Automatic detection of negated content is often a prerequisite in information extraction systems in various domains. In the biomedical domain especially, this task is important because negation plays an important role. In this work, two main contributions are proposed. First, we work with languages which have been poorly addressed up to now: Brazilian Portuguese and French. Thus, we developed new corpora for these two languages which have been manually annotated for marking up the negation cues and their scope. Second, we propose automatic methods based on supervised machine learning approaches for the automatic detection of negation marks and of their scopes. The methods show to be robust in both languages (Brazilian Portuguese and French) and in cross-domain (general and biomedical languages) contexts. The approach is also validated on English data from the state of the art: it yields very good results and outperforms other existing approaches. Besides, the application is accessible and usable online. We assume that, through these issues (new annotated corpora, application accessible online, and cross-domain robustness), the reproducibility of the results and the robustness of the NLP applications will be augmented.

The tremendous amount of increase in the number of documents available on the Web has turned finding the relevant piece of information into a challenging, tedious, and time-consuming activity. Accordingly, automatic text summarization has become an important field of study by gaining significant attention from the researchers. Lately, with the advances in deep learning, neural abstractive text summarization with sequence-to-sequence (Seq2Seq) models has gained popularity. There have been many improvements in these models such as the use of pretrained language models (e.g., GPT, BERT, and XLM) and pretrained Seq2Seq models (e.g., BART and T5). These improvements have addressed certain shortcomings in neural summarization and have improved upon challenges such as saliency, fluency, and semantics which enable generating higher quality summaries. Unfortunately, these research attempts were mostly limited to the English language. Monolingual BERT models and multilingual pretrained Seq2Seq models have been released recently providing the opportunity to utilize such state-of-the-art models in low-resource languages such as Turkish. In this study, we make use of pretrained Seq2Seq models and obtain state-of-the-art results on the two large-scale Turkish datasets, TR-News and MLSum, for the text summarization task. Then, we utilize the title information in the datasets and establish hard baselines for the title generation task on both datasets. We show that the input to the models has a substantial amount of importance for the success of such tasks. Additionally, we provide extensive analysis of the models including cross-dataset evaluations, various text generation options, and the effect of preprocessing in ROUGE evaluations for Turkish. It is shown that the monolingual BERT models outperform the multilingual BERT models on all tasks across all the datasets. Lastly, qualitative evaluations of the generated summaries and titles of the models are provided.

This study describes a Natural Language Processing (NLP) toolkit, as the first contribution of a larger project, for an under-resourced language—Urdu. In previous studies, standard NLP toolkits have been developed for English and many other languages. There is also a dire need for standard text processing tools and methods for Urdu, despite it being widely spoken in different parts of the world with a large amount of digital text being readily available. This study presents the first version of the UNLT (Urdu Natural Language Toolkit) which contains three key text processing tools required for an Urdu NLP pipeline; word tokenizer, sentence tokenizer, and part-of-speech (POS) tagger. The UNLT word tokenizer employs a morpheme matching algorithm coupled with a state-of-the-art stochastic n-gram language model with back-off and smoothing characteristics for the space omission problem. The space insertion problem for compound words is tackled using a dictionary look-up technique. The UNLT sentence tokenizer is a combination of various machine learning, rule-based, regular-expressions, and dictionary look-up techniques. Finally, the UNLT POS taggers are based on Hidden Markov Model and Maximum Entropy-based stochastic techniques. In addition, we have developed large gold standard training and testing data sets to improve and evaluate the performance of new techniques for Urdu word tokenization, sentence tokenization, and POS tagging. For comparison purposes, we have compared the proposed approaches with several methods. Our proposed UNLT, the training and testing data sets, and supporting resources are all free and publicly available for academic use.

In this paper, we present a novel lemmatization method based on a sequence-to-sequence neural network architecture and morphosyntactic context representation. In the proposed method, our context-sensitive lemmatizer generates the lemma one character at a time based on the surface form characters and its morphosyntactic features obtained from a morphological tagger. We argue that a sliding window context representation suffers from sparseness, while in majority of cases the morphosyntactic features of a word bring enough information to resolve lemma ambiguities while keeping the context representation dense and more practical for machine learning systems. Additionally, we study two different data augmentation methods utilizing autoencoder training and morphological transducers especially beneficial for low-resource languages. We evaluate our lemmatizer on 52 different languages and 76 different treebanks, showing that our system outperforms all latest baseline systems. Compared to the best overall baseline, UDPipe Future, our system outperforms it on 62 out of 76 treebanks reducing errors on average by 19% relative. The lemmatizer together with all trained models is made available as a part of the Turku-neural-parsing-pipeline under the Apache 2.0 license.

We use bilingual lexicon induction techniques, which learn translations from monolingual texts in two languages, to build an end-to-end statistical machine translation (SMT) system without the use of any bilingual sentence-aligned parallel corpora. We present detailed analysis of the accuracy of bilingual lexicon induction, and show how a discriminative model can be used to combine various signals of translation equivalence (like contextual similarity, temporal similarity, orthographic similarity and topic similarity). Our discriminative model produces higher accuracy translations than previous bilingual lexicon induction techniques. We reuse these signals of translation equivalence as features on a phrase-based SMT system. These monolingually estimated features enhance low resource SMT systems in addition to allowing end-to-end machine translation without parallel corpora.

We address the problem of extracting bilingual chunk pairs from parallel text to create training sets for statistical machine translation. We formulate the problem in terms of a stochastic generative process over text translation pairs, and derive two different alignment procedures based on the underlying alignment model. The first procedure is a now-standard dynamic programming alignment model which we use to generate an initial coarse alignment of the parallel text. The second procedure is a divisive clustering parallel text alignment procedure which we use to refine the first-pass alignments. This latter procedure is novel in that it permits the segmentation of the parallel text into sub-sentence units which are allowed to be reordered to improve the chunk alignment. The quality of chunk pairs are measured by the performance of machine translation systems trained from them. We show practical benefits of divisive clustering as well as how system performance can be improved by exploiting portions of the parallel text that otherwise would have to be discarded. We also show that chunk alignment as a first step in word alignment can significantly reduce word alignment error rate.

Natural language interfaces require dialogue models that allow for robust, habitable and efficient interaction. This paper presents such a model for dialogue management for natural language interfaces. The model is based on empirical studies of human computer interaction in various simple service applications. It is shown that for applications belonging to this class the dialogue can be handled using fairly simple means. The interaction can be modeled in a dialogue grammar with information on the functional role of an utterance as conveyed in the linguistic structure. Focusing is handled using dialogue objects recorded in a dialogue tree representing the constituents of the dialogue. The dialogue objects in the dialogue tree can be accessed by the various modules for interpretation, generation and background system access. Focused entities are modeled in entities pertaining to objects or sets of objects, and related domain concept information; properties of the domain objects. A simple copying principle, where a new dialogue object's focal parameters are instantiated with information from the preceding dialogue object, accounts for most context dependent utterances. The action to be carried out by the interface is determined on the basis of how the objects and related properties are specified. This in turn depends on information presented in the user utterance, context information from the dialogue tree and information in the domain model. The use of dialogue objects facilitates customization to the sublanguage utilized in a specific application. The framework has successfully been applied to various background systems and interaction modalities. In the paper results from the customization of the dialogue manager to three typed interaction applications are presented together with results from applying the model to two applications utilizing spoken interaction.

One major obstacle to the efficient processing of large wide coverage grammars in unification-based grammatical frameworks such as HPSG is the time and space cost of the unification operation itself. In a grammar development system it is not appropriate to address this problem with techniques which involve lengthy compilation, since this slows down the edit-test-debug cycle. Nor is it possible to radically restructure the grammar. In this paper, we describe novel extensions to an existing efficient unification algorithm which improve its space and time behaviour (without affecting its correctness) by substantially increasing the amount of structure sharing that takes place. We also describe a fast and automatically tunable pre-unification filter (the ‘quick check’) which in practice detects a large proportion of unifications that if performed would fail. Finally, we present an efficient algorithm for checking for subsumption relationships between two feature structures; a special case of this gives a fast equality test. The subsumption check is used in a parser (described elsewhere in this issue) which ‘packs’ local ambiguities to avoid performing redundant sub-computations.

Cross-language information retrieval (CLIR), finding information in one language in response to queries expressed in another language, has attracted much attention due to the explosive growth of multilingual information in the World Wide Web. One important issue in CLIR is how to apply monolingual information retrieval (IR) methods in cross-lingual environments. Recently, learning to rank (LTR) approach has been successfully employed in different IR tasks. In this paper, we use LTR for CLIR. In order to adapt monolingual LTR techniques in CLIR and pass the barrier of language difference, we map monolingual IR features to CLIR ones using translation information extracted from different translation resources. The performance of CLIR is highly dependent on the size and quality of available bilingual resources. Effective use of available resources is especially important in low-resource language pairs. In this paper, we further propose an LTR-based method for combining translation resources in CLIR. We have studied the effectiveness of the proposed approach using different translation resources. Our results also show that LTR can be used to successfully combine different translation resources to improve the CLIR performance. In the best scenario, the LTR-based combination method improves the performance of single-resource-based CLIR method by 6% in terms of Mean Average Precision.

This paper addresses the task of automatic extraction of definitions by thoroughly exploring an approach that solely relies on machine learning techniques, and by focusing on the issue of the imbalance of relevant datasets. We obtained a breakthrough in terms of the automatic extraction of definitions, by extensively and systematically experimenting with different sampling techniques and their combination, as well as a range of different types of classifiers. Performance consistently scored in the range of 0.95–0.99 of area under the receiver operating characteristics, with a notorious improvement between 17 and 22 percentage points regarding the baseline of 0.73–0.77, for datasets with different rates of imbalance. Thus, the present paper also represents a contribution to the seminal work in natural language processing that points toward the importance of exploring the research path of applying sampling techniques to mitigate the bias induced by highly imbalanced datasets, and thus greatly improving the performance of a large range of tools that rely on them.

The identification and extraction of technical terms is one of the better understood and most robust Natural Language Processing (NLP) technologies within the current state of the art of language engineering. In generic information management contexts, terms have been used primarily for procedures seeking to identify a set of phrases that is useful for tasks such as text indexing, computational lexicology, and machine-assisted translation: such tasks make important use of the assumption that terminology is representative of a given domain. This paper discusses an extension of basic terminology identification technology for the application to two higher level semantic tasks: domain description, the specification of the technical domain of a document, and content characterisation, the construction of a compact, coherent and useful representation of the topical content of a text. With these extensions, terminology identification becomes the foundation of an operational environment for document processing and content abstraction.

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

Despite the long history of Natural Language Generation (NLG) research, the potential for influencing real world behaviour through automatically generated texts has not received much attention. In this paper, we present SaferDrive, a behaviour change support system that uses NLG and telematic data in order to create weekly textual feedback for automobile drivers, which is delivered through a smartphone application. Usage-based car insurances use sensors to track driver behaviour. Although the data collected by such insurances could provide detailed feedback about the driving style, they are typically withheld from the driver and used only to calculate insurance premiums. SaferDrive instead provides detailed textual feedback about the driving style, with the intent to help drivers improve their driving habits. We evaluate the system with real drivers and report that the textual feedback generated by our system does have a positive influence on driving habits, especially with regard to speeding.

Newspaper text can be broadly divided in the classes ‘opinion’ (editorials, commentary, letters to the editor) and ‘neutral’ (reports). We describe a classification system for performing this separation, which uses a set of linguistically motivated features. Working with various English newspaper corpora, we demonstrate that it significantly outperforms bag-of-lemma and PoS-tag models. We conclude that the linguistic features constitute the best method for achieving robustness against change of newspaper or domain.

This paper discusses the nature, history and current characteristics of Language Engineering, which is contrasted with Natural Language Processing and Computational Linguistics, and which is shown to have attained its own distinct identity in recent years. Major trends in the field are examined, including its focus on large-scale practical tasks and on quantitative evaluation of progress, and its willingness to embrace a diverse range of techniques. The importance of software engineering in this context is noted, as are some sociological aspects of the practitioner group.

Morphological analysis is a crucial component of several natural language processing tasks, especially for languages with a highly productive morphology, where stipulating a full lexicon of surface forms is not feasible. This paper describes HAMSAH (HAifa Morphological System for Analyzing Hebrew), a morphological processor for Modern Hebrew, based on finite-state linguistically motivated rules and a broad coverage lexicon. The set of rules comprehensively covers the morphological, morpho-phonological and orthographic phenomena that are observable in contemporary Hebrew texts. Reliance on finite-state technology facilitates the construction of a highly efficient, completely bidirectional system for analysis and generation.

Most compositional distributional semantic models represent sentence meaning with a single vector. In this paper, we propose a structured distributional model (SDM) that combines word embeddings with formal semantics and is based on the assumption that sentences represent events and situations. The semantic representation of a sentence is a formal structure derived from discourse representation theory and containing distributional vectors. This structure is dynamically and incrementally built by integrating knowledge about events and their typical participants, as they are activated by lexical items. Event knowledge is modelled as a graph extracted from parsed corpora and encoding roles and relationships between participants that are represented as distributional vectors. SDM is grounded on extensive psycholinguistic research showing that generalized knowledge about events stored in semantic memory plays a key role in sentence comprehension.We evaluate SDMon two recently introduced compositionality data sets, and our results show that combining a simple compositionalmodel with event knowledge constantly improves performances, even with dif ferent types of word embeddings.

We present a general, novel methodology for extracting multi-word expressions (MWEs) of various types, along with their translations, from small, word-aligned parallel corpora. Unlike existing approaches, we focus on misalignments; these typically indicate expressions in the source language that are translated to the target in a non-compositional way. We introduce a simple algorithm that proposes MWE candidates based on such misalignments, relying on 1:1 alignments as anchors that delimit the search space. We use a large monolingual corpus to rank and filter these candidates. Evaluation of the quality of the extraction algorithm reveals significant improvements over naïve alignment-based methods. The extracted MWEs, with their translations, are used in the training of a statistical machine translation system, showing a small but significant improvement in its performance.

Based on constraint optimization techniques, an architecture for robust parsing of natural language utterances has been developed. The resulting system is able to combine possibly contradicting evidence from a variety of information sources, using a plausibility-based arbitration procedure to derive fairly rich structural representations, comprising aspects of syntax, semantics and other description levels of language. The results of a series of experiments are reported which demonstrate the high potential for robust behaviour with respect to ungrammaticality, incomplete utterances, and temporal pressure.