We propose a language-independent word normalisation method and exemplify it on modernising historical Slovene words. Our method relies on character-level statistical machine translation (CSMT) and uses only shallow knowledge. We present relevant data on historical Slovene, consisting of two (partially) manually annotated corpora and the lexicons derived from these corpora, containing historical word–modern word pairs. The two lexicons are disjoint, with one serving as the training set containing 40,000 entries, and the other as a test set with 20,000 entries. The data spans the years 1750–1900, and the lexicons are split into fifty-year slices, with all the experiments carried out separately on the three time periods. We perform two sets of experiments. In the first one – a supervised setting – we build a CSMT system using the lexicon of word pairs as training data. In the second one – an unsupervised setting – we simulate a scenario in which word pairs are not available. We propose a two-step method where we first extract a noisy list of word pairs by matching historical words with cognate modern words, and then train a CSMT system on these pairs. In both sets of experiments, we also optionally make use of a lexicon of modern words to filter the modernisation hypotheses. While we show that both methods produce significantly better results than the baselines, their accuracy and which method works best strongly correlates with the age of the texts, meaning that the choice of the best method will depend on the properties of the historical language which is to be modernised. As an extrinsic evaluation, we also compare the quality of part-of-speech tagging and lemmatisation directly on historical text and on its modernised words. We show that, depending on the age of the text, annotation on modernised words also produces significantly better results than annotation on the original text.

The alignment of WordNet and Wikipedia has received wide attention from researchers of computational linguistics, who are building a new lexical knowledge source or enriching the semantic information of WordNet entities. The main challenge of this alignment is how to handle the synonymy and ambiguity issues in the contents of two units from different sources. Therefore, this paper introduces mapping method that links an Arabic WordNet synset to its corresponding article in Wikipedia. This method uses monolingual and bilingual features to overcome the lack of semantic information in Arabic WordNet. For evaluating this method, an Arabic mapping data set, which contains 1,291 synset–article pairs, is compiled. The experimental analysis shows that the proposed method achieves promising results and outperforms the state-of-the-art methods that depend only on monolingual features. The mapped method has also been used to increase the coverage of Arabic WordNet by inserting new synsets from Wikipedia.

We investigate the problem of complex answers in question answering. Complex answers consist of several simple answers. We describe the online question answering system SHAPAQA, and using data from this system we show that the problem of complex answers is quite common. We define nine types of complex questions, and suggest two approaches, based on answer frequencies, that allow question answering systems to tackle the problem.

Arabic prosody is the science that studies the music of Arabic poetry, which is mainly meter and rhyme. The identification of meters for Arabic verses or poems is a complicated task. This task requires a certain level of expertise to identify the meter to which a verse belongs. In this paper, we present BASRAH1, a system that automatically identifies the meter of Arabic poetry by using the numerical prosody method. The numerical prosody method depends on verse coding, which is derived from the general concept of Al-Khalil's feet by using two primary units (cord = 2) and (peg = 3). On testing both old and modern Arabic verses and poems, BASRAH has proved to be an efficient tool to help inexperienced users to determine the meter of Arabic verses and poems.

We analyze resources and models for Arabic community Question Answering (cQA). In particular, we focus on CQA-MD, our cQA corpus for Arabic in the domain of medical forums. We describe the corpus and the main challenges it poses due to its mix of informal and formal language, and of different Arabic dialects, as well as due to its medical nature. We further present a shared task on cQA at SemEval, the International Workshop on Semantic Evaluation, based on this corpus. We discuss the features and the machine learning approaches used by the teams who participated in the task, with focus on the models that exploit syntactic information using convolutional tree kernels and neural word embeddings. We further analyze and extend the outcome of the SemEval challenge by training a meta-classifier combining the output of several systems. This allows us to compare different features and different learning algorithms in an indirect way. Finally, we analyze the most frequent errors common to all approaches, categorizing them into prototypical cases, and zooming into the way syntactic information in tree kernel approaches can help solve some of the most difficult cases. We believe that our analysis and the lessons learned from the process of corpus creation as well as from the shared task analysis will be helpful for future research on Arabic cQA.

Many research topics in natural language processing (NLP), such as explanation generation, dialog modeling, or machine translation, require evaluation that goes beyond standard metrics like accuracy or F1 score toward a more human-centered approach. Therefore, understanding how to design user studies becomes increasingly important. However, few comprehensive resources exist on planning, conducting, and evaluating user studies for NLP, making it hard to get started for researchers without prior experience in the field of human evaluation. In this paper, we summarize the most important aspects of user studies and their design and evaluation, providing direct links to NLP tasks and NLP-specific challenges where appropriate. We (i) outline general study design, ethical considerations, and factors to consider for crowdsourcing, (ii) discuss the particularities of user studies in NLP, and provide starting points to select questionnaires, experimental designs, and evaluation methods that are tailored to the specific NLP tasks. Additionally, we offer examples with accompanying statistical evaluation code, to bridge the gap between theoretical guidelines and practical applications.

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.

Paraphrase corpora are an essential but scarce resource in Natural Language Processing. In this paper, we present the Wikipedia-based Relational Paraphrase Acquisition (WRPA) method, which extracts relational paraphrases from Wikipedia, and the derived WRPA paraphrase corpus. The WRPA corpus currently covers person-related and authorship relations in English and Spanish, respectively, suggesting that, given adequate Wikipedia coverage, our method is independent of the language and the relation addressed. WRPA extracts entity pairs from structured information in Wikipedia applying distant learning and, based on the distributional hypothesis, uses them as anchor points for candidate paraphrase extraction from the free text in the body of Wikipedia articles. Focussing on relational paraphrasing and taking advantage of Wikipedia-structured information allows for an automatic and consistent evaluation of the results. The WRPA corpus characteristics distinguish it from other types of corpora that rely on string similarity or transformation operations. WRPA relies on distributional similarity and is the result of the free use of language outside any reformulation framework. Validation results show a high precision for the corpus.

Recently, most part-of-speech tagging approaches, such as rule-based, probabilistic and neural network approaches, have shown very promising results. In this paper, we are particularly interested in probabilistic approaches, which usually require lots of training data to get reliable probabilities. We alleviate such a restriction of probabilistic approaches by introducing a fuzzy network model to provide a method for estimating more reliable parameters of a model under a small amount of training data. Experiments with the Brown corpus show that the performance of the fuzzy network model is much better than that of the hidden Markov model under a limited amount of training data.

We present the RAGS (Reference Architecture for Generation Systems) framework, a specification of an abstract Natural Language Generation (NLG) system architecture to support sharing, re-use, comparison and evaluation of NLG technologies. We argue that the evidence from a survey of actual NLG systems calls for a different emphasis in a reference proposal from that seen in similar initiatives in information extraction and multimedia interfaces. We introduce the framework itself, in particular the two-level data model that allows us to support the complex data requirements of NLG systems in a flexible and coherent fashion, and describe our efforts to validate the framework through a range of implementations.

Finding translations for technical terms is an important problem in machine translation. In particular, in highly specialized domains such as biology or medicine, it is difficult to find bilingual experts to annotate sufficient cross-lingual texts in order to train machine translation systems. Moreover, new terms are constantly being generated in the biomedical community, which makes it difficult to keep the translation dictionaries up to date for all language pairs of interest. Given a biomedical term in one language (source language), we propose a method for detecting its translations in a different language (target language). Specifically, we train a binary classifier to determine whether two biomedical terms written in two languages are translations. Training such a classifier is often complicated due to the lack of common features between the source and target languages. We propose several feature space concatenation methods to successfully overcome this problem. Moreover, we study the effectiveness of contextual and character n-gram features for detecting term translations. Experiments conducted using a standard dataset for biomedical term translation show that the proposed method outperforms several competitive baseline methods in terms of mean average precision and top-k translation accuracy.

This paper describes the key aspects of a parser developed at the University of Pennsylvania from 1958 to 1959. The parser is essentially a cascade of finite state transducers. To the best of our knowledge, this is the first application of finite state transducers to parsing. This parser was recently faithfully reconstructed from the original documentation. Many aspects of this program have a close relationship to some of the recent work on finite state transducers.

This paper addresses the feasibility of cross-lingual parsing with Universal Dependencies (UD) between Romance languages, analyzing its performance when compared to the use of manually annotated resources of the target languages. Several experiments take into account factors such as the lexical distance between the source and target varieties, the impact of delexicalization, the combination of different source treebanks or the adaptation of resources to the target language, among others. The results of these evaluations show that the direct application of a parser from one Romance language to another reaches similar labeled attachment score (LAS) values to those obtained with a manual annotation of about 3,000 tokens in the target language, and unlabeled attachment score (UAS) results equivalent to the use of around 7,000 tokens, depending on the case. These numbers can noticeably increase by performing a focused selection of the source treebanks. Furthermore, the removal of the words in the training corpus (delexicalization) is not useful in most cases of cross-lingual parsing of Romance languages. The lessons learned with the performed experiments were used to build a new UD treebank for Galician, with 1,000 sentences manually corrected after an automatic cross-lingual annotation. Several evaluations in this new resource show that a cross-lingual parser built with the best combination and adaptation of the source treebanks performs better (77 percent LAS and 82 percent UAS) than using more than 16,000 (for LAS results) and more than 20,000 (UAS) manually labeled tokens of Galician.

Named Entity Recognition is a basic task in Information Extraction that aims at identifying entities of interest within full text documents. The patterns used to recognize entities can be rule based, as in the popular JAPE system. However, hand-crafting effective patterns is often difficult, and yet there is little research devoted to methods capable of learning human-readable patterns, possibly with arbitrary sets of features. In this paper, we present a semi-automatic method to generate both regular expressions and a subset of the JAPE language. It does not need a corpus annotated beforehand. Instead, it employs active learning and combines clustering with an algorithm that finds alignments between symbols present in the entities discovered during the learning process. The method currently supports a fixed set of character features and an arbitrary set of token features, but it can incorporate other kinds of features as well. Through several experiments with an English corpus, we show the ability of the method to generate effective patterns at a low annotation cost, and how it can successfully help in the annotation of brand new corpora.

Generic software architectures aim to support re-use of components, focusing of research and development effort, and evaluation and comparison of approaches. In the field of natural language processing, generic frameworks for understanding have been successfully deployed to meet all of these aims, but nothing comparable yet exists for generation. The nature of the task itself, and the current methodologies available to research it, seem to make it more difficult to reach the necessary level of consensus to support generic proposals. Recent work has made progress towards establishing a generic framework for generation at the functional level, but left open the issue of actual implementation. In this paper, we discuss the requirements for such an implementation layer for generation systems, drawing on two initial attempts to implement it. We argue that it is possible and useful to distinguish “functional architecture” from “implementation architecture” for generation systems.

In training deep learning networks, the optimizer and related learning rate are often used without much thought or with minimal tuning, even though it is crucial in ensuring a fast convergence to a good quality minimum of the loss function that can also generalize well on the test dataset. Drawing inspiration from the successful application of cyclical learning rate policy to computer vision tasks, we explore how cyclical learning rate can be applied to train transformer-based neural networks for neural machine translation. From our carefully designed experiments, we show that the choice of optimizers and the associated cyclical learning rate policy can have a significant impact on the performance. In addition, we establish guidelines when applying cyclical learning rates to neural machine translation tasks.

Alleviating pain is good and abandoning hope is bad. We instinctively understand how words like alleviate and abandon affect the polarity of a phrase, inverting or weakening it. When these words are content words, such as verbs, nouns, and adjectives, we refer to them as polarity shifters. Shifters are a frequent occurrence in human language and an important part of successfully modeling negation in sentiment analysis; yet research on negation modeling has focused almost exclusively on a small handful of closed-class negation words, such as not, no, and without. A major reason for this is that shifters are far more lexically diverse than negation words, but no resources exist to help identify them. We seek to remedy this lack of shifter resources by introducing a large lexicon of polarity shifters that covers English verbs, nouns, and adjectives. Creating the lexicon entirely by hand would be prohibitively expensive. Instead, we develop a bootstrapping approach that combines automatic classification with human verification to ensure the high quality of our lexicon while reducing annotation costs by over 70%. Our approach leverages a number of linguistic insights; while some features are based on textual patterns, others use semantic resources or syntactic relatedness. The created lexicon is evaluated both on a polarity shifter gold standard and on a polarity classification task.

Case systems abound in natural language processing. Almost any attempt to recognize and uniformly represent relationships within a clause – a unit at the centre of any linguistic system that goes beyond word level statistics – must be based on semantic roles drawn from a small, closed set. The set of roles describing relationships between a verb and its arguments within a clause is a case system. What is required of such a case system? How does a natural language practitioner build a system that is complete and detailed yet practical and natural? This paper chronicles the construction of a case system from its origin in English marker words to its successful application in the analysis of English text.

Automatic text summarisation is a topic that has been receiving attention from the research community from the early days of computational linguistics, but it really took off around 25 years ago. This article presents the main developments from the last 25 years. It starts by defining what a summary is and how its definition changed over time as a result of the interest in processing new types of documents. The article continues with a brief history of the field and highlights the main challenges posed by the evaluation of summaries. The article finishes with some thoughts about the future of the field.

In this paper, we discuss the results of a new unsupervised and computationally lightweight scoring of how two words are morphologically related to each other. This measure is meant to be an alternative to stemming, radicals (root) extraction, and morphological analysis in a wide range of applications; especially information extraction related ones. Compared to light stemming, which seems to be the most convenient approach for systems with efficiency concerns, our measure does not neglect unconditionally a prefix or a suffix as the light stemming does. Instead, our measure takes into account all letters of the word but with different weights. This prevents the missing of a significant letter. Compared to heavy stemming, morphological analysis, or radicals extraction, which rely on dictionaries and compatibility databases, our measure does not rely on any language-specific morphology knowledge. This makes our approach unsupervised and theoretically language independent and computationally much lighter. Our tests targeted Arabic: a Semitic language recognized to have a complex morphology due to its highly inflectional lexicon.