Word Sense Disambiguation

This chapter discusses the basic concepts of Word Sense Disambiguation (WSD) and the approaches to solving this problem. Both general purpose WSD and domain specific WSD are presented. The first part of the discussion focuses on existing approaches for WSD, including knowledge-based, supervised, semi-supervised, unsupervised, hybrid, and bilingual approaches. The accuracy value for general purpose WSD as the current state of affairs seems to be pegged at around 65%. This has motivated investigations into domain specific WSD, which is the current trend in the field. In the latter part of the chapter, we present a greedy neural network inspired algorithm for domain specific WSD and compare its performance with other state-of-the-art algorithms for WSD. Our experiments suggest that for domain-specific WSD, simply selecting the most frequent sense of a word does as well as any state-of-the-art algorithm.

Multiword Expressions in NLP

This chapter presents a survey of contemporary NLP research on Multiword Expressions (MWEs). MWEs pose a huge problem to precise language processing due to their idiosyncratic nature and diversity of their semantic, lexical, and syntactical properties. The chapter begins by considering MWEs definitions, describes some MWEs classes, indicates problems MWEs generate in language applications and their possible solutions, presents methods of MWE encoding in dictionaries and their automatic detection in corpora. The chapter goes into more detail on a particular MWE class called Verb-Noun Constructions (VNCs). Due to their frequency in corpus and unique characteristics, VNCs present a research problem in their own right. Having outlined several approaches to VNC representation in lexicons, the chapter explains the formalism of Lexical Function as a possible VNC representation. Such representation may serve as a tool for VNCs automatic detection in a corpus. The latter is illustrated on Spanish material applying some supervised learning methods commonly used for NLP tasks.

NLP and Digital Library Management

The field of study of Natural Language Processing (NLP) has developed over the past 50 years or so, producing an array of now mature technology, such as automatic morphological analysis, word sense disambiguation, parsing, anaphora resolution, natural language generation, named entity recognition, etc. The proliferation of large digital collections (evolving into Digital Libraries) and the emerging economic value of information demand efficient solutions for managing the information which is available, but which is not always easy to find. This chapter presents the requirements for handling documents in digital libraries and explains how existing NLP technology can be used to facilitate the task of document management.

A Computational Cognitive Model of Human Translation Processes

Human translation process research analyzes the translation behavior of translators, such as memory and search strategies to solve translation problems, types of units that translators focus on, etc., identifies the temporal (and/or contextual) structure of those activities, and describes inter- and intra-personal variation. Various models have been developed that explain translators’ behavior in terms of controlled and uncontrolled workspaces and with micro- and macro-translation strategies. However, only a few attempts have been made to ground and quantify translation process models in empirical user activity data. In order to close this gap, this chapter outlines a computational framework for a cognitive model of human translation. The authors investigate the structure of the translators’ keystrokes and gaze data, discuss possibilities for their classification and visualization, and explain how a translation model can be grounded and trained on the empirical data. The insight gained from such a computational translation model not only enlarges our knowledge about human translation processes, but also has the potential to enhance the design of interactive MT systems and help interpret user activity data in human-MT system interaction.

Statistical Machine Translation

Statistical Machine Translation (SMT) is an approach to automatic text translation based on the use of statistical models and examples of translations. SMT is the current dominant research paradigm for machine translation and has been attracting significant commercial interest in recent years. In this chapter, the authors introduce the rationale behind SMT, describe the currently leading approach (phrase-based SMT), and present a number of emerging approaches (tree-based SMT, discriminative SMT). They also present popular metrics to evaluate the performance of SMT systems and discuss promising research directions in the field.

Mining User-Generated Content for Social Research and Other Applications

The main objective of this chapter is to present a general overview of the most relevant applications of text mining and natural language processing technologies evolving and emerging around the Web 2.0 phenomenon (such as automatic categorization, document summarization, question answering, dialogue management, opinion mining, sentiment analysis, outlier identification, misbehavior detection, and social estimation and forecasting) along with the main challenges and new research opportunities that are directly and indirectly derived from them.

Multilingual Information Access

This chapter focuses on Multilingual Information Access (MLIA), a multidisciplinary area that aims to solve accessing, querying, and retrieving information from heterogeneous information sources expressed in different languages. Current Information Retrieval technology, combined with Natural Language Processing tools allows building systems able to efficiently retrieve relevant information and, to some extent, to provide concrete answers to questions expressed in natural language. Besides, when linguistic resources and translation tools are available, cross-language information systems can assist to find information in multiple languages. Nevertheless, little is still known about how to properly assist people to find and use information expressed in unknown languages. Approaches proved as useful for automatic systems seem not to match with real user’s needs.

Issues and Challenges in Building Multilingual Information Access Systems

In this chapter, the authors start their discussion highlighting the importance of Cross Lingual and Multilingual Information Retrieval and access research areas. They then discuss the distinction between Cross Language Information Retrieval (CLIR), Multilingual Information Retrieval (MLIR), Cross Language Information Access (CLIA), and Multilingual Information Access (MLIA) research areas. In addition, in further sections, issues and challenges in these areas are outlined, and various approaches, including machine learning-based and knowledge-based approaches to address the multilingual information access, are discussed. The authors describe various subsystems of a MLIA system ranging from query processing to output generation by sharing their experience of building a MLIA system and discuss its architecture. Then evaluation aspects of the MLIA and CLIA systems are discussed at the end of this chapter.

Interactive Question Answering

The increasing amount of information available online has led to the development of technologies that help to deal with it. One of them is Interactive Question Answering (IQA), a research field that has emerged at the intersection of question answering and dialogue systems, and which allows users to find the answers to questions in an interactive way. During the answering process, the automatic system can initiate a dialogue with the user in order to clarify missing or ambiguous information, or suggest further topics for discussion. This chapter presents the state-of-the-art in the field of interactive question answering. Given that IQA inherits a lot of features from dialogue systems and question answering, these fields are also briefly presented. Analysis of the existing systems reveals that in general IQA systems rely on a scaled-down version of a dialogue system, sometimes built on top of question answering systems. Evaluation of IQA is also discussed, showing that it combines evaluation techniques from question answering and dialogue systems.

Advanced Question-Answering and Discourse Semantics

In this chapter, the authors develop the paradigm of advanced question-answering that includes how-to, why, evaluative, comparative, and opinion questions. They show the different parameters at stake in answer production, involving several aspects of cooperativity. These types of questions require quite a lot of discourse semantics analysis and domain knowledge. The second part of this chapter is devoted to a short presentation of those text semantics aspects relevant to answering questions. The last part of this chapter introduces <TextCoop>, a platform the authors have developed for discourse semantics analysis that they use for answering complex questions, in particular how-to and opinion questions.