Matéo Mahaut, Laura Aina, Paula Czarnowska, Momchil Hardalov, Thomas Müller, Lluis Marquez. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Abstract We propose a language-independent graph-based method to build à-la-carte article collections on user-defined domains from the Wikipedia. The core model is based on the exploration of the encyclopedia’s category graph and can produce both mono- and multilingual comparable collections. We run thorough experiments to assess the quality of the obtained corpora in 10 languages and 743 domains. According to an extensive manual evaluation, our graph model reaches an average precision of $$84\%$$ 84 % on in-domain articles, outperforming an alternative model based on information retrieval techniques. As manual evaluations are costly, we introduce the concept of domainness and design several automatic metrics to account for the quality of the collections. Our best metric for domainness shows a strong correlation with human judgments, representing a reasonable automatic alternative to assess the quality of domain-specific corpora. We release the toolkit with the implementation of the extraction methods, the evaluation measures and several utilities.

Abstract This work introduces robust multi-dialectal part of speech tagging trained on an annotated data set of Arabic tweets in four major dialect groups: Egyptian, Levantine, Gulf, and Maghrebi. We implement two different sequence tagging approaches. The first uses conditional random fields (CRFs), while the second combines word- and character-based representations in a deep neural network with stacked layers of convolutional and recurrent networks with a CRF output layer. We successfully exploit a variety of features that help generalize our models, such as Brown clusters and stem templates. Also, we develop robust joint models that tag multi-dialectal tweets and outperform uni-dialectal taggers. We achieve a combined accuracy of 92.4% across all dialects, with per dialect results ranging between 90.2% and 95.4%. We obtained the results using a train/dev/test split of 70/10/20 for a data set of 350 tweets per dialect.

Abstract 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.

Community Question Answering (cQA) forums are very popular nowadays, as they represent effective means for communities around particular topics to share information. Unfortunately, this information is not always factual. Thus, here we explore a new dimension in the context of cQA, which has been ignored so far: checking the veracity of answers to particular questions in cQA forums. As this is a new problem, we create a specialized dataset for it. We further propose a novel multi-faceted model, which captures information from the answer content (what is said and how), from the author profile (who says it), from the rest of the community forum (where it is said), and from external authoritative sources of information (external support). Evaluation results show a MAP value of 86.54, which is 21 points absolute above the baseline.

We address jointly two important tasks for Question Answering in community forums: given a new question, (i) find related existing questions, and (ii) find relevant answers to this new question.We further use an auxiliary task to complement the previous two, i.e., (iii) find good answers with respect to the thread question in a question-comment thread.We use deep neural networks (DNNs) to learn meaningful task-specific embeddings, which we then incorporate into a conditional random field (CRF) model for the multitask setting, performing joint learning over a complex graph structure.While DNNs alone achieve competitive results when trained to produce the embeddings, the CRF, which makes use of the embeddings and the dependencies between the tasks, improves the results significantly and consistently across a variety of evaluation metrics, thus showing the complementarity of DNNs and structured learning.

Mitra Mohtarami, Ramy Baly, James Glass, Preslav Nakov, Lluís Màrquez, Alessandro Moschitti. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). 2018.

We address the problem of cross-language adaptation for question-question similarity reranking in community question answering, with the objective to port a system trained on one input language to another input language given labeled training data for the first language and only unlabeled data for the second language.In particular, we propose to use adversarial training of neural networks to learn high-level features that are discriminative for the main learning task, and at the same time are invariant across the input languages.The evaluation results show sizable improvements for our cross-language adversarial neural network (CLANN) model over a strong nonadversarial system.

While neural machine translation (NMT) models provide improved translation quality in an elegant framework, it is less clear what they learn about language. Recent work has started evaluating the quality of vector representations learned by NMT models on morphological and syntactic tasks. In this paper, we investigate the representations learned at different layers of NMT encoders. We train NMT systems on parallel data and use the models to extract features for training a classifier on two tasks: part-of-speech and semantic tagging. We then measure the performance of the classifier as a proxy to the quality of the original NMT model for the given task. Our quantitative analysis yields interesting insights regarding representation learning in NMT models. For instance, we find that higher layers are better at learning semantics while lower layers tend to be better for part-of-speech tagging. We also observe little effect of the target language on source-side representations, especially in higher quality models.

Community question answering (CQA) forums can provide effective means for sharing information and addressing a user's information needs about particular topics. However, many such online forums are not moderated, resulting in many low quality and redundant comments, which makes it very challenging for users to find the appropriate answers to their questions. In this paper, we apply a user-centered design approach to develop a system, CQAVis, which supports users in identifying high quality comments and get their questions answered. Informed by the user's requirements, the system combines both text analytics and interactive visualization techniques together in a synergistic way. Given a new question posed by the user, the text analytic module automatically finds relevant answers by exploring existing related questions and the comments within their threads. Then the visualization module presents the search results to the user and supports the exploration of related comments. We have evaluated the system in the wild by deploying it within a CQA forum among thousands of real users. Through the online study, we gained deeper insights about the potential utility of the system, as well as learned generalizable lessons for designing visual text analytics systems for the domain of CQA forums.

We study how to find relevant questions in community forums when the language of the new questions is different from that of the existing questions in the forum. In particular, we explore the Arabic-English language pair. We compare a kernel-based system with a feed-forward neural network in a scenario where a large parallel corpus is available for training a machine translation system, bilingual dictionaries, and cross-language word embeddings. We observe that both approaches degrade the performance of the system when working on the translated text, especially the kernel-based system, which depends heavily on a syntactic kernel. We address this issue using a cross-language tree kernel, which compares the original Arabic tree to the English trees of the related questions. We show that this kernel almost closes the performance gap with respect to the monolingual system. On the neural network side, we use the parallel corpus to train cross-language embeddings, which we then use to represent the Arabic input and the English related questions in the same space. The results also improve to close to those of the monolingual neural network. Overall, the kernel system shows a better performance compared to the neural network in all cases.

In this article, we explore the potential of using sentence-level discourse structure for machine translation evaluation. We first design discourse-aware similarity measures, which use all-subtree kernels to compare discourse parse trees in accordance with the Rhetorical Structure Theory (RST). Then, we show that a simple linear combination with these measures can help improve various existing machine translation evaluation metrics regarding correlation with human judgments both at the segment level and at the system level. This suggests that discourse information is complementary to the information used by many of the existing evaluation metrics, and thus it could be taken into account when developing richer evaluation metrics, such as the WMT-14 winning combined metric DiscoTKparty. We also provide a detailed analysis of the relevance of various discourse elements and relations from the RST parse trees for machine translation evaluation. In particular, we show that (i) all aspects of the RST tree are relevant, (ii) nuclearity is more useful than relation type, and (iii) the similarity of the translation RST tree to the reference RST tree is positively correlated with translation quality.

We address the problem of answering new questions in community forums, by selecting suitable answers to already asked questions.We approach the task as an answer ranking problem, adopting a pairwise neural network architecture that selects which of two competing answers is better.We focus on the utility of the three types of similarities occurring in the triangle formed by the original question, the related question, and an answer to the related comment, which we call relevance, relatedness, and appropriateness.Our proposed neural network models the interactions among all input components using syntactic and semantic embeddings, lexical matching, and domain-specific features.It achieves state-of-the-art results, showing that the three similarities are important and need to be modeled together.Our experiments demonstrate that all feature types are relevant, but the most important ones are the lexical similarity features, the domain-specific features, and the syntactic and semantic embeddings.

This paper addresses the problem of comment classification in community Question Answering.Following the state of the art, we approach the task with a global inference process to exploit the information of all comments in the answer-thread in the form of a fully connected graph.Our contribution comprises two novel joint learning models that are on-line and integrate inference within learning.The first one jointly learns two node-and edge-level MaxEnt classifiers with stochastic gradient descent and integrates the inference step with loopy belief propagation.The second model is an instance of fully connected pairwise CRFs (FCCRF).The FCCRF model significantly outperforms all other approaches and yields the best results on the task to date.Crucial elements for its success are the global normalization and an Ising-like edge potential.

Tao Lei, Hrishikesh Joshi, Regina Barzilay, Tommi Jaakkola, Kateryna Tymoshenko, Alessandro Moschitti, Lluís Màrquez. Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2016.

Web search engines have made great progress at answering factoid queries. However, they are not well-tailored for managing more complex questions, especially when they require explanation and/or description. The WebQA workshop series aims at exploring diverse approaches to answering questions on the Web. This year, particular emphasis will be given to Community Question Answering (CQA), where comments by the users engaged in the forum communities can be used to answer new questions. Questions posted on the Web can be short and ambiguous (similarly to Web queries to a search engine). These issues make the WebQA task more challenging than traditional QA, and finding the most effective approaches for it remains an open problem.

With the increasingly global nature of our everyday interactions, the need for multilin- gual technologies to support efficient and effective information access and communication cannot be overemphasized. Computational modeling of language has been the focus of Natural Language Processing, a subdiscipline of Artificial Intelligence. One of the current challenges for this discipline is to design methodologies and algorithms that are cross- language in order to create multilingual technologies rapidly. The goal of this JAIR special issue on Cross-Language Algorithms and Applications (CLAA) is to present leading re- search in this area, with emphasis on developing unifying themes that could lead to the development of the science of multi- and cross-lingualism. In this introduction, we provide the reader with the motivation for this special issue and summarize the contributions of the papers that have been included. The selected papers cover a broad range of cross-lingual technologies including machine translation, domain and language adaptation for sentiment analysis, cross-language lexical resources, dependency parsing, information retrieval and knowledge representation. We anticipate that this special issue will serve as an invaluable resource for researchers interested in topics of cross-lingual natural language processing.

Francisco Guzmán, Shafiq Joty, Lluís Màrquez, Preslav Nakov. Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2015.

Shafiq Joty, Alberto Barrón-Cedeño, Giovanni Da San Martino, Simone Filice, Lluís Màrquez, Alessandro Moschitti, Preslav Nakov. Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. 2015.

Tao Lei, Yuan Zhang, Lluís Màrquez, Alessandro Moschitti, Regina Barzilay. Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2015.

In this article we present a three-step methodology for dynamically improving a statistical machine translation (SMT) system by incorporating human feedback in the form of free edits on the system translations. We target at feedback provided by casual users, which is typically error-prone. Thus, we first propose a filtering step to automatically identify the better user-edited translations and discard the useless ones. A second step produces a pivot-based alignment between source and user-edited sentences, focusing on the errors made by the system. Finally, a third step produces a new translation model and combines it linearly with the one from the original system. We perform a thorough evaluation on a real-world dataset collected from the Reverso.net translation service and show that every step in our methodology contributes significantly to improve a general purpose SMT system. Interestingly, the quality improvement is not only due to the increase of lexical coverage, but to a better lexical selection, reordering, and morphology. Finally, we show the robustness of the methodology by applying it to a different scenario, in which the new examples come from an automatically Web-crawled parallel corpus. Using exactly the same architecture and models provides again a significant improvement of the translation quality of a general purpose baseline SMT system.

We present experiments in using discourse structure for improving machine translation evaluation.We first design two discourse-aware similarity measures, which use all-subtree kernels to compare discourse parse trees in accordance with the Rhetorical Structure Theory.Then, we show that these measures can help improve a number of existing machine translation evaluation metrics both at the segment-and at the system-level.Rather than proposing a single new metric, we show that discourse information is complementary to the state-of-the-art evaluation metrics, and thus should be taken into account in the development of future richer evaluation metrics.

Francisco Guzmán, Shafiq Joty, Lluís Màrquez, Alessandro Moschitti, Preslav Nakov, Massimo Nicosia. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). 2014.

We introduce a Semantic Role Labeling (SRL) parser that finds semantic roles for a predicate together with the syntactic paths linking predicates and arguments.Our main contribution is to formulate SRL in terms of shortest-path inference, on the assumption that the SRL model is restricted to arc-factored features of the syntactic paths behind semantic roles.Overall, our method for SRL is a novel way to exploit larger variability in the syntactic realizations of predicate-argument relations, moving away from pipeline architectures.Experiments show that our approach improves the robustness of the predictions, producing arc-factored models that perform closely to methods using unrestricted features from the syntax.

We present an empirical study on the use of semantic information for Concept Seg-mentation and Labeling (CSL), which is an important step for semantic parsing. We represent the alternative analyses out-put by a state-of-the-art CSL parser with tree structures, which we rerank with a classifier trained on two types of seman-tic tree kernels: one processing structures built with words, concepts and Brown clusters, and another one using semantic similarity among the words composing the structure. The results on a corpus from the restaurant domain show that our semantic kernels exploiting similarity measures out-perform state-of-the-art rerankers. 1

This paper focuses on a well-known open issue in Semantic Role Classification (SRC) research: the limited influence and sparseness of lexical features. We mitigate this problem using models that integrate automatically learned selectional preferences (SP). We explore a range of models based on WordNet and distributional-similarity SPs. Furthermore, we demonstrate that the SRC task is better modeled by SP models centered on both verbs and prepositions, rather than verbs alone. Our experiments with SP-based models in isolation indicate that they outperform a lexical baseline with 20 F1 points in domain and almost 40 F1 points out of domain. Furthermore, we show that a state-of-the-art SRC system extended with features based on selectional preferences performs significantly better, both in domain (17% error reduction) and out of domain (13% error reduction). Finally, we show that in an end-to-end semantic role labeling system we obtain small but statistically significant improvements, even though our modified SRC model affects only approximately 4% of the argument candidates. Our post hoc error analysis indicates that the SP-based features help mostly in situations where syntactic information is either incorrect or insufficient to disambiguate the correct role.

In this paper we introduce a joint arc-factored model for syntactic and semantic dependency parsing. The semantic role labeler predicts the full syntactic paths that connect predicates with their arguments. This process is framed as a linear assignment task, which allows to control some well-formedness constraints. For the syntactic part, we define a standard arc-factored dependency model that predicts the full syntactic tree. Finally, we employ dual decomposition techniques to produce consistent syntactic and predicate-argument structures while searching over a large space of syntactic configurations. In experiments on the CoNLL-2009 English benchmark we observe very competitive results.

Abstract During last decade, machine learning and, in particular, statistical approaches have become more and more important for research in Natural Language Processing (NLP) and Computational Linguistics. Nowadays, most stakeholders of the field use machine learning, as it can significantly enhance both system design and performance. However, machine learning requires careful parameter tuning and feature engineering for representing language phenomena. The latter becomes more complex when the system input/output data is structured, since the designer has both to (i) engineer features for representing structure and model interdependent layers of information, which is usually a non-trivial task; and (ii) generate a structured output using classifiers, which, in their original form, were developed only for classification or regression. Research in empirical NLP has been tackling this problem by constructing output structures as a combination of the predictions of independent local classifiers, eventually applying post-processing heuristics to correct incompatible outputs by enforcing global properties. More recently, some advances of the statistical learning theory, namely structured output spaces and kernel methods, have brought techniques for directly encoding dependencies between data items in a learning algorithm that performs global optimization. Within this framework, this special issue aims at studying, comparing, and reconciling the typical domain/task-specific NLP approaches to structured data with the most advanced machine learning methods. In particular, the selected papers analyze the use of diverse structured input/output approaches, ranging from re-ranking to joint constraint-based global models, for diverse natural language tasks, i.e., document ranking, syntactic parsing, sequence supertagging, and relation extraction between terms and entities. Overall, the experience with this special issue shows that, although a definitive unifying theory for encoding and generating structured information in NLP applications is still far from being shaped, some interesting and effective best practice can be defined to guide practitioners in modeling their own natural language application on complex data.

In this article, we present a factoid question-answering system, Sibyl, specifically tailored for question answering (QA) on spoken-word documents. This work explores, for the first time, which techniques can be robustly adapted from the usual QA on written documents to the more difficult spoken document scenario. More specifically, we study new information retrieval (IR) techniques designed or speech, and utilize several levels of linguistic information for the speech-based QA task. These include named-entity detection with phonetic information, syntactic parsing applied to speech transcripts, and the use of coreference resolution. Sibyl is largely based on supervised machine-learning techniques, with special focus on the answer extraction step, and makes little use of handcrafted knowledge. Consequently, it should be easily adaptable to other domains and languages. Sibyl and all its modules are extensively evaluated on the European Parliament Plenary Sessions English corpus, comparing manual with automatic transcripts obtained by three different automatic speech recognition (ASR) systems that exhibit significantly different word error rates. This data belongs to the CLEF 2009 track for QA on speech transcripts. The main results confirm that syntactic information is very useful for learning to rank question candidates, improving results on both manual and automatic transcripts, unless the ASR quality is very low. At the same time, our experiments on coreference resolution reveal that the state-of-the-art technology is not mature enough to be effectively exploited for QA with spoken documents. Overall, the performance of Sibyl is comparable or better than the state-of-the-art on this corpus, confirming the validity of our approach.

This paper presents our experiments in question answering for speech corpora. These experiments focus on improving the answer extraction step of the QA process. We present two approaches to answer extraction in question answering for speech corpora that apply machine learning to improve the coverage and precision of the extraction. The first one is a reranker that uses only lexical information, the second one uses dependency parsing to score robust similarity between syntactic structures. Our experimental results show that the proposed learning models improve our previous results using only hand-made ranking rules with small syntactic information. Moreover, this results show also that a dependency parser can be useful for speech transcripts even if it was trained with written text data from a\nnews collection. We evaluate the system on manual transcripts of speech from EPPS English corpus and a set of questions transcribed from spontaneous oral questions. This data belongs to the CLEF 2009 track on QA on speech transcripts (QAst).

A design for an Arabic-to-English translation system is presented. The core of the system implements a standard phrase-based statistical machine translation architecture, but it is extended by incorporating a local discriminative phrase selection model to address the semantic ambiguity of Arabic. Local classifiers are trained using linguistic information and context to translate a phrase, and this significantly increases the accuracy in phrase selection with respect to the most frequent translation traditionally considered. These classifiers are integrated into the translation system so that the global task gets benefits from the discriminative learning. As a result, we obtain significant improvements in the full translation task at the lexical, syntactic, and semantic levels as measured by an heterogeneous set of automatic evaluation metrics.

Semantic role labeling, the computational identification and labeling of arguments in text, has become a leading task in computational linguistics today. Although the issues for this task have been studied for decades, the availability of large resources and the development of statistical machine learning methods have heightened the amount of effort in this field. This special issue presents selected and representative work in the field. This overview describes linguistic background of the problem, the movement from linguistic theories to computational practice, the major resources that are being used, an overview of steps taken in computational systems, and a description of the key issues and results in semantic role labeling (as revealed in several international evaluations). We assess weaknesses in semantic role labeling and identify important challenges facing the field. Overall, the opportunities and the potential for useful further research in semantic role labeling are considerable.

This paper introduces and analyzes a battery of inference models for the problem of semantic role labeling: one based on constraint satisfaction, and several strategies that model the inference as a meta-learning problem using discriminative classifiers. These classifiers are developed with a rich set of novel features that encode proposition and sentence-level information. To our knowledge, this is the first work that: (a) performs a thorough analysis of learning-based inference models for semantic role labeling, and (b) compares several inference strategies in this context. We evaluate the proposed inference strategies in the framework of the CoNLL-2005 shared task using only automatically-generated syntactic information. The extensive experimental evaluation and analysis indicates that all the proposed inference strategies are successful -they all outperform the current best results reported in the CoNLL-2005 evaluation exercise- but each of the proposed approaches has its advantages and disadvantages. Several important traits of a state-of-the-art SRL combination strategy emerge from this analysis: (i) individual models should be combined at the granularity of candidate arguments rather than at the granularity of complete solutions; (ii) the best combination strategy uses an inference model based in learning; and (iii) the learning-based inference benefits from max-margin classifiers and global feedback.

We present a novel approach for parameter adjustment in empirical machine translation systems. Instead of relying on a single evaluation metric, or in an ad-hoc linear combination of metrics, our method works over metric combinations with maximum descriptive power, aiming to maximise the Human Likeness of the automatic translations. We apply it to the problem of optimising decoding stage parameters of a state- of-the-art Statistical machine translation system. By means of a rigorous manual evaluation, we show how our methodology provides more reliable and robust system configurations than a tuning strategy based on the BLEU metric alone.

An experimental comparison among support vector machines, Ada boost and a recently proposed model for maximizing the margin with feed-forward neural networks has been made on a real-world classification problem, namely text categorization. The results obtained when comparing their agreement on the predictions show that similar performance does not imply similar predictions, suggesting that different models can be combined to obtain better performance. As a consequence of the study, we derived a very simple confidence measure of the prediction of the tested margin-based classifiers. This measure is based on the margin curve. The combination of margin based classifiers with this confidence measure lead to a marked improvement on the performance of the system, when combined with several well-known combination schemes.

This work presents an architecture based on perceptrons to recognize phrase structures, and an online learning algorithm to train the percep- trons together and dependently. The recognition strategy applies learning in two layers: a filtering layer, which reduces the search space by identi- fying plausible phrase candidates, and a ranking layer, which recursively builds the optimal phrase structure. We provide a recognition-based feed- back rule which reflects to each local function its committed errors from a global point of view, and allows to train them together online as percep- trons. Experimentation on a syntactic parsing problem, the recognition of clause hierarchies, improves state-of-the-art results and evinces the advantages of our global training method over optimizing each function locally and independently.

This paper describes a set of experiments carried out to explore the domain dependence of alternative supervised Word Sense Disambiguation algorithms. The aim of the work is threefold: studying the performance of these algorithms when tested on a different corpus from that they were trained on; exploring their ability to tune to new domains, and demonstrating empirically that the Lazy-Boosting algorithm outperforms state-of-the-art supervised WSD algorithms in both previous situations.

We present an algorithm that automatically learns context constraints using statistical decision trees. We then use the acquired constraints in a flexible POS tagger. The tagger is able to use information of any degree: n-grams, automatically learned context constraints, linguistically motivated manually written constraints, etc. The sources and kinds of constraints are unrestricted, and the language model can be easily extended, improving the results. The tagger has been tested and evaluated on the WSJ corpus.