Spain

This paper describes the TRAVIS system built for the PARSEME Shared Task 2020 on semi-supervised identification of verbal multiword expressions. TRAVIS is a fully feature-independent model, relying only on the contextual embeddings. We have participated with two variants of TRAVIS, TRAVIS-multi and TRAVIS-mono, where the former employs multilingual contextual embeddings and the latter uses monolingual ones. Our systems are ranked second and third among seven submissions in the open track, respectively. A thorough comparison of both systems on eight languages reveals that despite the strong performance of multilingual contextual embeddings across all languages, language-specific contextual embeddings exhibit much better generalization capabilities.


COLING 2020

How good is (m)BERT at seeing the unseen?


stages 

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

First established in 1965, the biennial COLING conference is held in diverse parts of the globe and attracts participants from both top-ranked research centers and emerging countries. Today, the most important developments in our field are taking place not only in universities and academic research institutes, but also in industrial research departments and in technological startups. COLING conferences provide opportunities for all these communities to showcase their exciting developments.

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

technical paper

This paper presents our work on the refinement and improvement of the Serbian language part of Hurtlex, a multilingual lexicon of words to hurt. We pay special attention to adding Multi-word expressions that can be seen as abusive, as such lexical entries are very important in obtaining good results in a plethora of abusive language detection tasks. We use Serbian morphological dictionaries as a basis for data cleaning and MWE dictionary creation. A connection to other lexical and semantic resources in Serbian is outlined and building of abusive language detection systems based on that connection is foreseen.

Multi-word Expressions for Abusive Speech Detection in Serbian

This paper describes a semi-supervised system that jointly learns verbal multiword expressions (VMWEs) and dependency parse trees as an auxiliary task. The model benefits from pre-trained multilingual BERT. BERT hidden layers are shared among the two tasks and we introduce an additional linear layer to retrieve VMWE tags. The dependency parse tree prediction is modelled by a linear layer and a bilinear one plus a tree CRF on top of BERT. The system has participated in the open track of the PARSEME shared task 2020 and ranked first in terms of F1-score in identifying unseen VMWEs as well as VMWEs in general, averaged across all 14 languages.


Capturing Unseen Multiword Expressions Using Multi-task Learning and Pre-trained Masked Language Models

The majority of multiword expressions can be interpreted as figuratively or literally in different contexts which pose challenges in a number of downstream tasks. Most previous work deals with this ambiguity following the observation that MWEs with different usages occur in distinctly different contexts. Following this insight, we explore the usefulness of contextual embeddings by means of both supervised and unsupervised classification. The results show that in the supervised setting, the state-of-the-art can be substantially improved for all expressions in the experiments. The unsupervised classification, similarly, yields very impressive results, comparing favorably to the supervised classifier for the majority of the expressions. We also show that multilingual contextual embeddings can also be employed for this task without leading to any significant loss in performance; hence, the proposed methodology has the potential to be extended to a number of languages.


Disambiguation of Potentially Idiomatic Expressions with Contextual Embeddings

In this presentation, I will provide an overview over the paper MultiVitaminBooster at PARSEME Shared Task 2020: Combining Window- and Dependency-Based Features with Multilingual Contextualized Word Embeddings for VMWE detection. In our approch to the shared task, we interpreted detecting verbal multiword expressions as a token classification task aiming to decide wether a given word is part of a VMWE. Our systems achieved subpar results which I discuss, as well.

MultiVitaminBooster at PARSEME Shared Task 2020

This paper describes a manually annotated corpus of verbal multi-word expressions in Polish. It is among the 4 biggest datasets in release 1.2 of the PARSEME multiligual corpus. We describe the data sources, as well as the annotation process and its outcomes. We also present interesting phenomena encountered during the annotation task and put forward enhancements for the
PARSEME annotation guidelines.

Polish corpus of verbal multiword expressions

The multiword adverbials N-BY-N and NUM-BY-NUM (as English brick by brick and one by one, respectively) are event modifiers which require temporal sequencing of the event they modify into a linearly ordered series of sub-events. Previous studies unified these two constructions under a single semantic analysis and adopted either a mereological or a scalar approach. However, based on a corpus study examining new Slavic language material and a binomial logistic regression modelling of the manually annotated data, we argue that two separate analyses are needed to account for these constructions, namely a scalar analysis for the N-BY-N construction and a mereological one for the NUM-BY-NUM construction.

Scalar vs. mereological conceptualizations of the N-BY-N and NUM-BY-NUM adverbials

We present edition 1.2 of the PARSEME shared task on identification of verbal multiword expressions (VMWEs). Lessons learned from previous editions indicate that VMWEs have low ambiguity, and that the major challenge lies in identifying test instances never seen in the training data. Therefore, this edition focuses on unseen VMWEs. We have split annotated corpora so that the test corpora contain around 300 unseen VMWEs, and we provide non-annotated raw corpora to be used by complementary discovery methods. We released annotated and raw corpora in 14 languages, and this semi-supervised challenge attracted 7 teams who submitted 9 system results. This paper describes the effort of corpus creation, the task design, and the results obtained by the participating systems, especially their performance on unseen expressions.

Edition 1.2 of the PARSEME Shared Task on Semi-supervised Identification of Verbal Multiword Expressions

In this presentation I describe the automatic construction of FinnMWE: a lexicon of Finnish Multi-Word Expressions (MWEs). In focus are syntactic frames: verbal constructions with arguments in a particular morphological form. The verbal frames are automatically extracted from FinnWordNet and English Wiktionary. The resulting lexicon interoperates with dependency tree searching software so that instances can be quickly found within dependency treebanks. I close by describing some experiments comparing FinnMWE with Finnish PropBank.

Filling the ___-s in Finnish MWE lexicons

We introduce what is to the best of our knowledge a new task in natural language processing: measuring alignment to authoritarian state media. We operationalize alignment in terms of sociological definitions of media bias. We take as a case study the alignment of four Taiwanese media outlets to the Chinese Communist Party state media. We present the results of an initial investigation using the frequency of words in psychologically meaningful categories. Our findings suggest that the chosen word categories correlate with framing choices. We develop a calculation method that yields reasonable results for measuring alignment, agreeing well with the known labels. We confirm that our method does capture event selection bias, but whether it captures framing bias requires further investigation.

Measuring Alignment to Authoritarian State Media as Framing Bias

The explosive growth and popularity of Social Media has revolutionised the way we communicate and collaborate. Unfortunately, this same ease of accessing and sharing information has led
to an explosion of misinformation and propaganda. Given that stance detection can significantly
aid in veracity prediction, this work focuses on boosting automated stance detection, a task on
which pre-trained models have been extremely successful on, as on several other tasks. This
work shows that the task of stance detection can benefit from feature based information, especially on certain under performing classes, however, integrating such features into pre-trained
models using ensembling is challenging. We propose a novel architecture for integrating features
with pre-trained models that address these challenges and test our method on the RumourEval
2019 dataset. This method achieves state-of-the-art results with an F1-score of 63.94 on the test
set.

How good is (m)BERT at seeing the unseen?

Downloads

Next from COLING 2020

Multi-word Expressions for Abusive Speech Detection in Serbian

Similar lecture

Would you describe a leopard as yellow? Evaluating crowd annotations with justified and informative disagreement

How good is (m)BERT at seeing the unseen?

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from COLING 2020

Multi-word Expressions for Abusive Speech Detection in Serbian

Similar lecture

Would you describe a leopard as yellow? Evaluating crowd annotations with justified and informative disagreement

Downloads