Search

Starting in 2003 when the first MWE workshop was held with ACL in Sapporo, Japan, this year, the joint workshop of MWE-UD co-located with the LREC-COLING 2024 conference marked the 20th anniversary of MWE workshop events over the past nearly two decades. Standing at this milestone, we look back to this workshop series and summarise the research topics and methodologies researchers have carried out over the years. We also discuss the current challenges that we are facing and the broader impacts/synergies of MWE research within the CL and NLP fields. Finally, we give future research perspectives. We hope this position paper can help researchers, students, and industrial practitioners interested in MWE get a brief but easy understanding of its history, current, and possible future., Comment: ongoing work, position paper, 6 pages

Current open-domain neural semantics parsers show impressive performance. However, closer inspection of the symbolic meaning representations they produce reveals significant weaknesses: sometimes they tend to merely copy character sequences from the source text to form symbolic concepts, defaulting to the most frequent word sense based in the training distribution. By leveraging the hierarchical structure of a lexical ontology, we introduce a novel compositional symbolic representation for concepts based on their position in the taxonomical hierarchy. This representation provides richer semantic information and enhances interpretability. We introduce a neural "taxonomical" semantic parser to utilize this new representation system of predicates, and compare it with a standard neural semantic parser trained on the traditional meaning representation format, employing a novel challenge set and evaluation metric for evaluation. Our experimental findings demonstrate that the taxonomical model, trained on much richer and complex meaning representations, is slightly subordinate in performance to the traditional model using the standard metrics for evaluation, but outperforms it when dealing with out-of-vocabulary concepts. This finding is encouraging for research in computational semantics that aims to combine data-driven distributional meanings with knowledge-based symbolic representations., Comment: This manuscript has been accepted by Computational Linguistics journal on 2024-09-07

Three main topics were raised in this discussion session, which took place on the 19th of June at the NumHyp-2015 meeting: nonlinear resonance for 1D systems of balance laws, dispersive extensions of standard hyperbolic conservation laws, and the validation of weakly dispersive shallow water wave models. An introductory overview with many bibliographic references is provided for all these topics. Based on kinetic formulation, a numerical strategy that can overcome resonance issues is presented, and a well-balanced (WB) technique for Vlasov-Fokker-Planck equations is outlined. This WB scheme relies on the spectral representation of stationary solutions., Comment: 25 pages, 7 figures, 1 table, 83 references

Different ways of linguistically expressing the same real-world event can lead to different perceptions of what happened. Previous work has shown that different descriptions of gender-based violence (GBV) influence the reader's perception of who is to blame for the violence, possibly reinforcing stereotypes which see the victim as partly responsible, too. As a contribution to raise awareness on perspective-based writing, and to facilitate access to alternative perspectives, we introduce the novel task of automatically rewriting GBV descriptions as a means to alter the perceived level of responsibility on the perpetrator. We present a quasi-parallel dataset of sentences with low and high perceived responsibility levels for the perpetrator, and experiment with unsupervised (mBART-based), zero-shot and few-shot (GPT3-based) methods for rewriting sentences. We evaluate our models using a questionnaire study and a suite of automatic metrics., Comment: Accepted for publication in Findings of ACL 2023

Different linguistic expressions can conceptualize the same event from different viewpoints by emphasizing certain participants over others. Here, we investigate a case where this has social consequences: how do linguistic expressions of gender-based violence (GBV) influence who we perceive as responsible? We build on previous psycholinguistic research in this area and conduct a large-scale perception survey of GBV descriptions automatically extracted from a corpus of Italian newspapers. We then train regression models that predict the salience of GBV participants with respect to different dimensions of perceived responsibility. Our best model (fine-tuned BERT) shows solid overall performance, with large differences between dimensions and participants: salient _focus_ is more predictable than salient _blame_, and perpetrators' salience is more predictable than victims' salience. Experiments with ridge regression models using different representations show that features based on linguistic theory similarly to word-based features. Overall, we show that different linguistic choices do trigger different perceptions of responsibility, and that such perceptions can be modelled automatically. This work can be a core instrument to raise awareness of the consequences of different perspectivizations in the general public and in news producers alike., Comment: Accepted for publication at AACL-IJCNLP 2022

Massively multilingual models are promising for transfer learning across tasks and languages. However, existing methods are unable to fully leverage training data when it is available in different task-language combinations. To exploit such heterogeneous supervision, we propose Hyper-X, a single hypernetwork that unifies multi-task and multilingual learning with efficient adaptation. This model generates weights for adapter modules conditioned on both tasks and language embeddings. By learning to combine task and language-specific knowledge, our model enables zero-shot transfer for unseen languages and task-language combinations. Our experiments on a diverse set of languages demonstrate that Hyper-X achieves the best or competitive gain when a mixture of multiple resources is available, while being on par with strong baselines in the standard scenario. Hyper-X is also considerably more efficient in terms of parameters and resources compared to methods that train separate adapters. Finally, Hyper-X consistently produces strong results in few-shot scenarios for new languages, showing the versatility of our approach beyond zero-shot transfer., Comment: Accepted at EMNLP 2022 (Main Conference)

SOCIOFILLMORE is a multilingual tool which helps to bring to the fore the focus or the perspective that a text expresses in depicting an event. Our tool, whose rationale we also support through a large collection of human judgements, is theoretically grounded on frame semantics and cognitive linguistics, and implemented using the LOME frame semantic parser. We describe SOCIOFILLMORE's development and functionalities, show how non-NLP researchers can easily interact with the tool, and present some example case studies which are already incorporated in the system, together with the kind of analysis that can be visualised., Comment: Accepted for Demo Session at ACL 2022

This technical report introduces an adapted version of the LOME frame semantic parsing model (Xia et al., EACL 2021) which is capable of automatically annotating texts according to the "Kicktionary" domain-specific framenet resource. Several methods for training a model even with limited available training data are proposed. While there are some challenges for evaluation related to the nature of the available annotations, preliminary results are very promising, with the best model reaching F1-scores of 0.83 (frame prediction) and 0.81 (semantic role prediction).

We present a lemmatizer/POS-tagger/dependency parser for West Frisian using a corpus of 44,714 words in 3,126 sentences that were annotated according to the guidelines of Universal Dependency version 2. POS tags were assigned to words by using a Dutch POS tagger that was applied to a literal word-by-word translation, or to sentences of a Dutch parallel text. Best results were obtained when using literal translations that were created by using the Frisian translation program Oersetter. Morphologic and syntactic annotations were generated on the basis of a literal Dutch translation as well. The performance of the lemmatizer/tagger/annotator when it was trained using default parameters was compared to the performance that was obtained when using the parameter values that were used for training the LassySmall UD 2.5 corpus. A significant improvement was found for `lemma'. The Frisian lemmatizer/PoS tagger/dependency parser is released as a web app and as a web service., Comment: 6 pages, 2 figures, 6 tables

Recent advances in multilingual dependency parsing have brought the idea of a truly universal parser closer to reality. However, cross-language interference and restrained model capacity remain major obstacles. To address this, we propose a novel multilingual task adaptation approach based on contextual parameter generation and adapter modules. This approach enables to learn adapters via language embeddings while sharing model parameters across languages. It also allows for an easy but effective integration of existing linguistic typology features into the parsing network. The resulting parser, UDapter, outperforms strong monolingual and multilingual baselines on the majority of both high-resource and low-resource (zero-shot) languages, showing the success of the proposed adaptation approach. Our in-depth analyses show that soft parameter sharing via typological features is key to this success., Comment: In EMNLP 2020

Programming languages, libraries, and development tools have transformed the application development processes for mobile computing and machine learning. This paper introduces the CyPhyHouse - a toolchain that aims to provide similar programming, debugging, and deployment benefits for distributed mobile robotic applications. Users can develop hardware-agnostic, distributed applications using the high-level, event driven Koord programming language, without requiring expertise in controller design or distributed network protocols. The modular, platform-independent middleware of CyPhyHouse implements these functionalities using standard algorithms for path planning (RRT), control (MPC), mutual exclusion, etc. A high-fidelity, scalable, multi-threaded simulator for Koord applications is developed to simulate the same application code for dozens of heterogeneous agents. The same compiled code can also be deployed on heterogeneous mobile platforms. The effectiveness of CyPhyHouse in improving the design cycles is explicitly illustrated in a robotic testbed through development, simulation, and deployment of a distributed task allocation application on in-house ground and aerial vehicles.

The present study proposes an annotation scheme for classifying the content and discourse contribution of question-answer pairs. We propose detailed guidelines for using the scheme and apply them to dialogues in English, Spanish, and Dutch. Finally, we report on initial machine learning experiments for automatic annotation.

We investigate numerically a model consisting in a kinetic equation for the biased motion of bacteria following a run-and-tumble process, coupled with two reaction-diffusion equations for chemical signals. This model exhibits asymptotic propagation at a constant speed. In particular, it admits travelling wave solutions. To capture this propagation, we propose a well-balanced numerical scheme based on Case's elementary solutions for the kinetic equation, and L-splines for the parabolic equations. We use this scheme to explore the Cauchy problem for various parameters. Some examples far from the diffusive regime lead to the coexistence of two waves travelling at different speeds. Numerical tests support the hypothesis that they are both locally asymptotically stable. Interestingly, the exploration of the bifurcation diagram raises counter-intuitive features.

The existence of travelling waves for a coupled system of hyperbolic/ parabolic equations is established in the case of a finite number of velocities in the kinetic equation. This finds application in collective motion of chemotactic bacteria. The analysis builds on the previous work by the first author (arXiv:1607.00429) in the case of a continuum of velocities. Here, the proof is specific to the discrete setting, based on the decomposition of the population density in special Case's modes. Some counter-intuitive results are discussed numerically, including the coexistence of several travelling waves for some sets of parameters, as well as the possible non-existence of travelling waves.

This paper is concerned with diffusive approximations of peculiar numerical schemes for several linear (or weakly nonlinear) kinetic models which are motivated by wide-range applications, including radiative transfer or neutron transport, run-and-tumble models of chemotaxis dynamics, and Vlasov-Fokker-Planck plasma modeling. The well-balanced method applied to such kinetic equations leads to time-marching schemes involving a '' scattering S-matrix '' , itself derived from a normal modes decomposition of the stationary solution. One common feature these models share is the type of diffusive approximation: their macroscopic densities solve drift-diffusion systems, for which a distinguished numerical scheme is Il'in/Scharfetter-Gummel's '' exponential fitting '' discretization. We prove that the well-balanced schemes relax, within a parabolic rescaling, towards the Il'in exponential-fitting discretization by means of an appropriate decomposition of the S-matrix. This is the so-called asymptotic preserving (or uniformly accurate) property.

The purpose of this study is to contribute to the limited research base on the complex relationships between classroom supports and language development by addressing two research aims. The first aim is to determine the unique association between relational support and and instructional support and preschoolers' language development. The second aim is to determine whether this association is moderated by initial language ability. This second aim expands previous research by examining whether classroom supports may be particularly protective for children who begin preschool with low language skills and are at risk of difficulty acquiring literacy. (Contains 1 table and 2 figures.)