Dialogue-based Question Answering (QA) is a highly complex task that brings together a QA system including various natural language processing components (i.e., components for question classification, information extraction, and retrieval) with dialogue systems for effective and natural communication. The dialogue-based access is difficult to establish when the QA system in use is complex and combines many different answer services with different quality and access characteristics. For example, some questions are processed by opendomain QA services with a broad coverage. Others should be processed by using a domain-specific instance ontology for more reliable answers. Different answer services may change their characteristics over time and the dialogue reaction models have to be updated according to that. To solve this problem, we developed introspective methods to integrate adaptable models of the answer services. We evaluated the impact of the learned models on the dialogue performance, i.e., whether the adaptable models can be used for a more convenient dialogue formulation process. We show significant effectiveness improvements in the resulting dialogues when using the machine learning (ML) models. Examples are provided in the context of the generation of system-initiative feedback to user questions and answers, as provided by heterogeneous information services.

In this paper we propose a system to solve a language game, called Guillotine, which requires a player with a strong cultural and linguistic background knowledge. The player observes a set of five words, generally unrelated to each other, and in one minute she has to provide a sixth word, semantically connected to the others. Several knowledge sources, such as a dictionary  and a set of proverbs, have been modeled and integrated in order to realize a knowledge infusion process into the system. The main motivation for designing an artificial player for Guillotine is the challenge of providing the machine with the cultural and linguistic background knowledge which makes it similar to a human being, with the ability of interpreting natural language documents and reasoning on their content. Experiments carried out showed promising results, and both the knowledge source modeling and the reasoning mechanisms  (implementing  a spreading activation algorithm to find out the solution) seem to be appropriate. We are convinced that the approach has a great potential for other more practical applications besides solving a language game, such as semantic search.

An exception is which tracks the extent to which material has our Degrees of Grounding model [Roque and Traum, 2008], reached mutual belief in a dialogue, and conduct which provides a more detailed description of the extent to experiments in which the model is used to manage which material has become a part of the common ground during grounding behavior in spoken dialogues with a virtual a dialogue. In this paper we describe experiments in applying human. We show that the model produces improvements that model to handle explicit grounding behavior in in virtual human performance as measured a virtual human. We begin by describing the model and the by post-session questionnaires.

Unsupervised learning of morphology is an important task for human learners and in natural language processing systems. Previous systems focus on segmenting words into substrings (taking ⇒ tak.ing), but sometimes a segmentation-only analysis is insufficient (e.g., taking may be more appropriately analyzed as take+ing, with a spelling rule accounting for the deletion of the stem-final e). In this paper, we develop a Bayesian model for simultaneously inducing both morphology and spelling rules. We show that the addition of spelling rules improves performance over the baseline morphology-only model.

Reading involves, among others, identifying what is implied but not expressed in text. This task, known as textual entailment, offers a natural abstraction for many NLP tasks, and has been recognized as a central tool for the new area of Machine Reading. Important in the study of textual entailment is making precise the sense in which something is implied by text. The operational definition often employed is a subjective one: something is implied if humans are more likely to believe it given the truth of the text, than otherwise. In this work we propose a natural objective definition for textual entailment. Our approach is to view text as a partial depiction of some underlying hidden reality. Reality is mapped into text through a possibly stochastic process, the author of the text. Textual entailment is then formalized as the task of accurately, in a defined sense, recovering information about this hidden reality. We show how existing machine learning work can be applied to this information recovery setting, and discuss the implications for the construction of machines that autonomously engage in textual entailment. We then investigate the role of using multiple inference rules for this task. We establish that such rules cannot be learned and applied in parallel, but that layered learning and reasoning are necessary.

Question-answer pairs extracted from email threads can help construct summaries of the thread, as well as inform semantic-based assistance with email. Previous work dedicated to email threads extracts only questions in interrogative form. We extend the scope of question and answer detection and pairing to encompass also questions in imperative and declarative forms, and to operate at sentence-level fidelity. Building on prior work, our methods are based on learned models over a set of features that include the content, context, and structure of email threads. For two large email corpora, we show that our methods balance precision and recall in extracting question-answer pairs, while maintaining a modest computation time.

The field of information retrieval and text manipulation (classification, clustering) still strives for models allowing semantic information to be folded in to improve performance with respect to standard bag-of-word based models. Many approaches aim at a concept-based retrieval, but differ in the nature of the concepts, which range from linguistic concepts as defined in lexical resources such as WordNet, latent topics derived from the data itself—as in Latent Semantic Indexing (LSI) or (Latent Dirichlet Allocation (LDA)—to Wikipedia articles as proxies for concepts, as in the recently proposed Explicit Semantic Analysis (ESA) model. A crucial question which has not been answered so far is whether models based on explicitly given concepts (as in the ESA model for instance) perform inherently better than retrieval models based on "latent" concepts (as in LSI and/or LDA). In this paper we investigate this question closer in the context of a cross-language setting, which inherently requires concept-based retrieval bridging between different languages. In particular, we compare the recently proposed ESA model with two latent models (LSI and LDA) showing that the former is clearly superior to the both. From a general perspective, our results contribute to clarifying the role of explicit vs. implicitly derived or latent concepts in (cross-language) information retrieval research.

Web-scale data has been used in a diverse range of language research. Most of this research has used web counts for only short, fixed spans of context. We present a unified view of using web counts for lexical disambiguation. Unlike previous approaches, our supervised and unsupervised systems combine information from multiple and overlapping segments of context. On the tasks of preposition selection and context-sensitive spelling correction, the supervised system reduces disambiguation error by 20-24% over the current state-of-the-art.

This paper explores the application of knowledge-based Word Sense Disambiguation systems to specific domains, based on our state-of-the-art graph-based WSD system that uses the information in WordNet. Evaluation was performed over a publicly available domain-specific dataset of 41 words related to Sports and Finance, comprising examples drawn from three corpora: one balanced corpus (BNC), and two domain-specific corpora (news related to Sports and Finance). The results show that in all three corpora our knowledge-based WSD algorithm improves over previous results, and also over two state-of-the-art supervised WSD systems trained on SemCor, the largest publicly available annotated corpus. We also show that using related words as context, instead of the actual occurrence contexts, yields better results on the domain datasets, but not on the general one.  Interestingly, the results are higher for domain-specific corpus than for the general corpus, raising prospects for improving current WSD systems when applied to specific domains.

Finding the longest common subsequence of multiple strings is a classical computer science problem and has many applications in the areas of bioinformatics and computational genomics. In this paper, we present a new sequential algorithm for the general case of MLCS problem, and its parallel realization. The algorithm is based on the dominant point approach and employs a fast divide-and-conquer technique to compute the dominant points. When applied to find a MLCS of 3 strings, our general algorithm is shown to exhibit the same performance as the best existing MLCS algorithm by Hakata and Imai, designed specifically for the case of 3 strings. Moreover, we show that for a general case of more than 3 strings, the algorithm is significantly faster than the best existing sequential approaches, reaching up to 2-3 orders of magnitude faster on the large-size problems. Finally, we propose a parallel implementation of the algorithm. Evaluating the parallel algorithm on a benchmark set of both random and biological sequences reveals a near-linear speed-up with respect to the sequential algorithm.