This paper presents the Multitask, Multilingual, Multimodal Language Generation COST Action – Multi3Generation (CA18231), an interdisciplinary network of research groups working on different aspects of language generation. This “meta-paper” will serve as reference for citations of the Action in future publications. It presents the objectives, challenges and a the links for the achieved outcomes.

Language models for text-to-image generation can output good quality images when referential aspects of pictures are evaluated. The generation of creative images is not under scrutiny at the moment, but it poses interesting challenges: should we expect more creative images using more creative prompts? What is the relationship between prompts and images in the global process of human evaluation? In this paper, we want to highlight several criteria that should be taken into account for building a creative text-to-image generation benchmark, collecting insights from multiple disciplines (e.g., linguistics, cognitive psychology, philosophy, psychology of art).

Evaluating the complexity of a target word in a sentential context is the aim of the Lexical Complexity Prediction task at SemEval-2021. This paper presents the system created to assess single words lexical complexity, combining linguistic and psycholinguistic variables in a set of experiments involving random forest and XGboost regressors. Beyond encoding out-of-context information about the lemma, we implemented features based on pre-trained language models to model the target word’s in-context complexity.

The age of acquisition of a word is a psycholinguistic variable concerning the age at which a word is typically learned. It correlates with other psycholinguistic variables such as familiarity, concreteness, and imageability. Existing datasets for multiple languages also include linguistic variables such as the length and the frequency of lemmas in different corpora. There are substantial sets of normative values for English, but for other languages, such as Italian, the coverage is scarce. In this paper,a set of regression experiments investigates whether it is possible to guess the age of acquisition of Italian lemmas that have not been previously rated by humans. An intrinsic evaluation is proposed, correlating estimated Italian lemmas’ AoA with English lemmas’ AoA. An extrinsic evaluation - using AoA values as features for the classification of literary excerpts labeled by age appropriateness - shows how es-sential is lexical coverage for this task.

This proposal describes a new way to visualise resources in the LREMap, a community-built repository of language resource descriptions and uses. The LREMap is represented as a force-directed graph, where resources, papers and authors are nodes. The analysis of the visual representation of the underlying graph is used to study how the community gathers around LRs and how LRs are used in research.

Poor digital representation of minority languages further prevents their usability on digital media and devices. The Digital Language Diversity Project, a three-year project funded under the Erasmus+ programme, aims at addressing the problem of low digital representation of EU regional and minority languages by giving their speakers the intellectual an practical skills to create, share, and reuse online digital content. Availability of digital content and technical support to use it are essential prerequisites for the development of language-based digital applications, which in turn can boost digital usage of these languages. In this paper we introduce the project, its aims, objectives and current activities for sustaining digital usability of minority languages through adult education.

The paper describes the multimodal enrichment of ItalWordNet action verbs’ entries by means of an automatic mapping with an ontology of action types instantiated by video scenes (ImagAct). The two resources present important differences as well as interesting complementary features, such that a mapping of these two resources can lead to a an enrichment of IWN, through the connection between synsets and videos apt to illustrate the meaning described by glosses. Here, we describe an approach inspired by ontology matching methods for the automatic mapping of ImagAct video scened onto ItalWordNet sense. The experiments described in the paper are conducted on Italian, but the same methodology can be extended to other languages for which WordNets have been created, since ImagAct is done also for English, Chinese and Spanish. This source of multimodal information can be exploited to design second language learning tools, as well as for language grounding in video action recognition and potentially for robotics.

Lexica of predicate-argument structures constitute a useful tool for several tasks in NLP. This paper describes a web-service system for automatic acquisition of verb subcategorization frames (SCFs) from parsed data in Italian. The system acquires SCFs in an unsupervised manner. We created two gold standards for the evaluation of the system, the first by mixing together information from two lexica (one manually created and the second automatically acquired) and manual exploration of corpus data and the other annotating data extracted from a specialized corpus (environmental domain). Data filtering is accomplished by means of the maximum likelihood estimate (MLE). The evaluation phase has allowed us to identify the best empirical MLE threshold for the creation of a lexicon (P=0.653, R=0.557, F1=0.601). In addition to this, we assigned to the extracted entries of the lexicon a confidence score based on the relative frequency and evaluated the extractor on domain specific data. The confidence score will allow the final user to easily select the entries of the lexicon in terms of their reliability: one of the most interesting feature of this work is the possibility the final users have to customize the results of the SCF extractor, obtaining different SCF lexica in terms of size and accuracy.

Relations among phenomena at different linguistic levels are at the essence of language properties but today we focus mostly on one specific linguistic layer at a time, without (having the possibility of) paying attention to the relations among the different layers. At the same time our efforts are too much scattered without much possibility of exploiting other people's achievements. To address the complexities hidden in multilayer interrelations even small amounts of processed data can be useful, improving the performance of complex systems. Exploiting the current trend towards sharing we want to initiate a collective movement that works towards creating synergies and harmonisation among different annotation efforts that are now dispersed. In this paper we present the general architecture of the Language Library, an initiative which is conceived as a facility for gathering and making available through simple functionalities the linguistic knowledge the field is able to produce, putting in place new ways of collaboration within the LRT community. In order to reach this goal, a first population round of the Language Library has started around a core of parallel/comparable texts that have been annotated by several contributors submitting a paper for LREC2012. The Language Library has also an ancillary aim related to language documentation and archiving and it is conceived as a theory-neutral space which allows for several language processing philosophies to coexist.

Action verbs, which are highly frequent in speech, cause disambiguation problems that are relevant to Language Technologies. This is a consequence of the peculiar way each natural language categorizes Action i.e. it is a consequence of semantic factors. Action verbs are frequently “general”, since they extend productively to actions belonging to different ontological types. Moreover, each language categorizes action in its own way and therefore the cross-linguistic reference to everyday activities is puzzling. This paper briefly sketches the IMAGACT project, which aims at setting up a cross-linguistic Ontology of Action for grounding disambiguation tasks in this crucial area of the lexicon. The project derives information on the actual variation of action verbs in English and Italian from spontaneous speech corpora, where references to action are high in frequency. Crucially it makes use of the universal language of images to identify action types, avoiding the underdeterminacy of semantic definitions. Action concept entries are implemented as prototypic scenes; this will make it easier to extend the Ontology to other languages.

Accurate and reliable documentation of Language Resources is an undisputable need: documentation is the gateway to discovery of Language Resources, a necessary step towards promoting the data economy. Language resources that are not documented virtually do not exist: for this reason every initiative able to collect and harmonise metadata about resources represents a valuable opportunity for the NLP community. In this paper we describe the LRE Map, reporting statistics on resources associated with LREC2012 papers and providing comparisons with LREC2010 data. The LRE Map, jointly launched by FLaReNet and ELRA in conjunction with the LREC 2010 Conference, is an instrument for enhancing availability of information about resources, either new or already existing ones. It wants to reinforce and facilitate the use of standards in the community. The LRE Map web interface provides the possibility of searching according to a fixed set of metadata and to view the details of extracted resources. The LRE Map is continuing to collect bottom-up input about resources from authors of other conferences through standard submission process. This will help broadening the notion of “language resources” and attract to the field neighboring disciplines that so far have been only marginally involved by the standard notion of language resources.

Sentiment Analysis (SA) and Opinion Mining (OM) have become a popular task in recent years in NLP with the development of language resources, corpora and annotation schemes. The possibility to discriminate between objective and subjective expressions contributes to the identification of a document's semantic orientation and to the detection of the opinions and sentiments expressed by the authors or attributed to other participants in the document. Subjectivity word sense disambiguation helps in this task, automatically determining which word senses in a corpus are being used subjectively and which are being used objectively. This paper reports on a methodology to assign in a semi-automatic way connotative values to eventive nouns usually labelled as neutral through syntagmatic patterns that express cause-effect relations between emotion cause events and emotion words. We have applied our method to nouns and we have been able reduce the number of OBJ polarity values associated to event noun.

In this paper we present the LREC Map of Language Resources and Tools, an innovative feature introduced with this LREC. The purpose of the Map is to shed light on the vast amount of resources and tools that represent the background of the research presented at LREC, in the attempt to fill in a gap in the community knowledge about the resources and tools that are used or created worldwide. It also aims at a change of culture in the field, actively engaging each researcher in the documentation task about resources. The Map has been developed on the basis of the information provided by LREC authors during the submission of papers to the LREC 2010 conference and the LREC workshops, and contains information about almost 2000 resources. The paper illustrates the motivation behind this initiative, its main characteristics, its relevance and future impact in the field, the metadata used to describe the resources, and finally presents some of the most relevant findings.

The field of opinion mining has emerged in recent years as an exciting challenge for computational linguistics: investigating how humans express subjective judgments through linguistic means paves the way for automatic recognition and summarization of opinionated texts, with the possibility of determining the polarities and strengths of opinions asserted. Sentiment lexicons are basic resources for investigating the orientation of a text that can be performed considering polarized words included in it but they encode the polarity of word types instead that the polarity of word tokens. The expression of an opinion through the choice of lexical items is context-sensitive and sentiment lexicons could be integrated with syntagmatic patterns that emerge as significant with statistical analyses. In this paper it will be proposed a corpus analysis of adverbially modified ambiguous (e.g. fast, rich) and objective adjectives (e.g. chemical, political) - that can be occasionally exploited to express a subjective judgments -. Comparing polarity encoded in sentiment lexicons and the results of a logistic regression analysis, the role of adverbial cues for polarity detection will be evaluated on the basis of a small sample of sentences manually annotated.