When assessing the similarity of arguments, researchers typically use approaches that do not provide interpretable evidence or justifications for their ratings. Hence, the features that determine argument similarity remain elusive. We address this issue by introducing novel argument similarity metrics that aim at high performance and explainability. We show that Abstract Meaning Representation (AMR) graphs can be useful for representing arguments, and that novel AMR graph metrics can offer explanations for argument similarity ratings. We start from the hypothesis that similar premises often lead to similar conclusions—and extend an approach for AMR-based argument similarity rating by estimating, in addition, the similarity of conclusions that we automatically infer from the arguments used as premises. We show that AMR similarity metrics make argument similarity judgements more interpretable and may even support argument quality judgements. Our approach provides significant performance improvements over strong baselines in a fully unsupervised setting. Finally, we make first steps to address the problem of reference-less evaluation of argumentative conclusion generations.
Key point analysis is the task of extracting a set of concise and high-level statements from a given collection of arguments, representing the gist of these arguments. This paper presents our proposed approach to the Key Point Analysis Shared Task, colocated with the 8th Workshop on Argument Mining. The approach integrates two complementary components. One component employs contrastive learning via a siamese neural network for matching arguments to key points; the other is a graph-based extractive summarization model for generating key points. In both automatic and manual evaluation, our approach was ranked best among all submissions to the shared task.
Recent question answering and machine reading benchmarks frequently reduce the task to one of pinpointing spans within a certain text passage that answers the given question. Typically, these systems are not required to actually understand the text on a deeper level that allows for more complex reasoning on the information contained. We introduce a new dataset called BiQuAD that requires deeper comprehension in order to answer questions in both extractive and deductive fashion. The dataset consist of 4,190 closed-domain texts and a total of 99,149 question-answer pairs. The texts are synthetically generated soccer match reports that verbalize the main events of each match. All texts are accompanied by a structured Datalog program that represents a (logical) model of its information. We show that state-of-the-art QA models do not perform well on the challenging long form contexts and reasoning requirements posed by the dataset. In particular, transformer based state-of-the-art models achieve F1-scores of only 39.0. We demonstrate how these synthetic datasets align structured knowledge with natural text and aid model introspection when approaching complex text understanding.
Model-complete text comprehension aims at interpreting a natural language text with respect to a semantic domain model describing the classes and their properties relevant for the domain in question. Solving this task can be approached as a structured prediction problem, consisting in inferring the most probable instance of the semantic model given the text. In this work, we focus on the challenging sub-problem of cardinality prediction that consists in predicting the number of distinct individuals of each class in the semantic model. We show that cardinality prediction can successfully be approached by modeling the overall task as a joint inference problem, predicting the number of individuals of certain classes while at the same time extracting their properties. We approach this task with probabilistic graphical models computing the maximum-a-posteriori instance of the semantic model. Our main contribution lies on the empirical investigation and analysis of different approximative inference strategies based on Gibbs sampling. We present and evaluate our models on the task of extracting key parameters from scientific full text articles describing pre-clinical studies in the domain of spinal cord injury.
In recent years, there has been increasing interest in publishing lexicographic and terminological resources as linked data. The benefit of using linked data technologies to publish terminologies is that terminologies can be linked to each other, thus creating a cloud of linked terminologies that cross domains, languages and that support advanced applications that do not work with single terminologies but can exploit multiple terminologies seamlessly. We present Terme-‘a-LLOD (TAL), a new paradigm for transforming and publishing terminologies as linked data which relies on a virtualization approach. The approach rests on a preconfigured virtual image of a server that can be downloaded and installed. We describe our approach to simplifying the transformation and hosting of terminological resources in the remainder of this paper. We provide a proof-of-concept for this paradigm showing how to apply it to the conversion of the well-known IATE terminology as well as to various smaller terminologies. Further, we discuss how the implementation of our paradigm can be integrated into existing NLP service infrastructures that rely on virtualization technology. While we apply this paradigm to the transformation and hosting of terminologies as linked data, the paradigm can be applied to any other resource format as well.
In social care environments, the main goal of social workers is to foster independent living by their clients. An important task is thus to monitor progress towards reaching independence in different areas of their patients’ life. To support this task, we present an approach that extracts indications of independence on different life aspects from the day-to-day documentation that social workers create. We describe the process of collecting and annotating a corresponding corpus created from data records of two social work institutions with a focus on disability care. We show that the agreement on the task of annotating the observations of social workers with respect to discrete independent levels yields a high agreement of .74 as measured by Fleiss’ Kappa. We present a classification approach towards automatically classifying an observation into the discrete independence levels and present results for different types of classifiers. Against our original expectation, we show that we reach F-Measures (macro) of 95% averaged across topics, showing that this task can be automatically solved.
In this paper we describe the contributions made by the European H2020 project “Prêt-à-LLOD” (‘Ready-to-use Multilingual Linked Language Data for Knowledge Services across Sectors’) to the further development of the Linguistic Linked Open Data (LLOD) infrastructure. Prêt-à-LLOD aims to develop a new methodology for building data value chains applicable to a wide range of sectors and applications and based around language resources and language technologies that can be integrated by means of semantic technologies. We describe the methods implemented for increasing the number of language data sets in the LLOD. We also present the approach for ensuring interoperability and for porting LLOD data sets and services to other infrastructures, as well as the contribution of the projects to existing standards.
Aspect-based sentiment analysis involves the recognition of so called opinion target expressions (OTEs). To automatically extract OTEs, supervised learning algorithms are usually employed which are trained on manually annotated corpora. The creation of these corpora is labor-intensive and sufficiently large datasets are therefore usually only available for a very narrow selection of languages and domains. In this work, we address the lack of available annotated data for specific languages by proposing a zero-shot cross-lingual approach for the extraction of opinion target expressions. We leverage multilingual word embeddings that share a common vector space across various languages and incorporate these into a convolutional neural network architecture for OTE extraction. Our experiments with 5 languages give promising results: We can successfully train a model on annotated data of a source language and perform accurate prediction on a target language without ever using any annotated samples in that target language. Depending on the source and target language pairs, we reach performances in a zero-shot regime of up to 77% of a model trained on target language data. Furthermore, we can increase this performance up to 87% of a baseline model trained on target language data by performing cross-lingual learning from multiple source languages.
Supervised machine learning algorithms require training data whose generation for complex relation extraction tasks tends to be difficult. Being optimized for relation extraction at sentence level, many annotation tools lack in facilitating the annotation of relational structures that are widely spread across the text. This leads to non-intuitive and cumbersome visualizations, making the annotation process unnecessarily time-consuming. We propose SANTO, an easy-to-use, domain-adaptive annotation tool specialized for complex slot filling tasks which may involve problems of cardinality and referential grounding. The web-based architecture enables fast and clearly structured annotation for multiple users in parallel. Relational structures are formulated as templates following the conceptualization of an underlying ontology. Further, import and export procedures of standard formats enable interoperability with external sources and tools.
We propose to study the evolution of concepts by learning to complete diachronic analogies between lists of terms which relate to the same concept at different points in time. We present a number of models based on operations on word embedddings that correspond to different assumptions about the characteristics of diachronic analogies and change in concept vocabularies. These are tested in a quantitative evaluation for nine different concepts on a corpus of Dutch newspapers from the 1950s and 1980s. We show that a model which treats the concept terms as analogous and learns weights to compensate for diachronic changes (weighted linear combination) is able to more accurately predict the missing term than a learned transformation and two baselines for most of the evaluated concepts. We also find that all models tend to be coherent in relation to the represented concept, but less discriminative in regard to other concepts. Additionally, we evaluate the effect of aligning the time-specific embedding spaces using orthogonal Procrustes, finding varying effects on performance, depending on the model, concept and evaluation metric. For the weighted linear combination, however, results improve with alignment in a majority of cases. All related code is released publicly.
Fine-grained sentiment analysis is receiving increasing attention in recent years. Extracting opinion target expressions (OTE) in reviews is often an important step in fine-grained, aspect-based sentiment analysis. Retrieving this information from user-generated text, however, can be difficult. Customer reviews, for instance, are prone to contain misspelled words and are difficult to process due to their domain-specific language. In this work, we investigate whether character-level models can improve the performance for the identification of opinion target expressions. We integrate information about the character structure of a word into a sequence labeling system using character-level word embeddings and show their positive impact on the system’s performance. Specifically, we obtain an increase by 3.3 points F1-score with respect to our baseline model. In further experiments, we reveal encoded character patterns of the learned embeddings and give a nuanced view of the performance differences of both models.
Word embeddings have been shown to be highly effective in a variety of lexical semantic tasks. They tend to capture meaningful relational similarities between individual words, at the expense of lacking the capabilty of making the underlying semantic relation explicit. In this paper, we investigate the attribute relation that often holds between the constituents of adjective-noun phrases. We use CBOW word embeddings to represent word meaning and learn a compositionality function that combines the individual constituents into a phrase representation, thus capturing the compositional attribute meaning. The resulting embedding model, while being fully interpretable, outperforms count-based distributional vector space models that are tailored to attribute meaning in the two tasks of attribute selection and phrase similarity prediction. Moreover, as the model captures a generalized layer of attribute meaning, it bears the potential to be used for predictions over various attribute inventories without re-training.
The Open Linguistics Working Group (OWLG) brings together researchers from various fields of linguistics, natural language processing, and information technology to present and discuss principles, case studies, and best practices for representing, publishing and linking linguistic data collections. A major outcome of our work is the Linguistic Linked Open Data (LLOD) cloud, an LOD (sub-)cloud of linguistic resources, which covers various linguistic databases, lexicons, corpora, terminologies, and metadata repositories. We present and summarize five years of progress on the development of the cloud and of advancements in open data in linguistics, and we describe recent community activities. The paper aims to serve as a guideline to orient and involve researchers with the community and/or Linguistic Linked Open Data.
In order to explore intuitive verbal and non-verbal interfaces in smart environments we recorded user interactions with an intelligent apartment. Besides offering various interactive capabilities itself, the apartment is also inhabited by a social robot that is available as a humanoid interface. This paper presents a multi-modal corpus that contains goal-directed actions of naive users in attempts to solve a number of predefined tasks. Alongside audio and video recordings, our data-set consists of large amount of temporally aligned sensory data and system behavior provided by the environment and its interactive components. Non-verbal system responses such as changes in light or display contents, as well as robot and apartment utterances and gestures serve as a rich basis for later in-depth analysis. Manual annotations provide further information about meta data like the current course of study and user behavior including the incorporated modality, all literal utterances, language features, emotional expressions, foci of attention, and addressees.
In order to make the growing amount of conceptual knowledge available through ontologies and datasets accessible to humans, NLP applications need access to information on how this knowledge can be verbalized in natural language. One way to provide this kind of information are ontology lexicons, which apart from the actual verbalizations in a given target language can provide further, rich linguistic information about them. Compiling such lexicons manually is a very time-consuming task and requires expertise both in Semantic Web technologies and lexicon engineering, as well as a very good knowledge of the target language at hand. In this paper we present an alternative approach to generating ontology lexicons by means of crowdsourcing: We use CrowdFlower to generate a small Japanese ontology lexicon for ten exemplary ontology elements from the DBpedia ontology according to a two-stage workflow, the main underlying idea of which is to turn the task of generating lexicon entries into a translation task; the starting point of this translation task is a manually created English lexicon for DBpedia. Comparison of the results to a manually created Japanese lexicon shows that the presented workflow is a viable option if an English seed lexicon is already available.
Recent years have witnessed a surge in the amount of semantic information published on the Web. Indeed, the Web of Data, a subset of the Semantic Web, has been increasing steadily in both volume and variety, transforming the Web into a ‘global database’ in which resources are linked across sites. Linguistic fields -- in a broad sense -- have not been left behind, and we observe a similar trend with the growth of linguistic data collections on the so-called ‘Linguistic Linked Open Data (LLOD) cloud’. While both Semantic Web and Natural Language Processing communities can obviously take advantage of this growing and distributed linguistic knowledge base, they are today faced with a new challenge, i.e., that of facilitating multilingual access to the Web of data. In this paper we present the publication of BabelNet 2.0, a wide-coverage multilingual encyclopedic dictionary and ontology, as Linked Data. The conversion made use of lemon, a lexicon model for ontologies particularly well-suited for this enterprise. The result is an interlinked multilingual (lexical) resource which can not only be accessed on the LOD, but also be used to enrich existing datasets with linguistic information, or to support the process of mapping datasets across languages.
Opinion mining has received wide attention in recent years. Models for this task are typically trained or evaluated with a manually annotated dataset. However, fine-grained annotation of sentiments including information about aspects and their evaluation is very labour-intensive. The data available so far is limited. Contributing to this situation, this paper describes the Bielefeld University Sentiment Analysis Corpus for German and English (USAGE), which we offer freely to the community and which contains the annotation of product reviews from Amazon with both aspects and subjective phrases. It provides information on segments in the text which denote an aspect or a subjective evaluative phrase which refers to the aspect. Relations and coreferences are explicitly annotated. This dataset contains 622 English and 611 German reviews, allowing to investigate how to port sentiment analysis systems across languages and domains. We describe the methodology how the corpus was created and provide statistics including inter-annotator agreement. We further provide figures for a baseline system and results for German and English as well as in a cross-domain setting. The results are encouraging in that they show that aspects and phrases can be extracted robustly without the need of tuning to a particular type of products.
The creation of language resources is a time-consuming process requiring the efforts of many people. The use of resources collaboratively created by non-linguistists can potentially ameliorate this situation. However, such resources often contain more errors compared to resources created by experts. For the particular case of lexica, we analyse the case of Wiktionary, a resource created along wiki principles and argue that through the use of a principled lexicon model, namely Lemon, the resulting data could be better understandable to machines. We then present a platform called Lemon Source that supports the creation of linked lexical data along the Lemon model. This tool builds on the concept of a semantic wiki to enable collaborative editing of the resources by many users concurrently. In this paper, we describe the model, the tool and present an evaluation of its usability based on a small group of users.
In this paper we describe SOBA, a sub-component of the SmartWeb multi-modal dialog system. SOBA is a component for ontologybased information extraction from soccer web pages for automatic population of a knowledge base that can be used for domainspecific question answering. SOBA realizes a tight connection between the ontology, knowledge base and the information extraction component. The originality of SOBA is in the fact that it extracts information from heterogeneous sources such as tabular structures, text and image captions in a semantically integrated way. In particular, it stores extracted information in a knowledge base, and in turn uses the knowledge base to interpret and link newly extracted information with respect to already existing entities.
Recent work has aimed at discovering ontological relations from text corpora. Most approaches are based on the assumption that verbs typically indicate semantic relations between concepts. However, the problem of finding the appropriate generalization level for the verb's arguments with respect to a given taxonomy has not received much attention in the ontology learning community. In this paper, we address the issue of determining the appropriate level of abstraction for binary relations extracted from a corpus with respect to a given concept hierarchy. For this purpose, we reuse techniques from the subcategorization and selectional restrictions acquisition communities. The contribution of our work lies in the systematic analysis of three different measures. We conduct our experiments on the Genia corpus and the Genia ontology and evaluate the different measures by comparing the results of our approach with a gold standard provided by one of the authors, a biologist.