In this paper, we apply different supervised learning techniques to build query-focused multi-document summarization systems, where the task is to produce automatic summaries in response to a given query or specific information request stated by the user. A huge amount of labeled data is a prerequisite for supervised training. It is expensive and time-consuming when humans perform the labeling task manually. Automatic labeling can be a good remedy to this problem. We employ five different automatic annotation techniques to build extracts from human abstracts using ROUGE, Basic Element overlap, syntactic similarity measure, semantic similarity measure, and Extended String Subsequence Kernel. The supervised methods we use are Support Vector Machines, Conditional Random Fields, Hidden Markov Models, Maximum Entropy, and two ensemble-based approaches. During different experiments, we analyze the impact of automatic labeling methods on the performance of the applied supervised methods. To our knowledge, no other study has deeply investigated and compared the effects of using different automatic annotation techniques on different supervised learning approaches in the domain of query-focused multi-document summarization.

This article proposes clause-level evaluation detection, which is a fine-grained type of opinion mining, and describes an unsupervised lexicon building method for capturing domain-specific knowledge by leveraging the similar polarities of sentiments between adjacent clauses. The lexical entries to be acquired are called polar atoms, the minimum human-understandable syntactic structures that specify the polarity of clauses. As a hint to obtain candidate polar atoms, we use context coherency, the tendency for the same polarity to appear successively in a context. Using the overall density and precision of coherency in the corpus, the statistical estimation picks up appropriate polar atoms from among the candidates, without any manual tuning of the threshold values. The experimental results show that the precision of polarity assignment with the automatically acquired lexicon was 83 per cent on average, and our method is robust for corpora in diverse domains and for the size of the initial lexicon.

For the past two decades, specialised events on finite-state methods have been successful in presenting interesting studies on natural language processing to the public through journals and collections. The FSMNLP workshops have become well-known among researchers and are now the main forum of the Association for Computational Linguistics' (ACL) Special Interest Group on Finite-State Methods (SIGFSM). The current issue on finite-state methods and models in natural language processing was planned in 2008 in this context as a response to a call for special issue proposals. In 2010, the issue received a total of sixteen submissions, some of which were extended and updated versions of workshop papers, and others which were completely new. The final selection, consisting of only seven papers that could fit into one issue, is not fully representative, but complements the prior special issues in a nice way. The selected papers showcase a few areas where finite-state methods have less than obvious and sometimes even groundbreaking relevance to natural language processing (NLP) applications.

Text correction systems rely on a core mechanism where suitable correction suggestions for garbled input tokens are generated. Current systems, which are designed for documents including modern language, use some form of approximate search in a given background lexicon. Due to the large amount of spelling variation found in historical documents, special lexica for historical language can only offer restricted coverage. Hence historical language is often described in terms of a matching procedure to be applied to modern words. Given such a procedure and a base lexicon of modern words, the question arises of how to generate correction suggestions for garbled historical variants. In this paper we suggest an efficient algorithm that solves this problem. The algorithm is used for postcorrection of optical character recognition results on historical document collections.

Relations computed by finite-state transducers are applied to interpret temporal propositions in terms of strings representing finite contexts or situations. Carnap–Montague intensions mapping indices to extensions are reformulated as relations between strings that can serve as indices and extensions alike. Strings are related according to information content, temporal span and granularity, the bounds on which reflect the partiality of natural language statements. That partiality shapes not only strings-as-extensions (indicating what statements are about) but also strings-as-indices (underlying truth conditions).

Synchronous tree substitution grammars (stsg) are a (formal) tree transformation model that is used in the area of syntax-based machine translation. A competitor that is at least as expressive as stsg is proposed and compared to stsg. The competitor is the extended multi bottom-up tree transducer (mbot), which is the bottom-up analogue with the additional feature that states have non-unary ranks. Unweighted mbot have already been investigated with respect to their basic properties, but the particular properties of the constructions that are required in the machine translation task are largely unknown. stsg and mbot are compared with respect to binarization, regular restriction, and application. Particular attention is paid to the complexity of the constructions.

Feature-based regular tree grammars (FRTG) can be used to generate the derivation trees of a feature-based tree adjoining grammar (FTAG). We make use of this fact to specify and implement both an FTAG-based sentence realiser and a benchmark generator for this realiser. We argue furthermore that the FRTG encoding enables us to improve on other proposals based on a grammar of TAG derivation trees in several ways. It preserves the compositional semantics that can be encoded in feature-based TAGs; it increases efficiency and restricts overgeneration; and it provides a uniform resource for generation, benchmark construction and parsing.

In this paper, we present techniques that exploit finite-state models for voice search applications. In particular, we illustrate the use of finite-state models for encoding the search index in order to tightly integrate the speech recognition and the search components of a voice search system. We show that the tight integration mutually benefits Automatic Speech Recognition and improves the search. In the second part of the paper, we discuss the use of finite-state techniques for spoken language understanding, in particular, to segment an input query into its component semantic fields so as to improve search as well as to extend the functionality of the system and be able to execute the user's request against a backend database.

This paper presents a set of experiments for the detection and correction of syntactic errors, exploring two alternative approaches. The first one uses an error grammar which combines a robust morphosyntactic analyser and two groups of finite-state transducers (one for the description of syntactic error patterns and the other for the correction of the detected errors). We have also experimented an alternative approach using a positive date grammar where deviations are detected by applying edit-distance techniques. The system has been tested on a corpus of real texts which contained both correct and incorrect sentences. Although the experiment was limited to one language, the results show that attainable performance is not the only criterion for preferring one solution over another.

We present a randomised inference algorithm for regular tree languages. The algorithm takes as input two disjoint finite nonempty sets of trees 𝒫 and 𝒩 and outputs a nondeterministic finite tree automaton that accepts every tree in 𝒫 and rejects every tree in 𝒩. The output automaton typically represents a nontrivial generalisation of the examples given in 𝒫 and 𝒩. To obtain compact output automata, we use a heuristics similar to bisimulation minimisation. The algorithm has time complexity of , where n𝒩 and n𝒫 are the size of 𝒩 and 𝒫, respectively. Experiments are conducted on a prototype implementation, and the empirical results appear to second the theoretical results.

The user-generated Web content has been intensively analyzed in Information Extraction and Natural Language Processing research. Web-posted reviews of consumer goods are studied to find customer opinions about the products. We hypothesize that nonemotionally charged descriptions can be applied to predict those opinions. The descriptions may include indicators of product size (tall), commonplace (some), frequency of happening (often), and reviewer certainty (maybe). We first construct patterns of how the descriptions are used in consumer-written texts and then represent individual reviews through these patterns. We propose a semantic hierarchy that organizes individual words into opinion types. We run machine learning algorithms on five data sets of user-written product reviews: four are used in classification experiments, another one for regression and classification. The obtained results support the use of non-emotional descriptions in opinion learning.

In this article, we explore the task of mood classification for blog postings. We propose a novel approach that uses the hierarchy of possible moods to achieve better results than a standard machine learning approach. We also show that using sentiment orientation features improves the performance of classification. We used the Livejournal blog corpus as a data set to train and evaluate our method. We present extensive error analysis and discuss the difficulty of the task.

A vast amount of usable electronic data is in the form of unstructured text. The relation extraction task aims to identify useful information in text (e.g. PersonW works for OrganisationX, GeneY encodes ProteinZ) and recode it in a format such as a relational database or RDF triplestore that can be more effectively used for querying and automated reasoning. A number of resources have been developed for training and evaluating automatic systems for relation extraction in different domains. However, comparative evaluation is impeded by the fact that these corpora use different markup formats and notions of what constitutes a relation. We describe the preparation of corpora for comparative evaluation of relation extraction across domains based on the publicly available ACE 2004, ACE 2005 and BioInfer data sets. We present a common document type using token standoff and including detailed linguistic markup, while maintaining all information in the original annotation. The subsequent reannotation process normalises the two data sets so that they comply with a notion of relation that is intuitive, simple and informed by the semantic web. For the ACE data, we describe an automatic process that automatically converts many relations involving nested, nominal entity mentions to relations involving non-nested, named or pronominal entity mentions. For example, the first entity is mapped from ‘one’ to ‘Amidu Berry’ in the membership relation described in ‘Amidu Berry, one half of PBS’. Moreover, we describe a comparably reannotated version of the BioInfer corpus that flattens nested relations, maps part-whole to part-part relations and maps n-ary to binary relations. Finally, we summarise experiments that compare approaches to generic relation extraction, a knowledge discovery task that uses minimally supervised techniques to achieve maximally portable extractors. These experiments illustrate the utility of the corpora.1

In dialogue systems it is important to label the dialogue turns with dialogue-related meaning. Each turn is usually divided into segments and these segments are labelled with dialogue acts (DAs). A DA is a representation of the functional role of the segment. Each segment is labelled with one DA, representing its role in the ongoing discourse. The sequence of DAs given a dialogue turn is used by the dialogue manager to understand the turn. Probabilistic models that perform DA labelling can be used on segmented or unsegmented turns. The last option is more likely for a practical dialogue system, but it provides poorer results. In that case, a hypothesis for the number of segments can be provided to improve the results. We propose some methods to estimate the probability of the number of segments based on the transcription of the turn. The new labelling model includes the estimation of the probability of the number of segments in the turn. We tested this new approach with two different dialogue corpora: SwitchBoard and Dihana. The results show that this inclusion significantly improves the labelling accuracy.

While different user simulations are built to assist dialog system development, there is an increasing need to quickly assess the quality of the user simulations reliably. Previous studies have proposed several automatic evaluation measures for this purpose. However, the validity of these evaluation measures has not been fully proven. We present an assessment study in which human judgments are collected on user simulation qualities as the gold standard to validate automatic evaluation measures. We show that a ranking model can be built using the automatic measures to predict the rankings of the simulations in the same order as the human judgments. We further show that the ranking model can be improved by using a simple feature that utilizes time-series analysis.