The goal of identifying textual entailment – whether one piece of text can be plausibly inferred from another – has emerged in recent years as a generic core problem in natural language understanding. Work in this area has been largely driven by the PASCAL Recognizing Textual Entailment (RTE) challenges, which are a series of annual competitive meetings. The current work exhibits strong ties to some earlier lines of research, particularly automatic acquisition of paraphrases and lexical semantic relationships and unsupervised inference in applications such as question answering, information extraction and summarization. It has also opened the way to newer lines of research on more involved inference methods, on knowledge representations needed to support this natural language understanding challenge and on the use of learning methods in this context. RTE has fostered an active and growing community of researchers focused on the problem of applied entailment. This special issue of the JNLE provides an opportunity to showcase some of the most important work in this emerging area.

Richly annotated dialogue corpora are essential for new research directions in statistical learning approaches to dialogue management, context-sensitive interpretation, and context-sensitive speech recognition. In particular, large dialogue corpora annotated with contextual information and speech acts are urgently required. We explore how existing dialogue corpora (usually consisting of utterance transcriptions) can be automatically processed to yield new corpora where dialogue context and speech acts are accurately represented. We present a conceptual and computational framework for generating such corpora. As an example, we present and evaluate an automatic annotation system which builds ‘Information State Update’ (ISU) representations of dialogue context for the Communicator (2000 and 2001) corpora of human–machine dialogues (2,331 dialogues). The purposes of this annotation are to generate corpora for reinforcement learning of dialogue policies, for building user simulations, for evaluating different dialogue strategies against a baseline, and for training models for context-dependent interpretation and speech recognition. The automatic annotation system parses system and user utterances into speech acts and builds up sequences of dialogue context representations using an ISU dialogue manager. We present the architecture of the automatic annotation system and a detailed example to illustrate how the system components interact to produce the annotations. We also evaluate the annotations, with respect to the task completion metrics of the original corpus and in comparison to hand-annotated data and annotations produced by a baseline automatic system. The automatic annotations perform well and largely outperform the baseline automatic annotations in all measures. The resulting annotated corpus has been used to train high-quality user simulations and to learn successful dialogue strategies. The final corpus will be made publicly available.

Having located a misspelling, a spellchecker generally offers some suggestions for the intended word. Even without using context, a spellchecker can draw on various types of information in ordering its suggestions. A series of experiments is described, beginning with a basic corrector that implements a well-known algorithm for reversing single simple errors, and making successive enhancements to take account of substring matches, pronunciation, known error patterns, syllable structure and word frequency. The improvement in the ordering produced by each enhancement is measured on a large corpus of misspellings. The final version is tested on other corpora against a widely used commercial spellchecker and a research prototype.

Policy learning is an active topic in dialogue systems research, but it has not been explored in relation to interactive question answering (IQA). We take a first step in learning adaptive interaction policies for question answering : we address the question of how to acquire enough reliable query constraints, how many database results to present to the user and when to present them, given the competing trade-offs between the length of the answer list, the length of the interaction, the type of database and the noise in the communication channel. The operating conditions are reflected in an objective function which we use to derive a hand-coded threshold-based policy and rewards to train a reinforcement learning policy. The same objective function is used for evaluation. We show that we can learn strategies for this complex trade-off problem which perform significantly better than a variety of hand-coded policies, for a wide range of noise conditions, user types, types of DB and turn-penalties. Our policy learning framework thus covers a wide spectrum of operating conditions. The learned policies produce an average relative increase in reward of 86.78% over the hand-coded policies. In 93% of the cases the learned policies perform significantly better than the hand-coded ones (p < .001). Furthermore we show that the type of database has a significant effect on learning and we give qualitative descriptions of the learned IQA policies.

We introduce a system for textual entailment that is based on a probabilistic model of entailment. The model is defined using a calculus of transformations on dependency trees, which is characterized by the fact that derivations in that calculus preserve the truth only with a certain probability. The calculus is successfully evaluated on the datasets of the PASCAL Challenge on Recognizing Textual Entailment.

We describe a system that automatically learns effective and engaging dialogue strategies, generated from a library of dialogue content, using reinforcement learning from user feedback. Besides the more usual clarification and verification components of dialogue, this library contains various social elements like greetings, apologies, small talk, relational questions and jokes. We tested the method through an experimental dialogue system that encourages take-up of exercise and shows that the learned dialogue policy performs as well as one built by human experts for this system.

Human-generated summaries are a blend of content and style, bound by the task restrictions, but are ‘subject to subjectiveness’ of the individuals summarising the documents. We study the impact of various facets that cause subjectivity such as brevity, information content and information coverage on human-authored summaries. The scale of subjectivity is quantitatively measured among various summaries using a question–answer-based cross-comprehension test. The test evaluates summaries for meaning rather than exact words based on questions, framed by the summary authors, derived from the summary. The number of questions that cannot be answered after reading the candidate summary reflects its subjectivity. The qualitative analysis of the outcome of the cross-comprehension test shows the relationship between the length of a summary, information content and nature of questions framed by the summary author.

Evaluating interactive question answering (QA) systems with real users can be challenging because traditional evaluation measures based on the relevance of items returned are difficult to employ since relevance judgments can be unstable in multi-user evaluations. The work reported in this paper evaluates, in distinguishing among a set of interactive QA systems, the effectiveness of three questionnaires: a Cognitive Workload Questionnaire (NASA TLX), and Task and System Questionnaires customized to a specific interactive QA application. These Questionnaires were evaluated with four systems, seven analysts, and eight scenarios during a 2-week workshop. Overall, results demonstrate that all three Questionnaires are effective at distinguishing among systems, with the Task Questionnaire being the most sensitive. Results also provide initial support for the validity and reliability of the Questionnaires.

In this introduction, we present our overview of interactive question answering (IQA). We contextualize IQA in the wider field of question answering, and establish connections to research in Information Retrieval and Dialogue Systems. We highlight the development of QA as a field, and identify challenges in the present research paradigm for which IQA is a potential solution. Finally, we present an overview of papers in this special issue, drawing connections between these and the challenges they address.

This article studies the issue of argument realization by preposition structures. By examining the preposition structures that are marked as frame elements in FrameNet, the article attempts to give corpus-based attestations to the hypothesized link between deep semantic arguments and their surface syntactic representations. Problems addressed in this article include how argument realization by preposition structures can be predictable from the target lexical unit and the frame it evokes, and why some noncentral prepositions get selected in the argument realization options. The investigation is primarily inspired by Fillmore's work in frame semantics. The source data for this study is derived from a preposition knowledge base that we have recently built by extracting all the semantically annotated preposition structures in FrameNet. The analysis shows that while there are various semantic–syntactic mapping possibilities, for most semantic arguments, the tendency of using central prepositions in their realization expressions is very strong. This is a clear indication that some preposition structures are linked to certain semantic arguments more than they are to others. A similar experiment was conducted using the annotated PropBank corpus to corroborate the supporting evidence found in FrameNet. The results of this study, together with the syntactic–semantic mapping lists of preposition structures can provide raw linguistic data for the study of preposition semantics, lexicography, argument realization, word sense disambiguation, and natural language understanding.

An important problem in knowledge discovery from text is the automatic extraction of semantic relations. This paper addresses the automatic classification of the semantic relations expressed by English genitives. A learning model is introduced based on the statistical analysis of the distribution of genitives' semantic relations in a corpus. The semantic and contextual features of the genitive's noun phrase constituents play a key role in the identification of the semantic relation. The algorithm was trained and tested on a corpus of approximately 20,000 sentences and achieved an f-measure of 79.80 per cent for of-genitives, far better than the 40.60 per cent obtained using a Decision Trees algorithm, the 50.55 per cent obtained using a Naive Bayes algorithm, or the 72.13 per cent obtained using a Support Vector Machines algorithm on the same corpus using the same features. The results were similar for s-genitives: 78.45 per cent using Semantic Scattering, 47.00 per cent using Decision Trees, 43.70 per cent using Naive Bayes, and 70.32 per cent using a Support Vector Machines algorithm. The results demonstrate the importance of word sense disambiguation and semantic generalization/specialization for this task. They also demonstrate that different patterns (in our case the two types of genitive constructions) encode different semantic information and should be treated differently in the sense that different models should be built for different patterns.

This paper describes a new method for recognizing whether a student's response to an automated tutor's question entails that they understand the concepts being taught. We demonstrate the need for a finer-grained analysis of answers than is supported by current tutoring systems or entailment databases and describe a new representation for reference answers that addresses these issues, breaking them into detailed facets and annotating their entailment relationships to the student's answer more precisely. Human annotation at this detailed level still results in substantial interannotator agreement (86.2%), with a kappa statistic of 0.728. We also present our current efforts to automatically assess student answers, which involves training machine learning classifiers on features extracted from dependency parses of the reference answer and student's response and features derived from domain-independent lexical statistics. Our system's performance, as high as 75.5% accuracy within domain and 68.8% out of domain, is very encouraging and confirms the approach is feasible. Another significant contribution of this work is that it represents a significant step in the direction of providing domain-independent semantic assessment of answers. No prior work in the area of tutoring or educational assessment has attempted to build such domain-independent systems. They have virtually all required hundreds of examples of learner answers for each new question in order to train aspects of their systems or to hand-craft information extraction templates.

Paraphrase patterns are semantically equivalent patterns, which are useful in both paraphrase recognition and generation. This paper presents a pivot approach for extracting paraphrase patterns from bilingual parallel corpora, whereby the paraphrase patterns in English are extracted using the patterns in another language as pivots. We make use of log-linear models for computing the paraphrase likelihood between pattern pairs and exploit feature functions based on maximum likelihood estimation (MLE), lexical weighting (LW), and monolingual word alignment (MWA). Using the presented method, we extract more than 1 million pairs of paraphrase patterns from about 2 million pairs of bilingual parallel sentences. The precision of the extracted paraphrase patterns is above 78%. Experimental results show that the presented method significantly outperforms a well-known method called discovery of inference rules from text (DIRT). Additionally, the log-linear model with the proposed feature functions are effective. The extracted paraphrase patterns are fully analyzed. Especially, we found that the extracted paraphrase patterns can be classified into five types, which are useful in multiple natural language processing (NLP) applications.

Support Vector Machines (SVM) have been used successfully in many Natural Language Processing (NLP) tasks. The novel contribution of this paper is in investigating two techniques for making SVM more suitable for language learning tasks. Firstly, we propose an SVM with uneven margins (SVMUM) model to deal with the problem of imbalanced training data. Secondly, SVM active learning is employed in order to alleviate the difficulty in obtaining labelled training data. The algorithms are presented and evaluated on several Information Extraction (IE) tasks, where they achieved better performance than the standard SVM and the SVM with passive learning, respectively. Moreover, by combining SVMUM with the active learning algorithm, we achieve the best reported results on the seminars and jobs corpora, which are benchmark data sets used for evaluation and comparison of machine learning algorithms for IE. In addition, we also evaluate the token based classification framework for IE with three different entity tagging schemes. In comparison to previous methods dealing with the same problems, our methods are both effective and efficient, which are valuable features for real-world applications. Due to the similarity in the formulation of the learning problem for IE and for other NLP tasks, the two techniques are likely to be beneficial in a wide range of applications1.

The FrameNet database comprises an English lexicon, organized in terms of semantic frames. Frames describe situations or entities, along with their participants and props, termed frame elements. The frames are organized in an ontology-like network. For the lexical units, corpus annotations illustrate which frame elements are typically realized, and how they behave syntactically. Texts where all content words are annotated with FrameNet information offer a detailed, structured semantic representation with a variety of uses in Natural Language Processing applications, in particular in retrieving and meaningfully organizing texts written by humans, or in making human–computer interaction more natural. Also, the FrameNet English lexicon can be replaced by lexical data from other languages, while maintaining frame information, so the model is attractive for cross-lingual resources and applications. Manual annotation produced by FrameNet and similar projects for other languages is used to train automatic frame semantic annotation systems, which add rich semantic information to any type of text, and are important components for more sophisticated semantic processing applications.

We report work on adding semantic role labels to the Chinese Treebank, a corpus already annotated with phrase structures. The work involves locating all verbs and their nominalizations in the corpus, and semi-automatically adding semantic role labels to their arguments, which are constituents in a parse tree. Although the same procedure is followed, different issues arise in the annotation of verbs and nominalized predicates. For verbs, identifying their arguments is generally straightforward given their syntactic structure in the Chinese Treebank as they tend to occupy well-defined syntactic positions. Our discussion focuses on the syntactic variations in the realization of the arguments as well as our approach to annotating dislocated and discontinuous arguments. In comparison, identifying the arguments for nominalized predicates is more challenging and we discuss criteria and procedures for distinguishing arguments from non-arguments. In particular we focus on the role of support verbs as well as the relevance of event/result distinctions in the annotation of the predicate-argument structure of nominalized predicates. We also present our approach to taking advantage of the syntactic structure in the Chinese Treebank to bootstrap the predicate-argument structure annotation of verbs. Finally, we discuss the creation of a lexical database of frame files and its role in guiding predicate-argument annotation. Procedures for ensuring annotation consistency and inter-annotator agreement evaluation results are also presented.

We propose a novel approach to developing a tractable affective dialogue model for probabilistic frame-based dialogue systems. The affective dialogue model, based on Partially Observable Markov Decision Process (POMDP) and Dynamic Decision Network (DDN) techniques, is composed of two main parts: the slot-level dialogue manager and the global dialogue manager. It has two new features: (1) being able to deal with a large number of slots and (2) being able to take into account some aspects of the user's affective state in deriving the adaptive dialogue strategies. Our implemented prototype dialogue manager can handle hundreds of slots, where each individual slot might have hundreds of values. Our approach is illustrated through a route navigation example in the crisis management domain. We conducted various experiments to evaluate our approach and to compare it with approximate POMDP techniques and handcrafted policies. The experimental results showed that the DDN–POMDP policy outperforms three handcrafted policies when the user's action error is induced by stress as well as when the observation error increases. Further, performance of the one-step look-ahead DDN–POMDP policy after optimizing its internal reward is close to state-of-the-art approximate POMDP counterparts.

Interactive question answering (QA), where a dialogue interface enables follow-up and clarification questions, is a recent although long-advocated field of research. We report on the design and implementation of YourQA, our open-domain, interactive QA system. YourQA relies on a Web search engine to obtain answers to both fact-based and complex questions, such as descriptions and definitions. We describe the dialogue moves and management model making YourQA interactive, and discuss the architecture, implementation and evaluation of its chat-based dialogue interface. Our Wizard-of-Oz study and final evaluation results show how the designed architecture can effectively achieve open-domain, interactive QA.

In this article, we underpin the intuition that frame semantic information is a useful resource for modelling textual entailment. To this end, we provide a manual frame semantic annotation for the test set used in the second recognizing textual entailment (RTE) challenge – the FrameNet-annotated textual entailment (FATE) corpus – and discuss experiments we conducted on this basis. In particular, our experiments show that the frame semantic lexicon provided by the Berkeley FrameNet project provides surprisingly good coverage for the task at hand. We identify issues of automatic semantic analysis components, as well as insufficient modelling of the information provided by frame semantic analysis as reasons for ambivalent results of current systems based on frame semantics.