied to a variety of aspects related to language processing. We provide an overview of how Natural Language Processing problems have been projected into the graph framework, focusing in particular on graph construction – a crucial step in modeling the data to emphasize the phenomena targeted.

Paraphrase corpora are an essential but scarce resource in Natural Language Processing. In this paper, we present the Wikipedia-based Relational Paraphrase Acquisition (WRPA) method, which extracts relational paraphrases from Wikipedia, and the derived WRPA paraphrase corpus. The WRPA corpus currently covers person-related and authorship relations in English and Spanish, respectively, suggesting that, given adequate Wikipedia coverage, our method is independent of the language and the relation addressed. WRPA extracts entity pairs from structured information in Wikipedia applying distant learning and, based on the distributional hypothesis, uses them as anchor points for candidate paraphrase extraction from the free text in the body of Wikipedia articles. Focussing on relational paraphrasing and taking advantage of Wikipedia-structured information allows for an automatic and consistent evaluation of the results. The WRPA corpus characteristics distinguish it from other types of corpora that rely on string similarity or transformation operations. WRPA relies on distributional similarity and is the result of the free use of language outside any reformulation framework. Validation results show a high precision for the corpus.

Machine learning techniques have been implemented to extract instances of semantic relations using diverse features based on linguistic knowledge, such as tokens, lemmas, PoS-tags, or dependency paths. However, there has been little work aiming to know which of these features works better in the relation extraction task, and less in languages other than English. In this paper, various features representing different levels of linguistic knowledge are systematically evaluated for biographical relation extraction. The effectiveness of these features was measured by training several supervised classifiers that only differ in the type of linguistic knowledge used to define their features. The experiments performed in this paper show that some basic linguistic knowledge (provided by lemmas and their combination in bigrams) behaves better than other complex features, such as those based on syntactic analysis. Furthermore, some feature combinations using different levels of analysis are proposed in order (i) to avoid feature overlapping as well as (ii) to evaluate the use of computationally inexpensive and widespread tools such as tokenization and lemmatization. This paper also describes two new freely available corpora for biographical relation extraction in Portuguese and Spanish, built by means of a distant-supervision strategy. Experiments were performed with five semantic relations and two languages, using these corpora.

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.

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.

We address the problem of unsupervised and semi-supervised SMS (Short Message Service) text message SPAM detection. We develop a content-based Bayesian classification approach which is a modest extension of the technique discussed by Resnik and Hardisty in 2010. The approach assumes that the bodies of the SMS messages arise from a probabilistic generative model and estimates the model parameters by Gibbs sampling using an unlabeled, or partially labeled, SMS training message corpus. The approach classifies new SMS messages as SPAM or HAM (non-SPAM) by zero-thresholding their logit estimates. We tested the approach on a publicly available SMS corpora collected from the UK. Used in semi-supervised fashion, the approach clearly outperformed a competing algorithm, Semi-Boost. Used in unsupervised fashion, the approach outperformed a fully supervised classifier, an SVM (Support Vector Machine), when the number of training messages used by the SVM was small and performed comparably otherwise. We believe the approach works well and is a useful tool for SMS SPAM detection.

In this work, we present a novel type of graphs for natural language processing (NLP), namely textual entailment graphs (TEGs). We describe the complete methodology we developed for the construction of such graphs and provide some baselines for this task by evaluating relevant state-of-the-art technology. We situate our research in the context of text exploration, since it was motivated by joint work with industrial partners in the text analytics area. Accordingly, we present our motivating scenario and the first gold-standard dataset of TEGs. However, while our own motivation and the dataset focus on the text exploration setting, we suggest that TEGs can have different usages and suggest that automatic creation of such graphs is an interesting task for the community.

Most statistical machine translation systems typically rely on word alignments to extract translation rules. This approach would suffer from a practical problem that even one spurious word alignment link can prevent some desirable translation rules from being extracted. To address this issue, this paper presents two approaches, referred to as sub-tree alignment and phrase-based forced decoding methods, to automatically learn translation span alignments from parallel data. Then, we improve the translation rule extraction by deleting spurious links and inserting new links based on bilingual translation span correspondences. Some comparison experiments are designed to demonstrate the effectiveness of the proposed approaches.

Natural Language Generation systems in interactive settings often face a multitude of choices, given that the communicative effect of each utterance they generate depends crucially on the interplay between its physical circumstances, addressee and interaction history. This is particularly true in interactive and situated settings. In this paper we present a novel approach for situated Natural Language Generation in dialogue that is based on hierarchical reinforcement learning and learns the best utterance for a context by optimisation through trial and error. The model is trained from human–human corpus data and learns particularly to balance the trade-off between efficiency and detail in giving instructions: the user needs to be given sufficient information to execute their task, but without exceeding their cognitive load. We present results from simulation and a task-based human evaluation study comparing two different versions of hierarchical reinforcement learning: One operates using a hierarchy of policies with a large state space and local knowledge, and the other additionally shares knowledge across generation subtasks to enhance performance. Results show that sharing knowledge across subtasks achieves better performance than learning in isolation, leading to smoother and more successful interactions that are better perceived by human users.

Inference in natural language often involves recognizing lexical entailment (RLE), that is, identifying whether one word entails another. For example, buy entails own. Two general strategies for RLE have been proposed: One strategy is to manually construct an asymmetric similarity measure for context vectors (directional similarity) and another is to treat RLE as a problem of learning to recognize semantic relations using supervised machine-learning techniques (relation classification). In this paper, we experiment with two recent state-of-the-art representatives of the two general strategies. The first approach is an asymmetric similarity measure (an instance of the directional similarity strategy), designed to capture the degree to which the contexts of a word, a, form a subset of the contexts of another word, b. The second approach (an instance of the relation classification strategy) represents a word pair, a: b, with a feature vector that is the concatenation of the context vectors of a and b, and then applies supervised learning to a training set of labeled feature vectors. In addition, we introduce a third approach that is a new instance of the relation classification strategy. The third approach represents a word pair, a: b, with a feature vector in which the features are the differences in the similarities of a and b to a set of reference words. All three approaches use vector space models of semantics, based on word–context matrices. We perform an extensive evaluation of the three approaches using three different datasets. The proposed new approach (similarity differences) performs significantly better than the other two approaches on some datasets and there is no dataset for which it is significantly worse. Along the way, we address some of the concerns raised in past research, regarding the treatment of RLE as a problem of semantic relation classification, and we suggest, it is beneficial to make connections between the research in lexical entailment and the research in semantic relation classification.

The emergence of knowledge repositories in a variety of domains provides a valuable opportunity for semantic interpretation of high dimensional datasets. Previous researches investigate the use of concept instead of word as a core semantic feature for incorporating semantic knowledge from an ontology into the representation model of documents. On the other hand, in machine learning and information retrieval, data objects are represented as a flat feature vector. The inconsistency between the structural nature of the knowledge repositories and the flat representation of features in machine learning leads researchers to neglect the structure of the knowledge base and leverage concepts as isolated semantic features, which is known as bag-of-concepts. Although, using concepts has some advantages over words, by neglecting the relation between concepts, the problem of vocabulary mismatch remains in force. In this paper, a novel semantic kernel is proposed which is capable of incorporating the relatedness between conceptual features. This kernel leverages clique theory to map data objects to a novel feature space wherein complex data objects will be comparable. The proposed kernel is relevant to all applications which have a prior knowledge about the relatedness between features. We concentrate on representing text documents and words using Wikipedia and WordNet, respectively. The experimental results over a set of benchmark datasets have revealed that the proposed kernel significantly improves the representation of both words and texts in the application of semantic relatedness.

In this paper, we study the problem of structural analysis of Web documents aiming at extracting the sectional hierarchy of a document. In general, a document can be represented as a hierarchy of sections and subsections with corresponding headings and subheadings. We developed two machine learning models: heading extraction model and hierarchy extraction model. Heading extraction was formulated as a classification problem whereas a tree-based learning approach was employed in hierarchy extraction. For this purpose, we developed an incremental learning algorithm based on support vector machines and perceptrons. The models were evaluated in detail with respect to the performance of the heading and hierarchy extraction tasks. For comparison, a baseline rule-based approach was used that relies on heuristics and HTML document object model tree processing. The machine learning approach, which is a fully automatic approach, outperformed the rule-based approach. We also analyzed the effect of document structuring on automatic summarization in the context of Web search. The results of the task-based evaluation on TREC queries showed that structured summaries are superior to unstructured summaries both in terms of accuracy and user ratings, and enable the users to determine the relevancy of search results more accurately than search engine snippets.

We present a methodology for the extraction of narrative information from a large corpus. The key idea is to transform the corpus into a network, formed by linking the key actors and objects of the narration, and then to analyse this network to extract information about their relations. By representing information into a single network it is possible to infer relations between these entities, including when they have never been mentioned together. We discuss various types of information that can be extracted by our method, various ways to validate the information extracted and two different application scenarios. Our methodology is very scalable, and addresses specific research needs in social sciences.

An open problem in natural language processing is word sense disambiguation (WSD). A word may have several meanings, but WSD is the task of selecting the correct sense of a polysemous word based on its context. Proposed solutions are based on supervised and unsupervised learning methods. The majority of researchers in the area focused on choosing proper size of ‘n’ in n-gram that is used for WSD problem. In this research, the concept has been taken to a new level by using variable ‘n’ and variable size window. The concept is based on the iterative patterns extracted from the text. We show that this type of sequential pattern is more effective than many other solutions for WSD. Using regular data mining algorithms on the extracted features, we significantly outperformed most monolingual WSD solutions. The state-of-the-art results were obtained using external knowledge like various translations of the same sentence. Our method improved the accuracy of the multilingual system more than 4 percent, although we were using monolingual features.