Croatia

This paper describes the process of annotation of 996 lexical bundles (LB) assigned to 39 different discourse functions in a Spanish academic corpus. The purpose of the annotation is to obtain a new Spanish gold-standard corpus of 1,800,000 words useful for training and evaluating computational models that are capable of identifying automatically LBs for each context in new corpora, as well as for linguistic analysis about the role of LBs in academic discourse. The annotation process revealed that correspondence between LBs and discourse functions is not biunivocal and that the degree of ambiguity is high, so linguists’ contribution has been essential for improving the automatic assignation of tags.

EACL 2023

Annotation of lexical bundles with discourse functions in a Spanish academic corpus

academic discourse

lexical bundles

collocations

annotation

workshop paper

### Welcome to the 17th Conference of the European Chapter of the Association for Computational Linguistics (EACL) 
Continuing its mission of expanding and involving the science community of all European countries, EACL had selected the Ukrainian community for the 16th EACL, which took place online due to the COVID pandemic. Unfortunately, the ongoing war made the organisation in Kyiv impossible. Considering the importance of physical interaction among researchers, especially after the restrictions imposed by the COVID pandemic, in addition to an online mode, the conference will be held in Dubrovnik, Croatia, from 2 to 6 of May, 2023. The original aim of strengthening the connection with the Ukrainian community will not change as our program will feature a dedicated session and a workshop to highlight work on Ukrainian language technologies. As the flagship European conference in the field of computational linguistics, EACL welcomes European and international researchers covering a broad spectrum of research areas that are concerned with computational approaches to natural language.

You need to register for the conference in order to access this site. Please visit https://2023.eacl.org/registration for more information.

As the flagship European conference in the field of computational linguistics, EACL welcomes European and international researchers covering a broad spectrum of research areas that are concerned with computational approaches to natural language.

We report on work in progress dealing with the
automated generation of pronunciation infor-
mation for English multiword terms (MWTs)
in Wiktionary, combining information avail-
able for their single components. We describe
the issues we were encountering, the build-
ing of an evaluation dataset, and our teaming
with the DBnary resource maintainer. Our
approach shows potential for automatically
adding morphosyntactic and semantic informa-
tion to the components of such MWTs.

Enriching Multiword Terms in Wiktionary with Pronunciation Information

The importance of multiword expressions (MWEs) for language learning is well established. While MWE research has been evaluated on various downstream tasks such as syntactic parsing and machine translation, its applications in computer-assisted language learning has been less explored. This paper investigates the selection of MWEs for graded vocabulary lists. Widely used by language teachers and students, these lists recommend a language acquisition sequence to optimize learning efficiency. We automatically generate these lists using difficulty-graded corpora and MWEs extracted based on semantic compositionality. We evaluate these lists on their ability to facilitate text comprehension for learners. Experimental results show that our proposed method generates higher-quality lists than baselines using collocation measures.

Automatic Generation of Vocabulary Lists with Multiword Expressions

Construction Grammar (CxG) is a paradigm from cognitive linguistics emphasising the connection between syntax and semantics. Rather than rules that operate on lexical items, it posits constructions as the central building blocks of language, i.e., linguistic units of different granularity that combine syntax and semantics. As a first step towards assessing the compatibility of CxG with the syntactic and semantic knowledge demonstrated by state-of-the-art pretrained language models (PLMs), we present an investigation of their capability to classify and understand one of the most commonly studied constructions, the English comparative correlative (CC). We conduct experiments examining the classification accuracy of a syntactic probe on the one hand and the models' behaviour in a semantic application task on the other, with BERT, RoBERTa, and DeBERTa as the example PLMs. Our results show that all three investigated PLMs are able to recognise the structure of the CC but fail to use its meaning. While human-like performance of PLMs on many NLP tasks has been alleged, this indicates that PLMs still suffer from substantial shortcomings in central domains of linguistic knowledge.

The Better Your Syntax, the Better Your Semantics? Probing Pretrained Language Models for the English Comparative Correlative

Pre-trained neural masked language models are often used for predicting a replacement token for a given sequence position, in a cloze-like task. However, this usage is restricted to predicting a single token, from a relatively small pre-trained vocabulary. Recent Sequence2Sequence pre-trained LMs like T5 do allow predicting multi-token completions, but are more expensive to train and run. We show that pre-trained masked language models can be adapted to produce multi-token completions, with only a modest addition to their parameter count. We propose two simple adap- tation approaches, trading parameter counts for accuracy. The first method generates multi- token completions from a conditioned RNN. It has a very low parameter count and achieves competitive results. The second method is even simpler: it adds items corresponding to multi-token units to the output prediction ma- trix. While being higher in parameter count than the RNN method, it also surpasses current state-of-the-art multi-token completion mod- els, including T5-3B, while being significantly more parameter efficient. We demonstrate that our approach is flexible to different vocabularies and domains and can effectively leverage existing pre-trained models available in different domains. Finally, a human evaluation further validates our results and shows that our solution regularly provides valid completions, as well as reasonable correctness for factual-sentence completions.

Simple and Effective Multi-Token Completion from Masked Language Models

One of the major challenges that underrepresented and endangered language communities face in language technology is the lack or paucity of language data. This is also the case of the Southern varieties of the Kurdish and Laki languages for which very limited resources are available with insubstantial progress in tools. To tackle this, we provide a few approaches that rely on the content of local news websites, a local radio station that broadcasts content in Southern Kurdish and fieldwork for Laki. In this paper, we describe some of the challenges of such under-represented
languages, particularly in writing and standardization, and also, in retrieving sources of data and retro-digitizing handwritten content to create a corpus for Southern Kurdish and Laki. In addition, we study the task of language identification in light of the other variants of Kurdish and Zaza-Gorani languages.

Approaches to Corpus Creation for Low-Resource Language Technology: the Case of Southern Kurdish and Laki

Experiments to fine-tune large multilingual models with limited data from a specific domain or setting has potential to improve automatic speech recognition (ASR) outcomes. This paper reports on the use of the Elpis ASR pipeline to fine-tune two pre-trained base models, Wav2Vec2-XLSR-53 and Wav2Vec2- Large-XLSR-Indonesian, with various mixes of data from 3 YouTube channels teaching Indonesian with English as the language of instruction. We discuss our results inferring new lesson audio (22-46% word error rate) in the context of speeding data collection in diverse and specialised settings. This study is an example of how ASR can be used to accelerate natural language research, expanding ethically sourced data in low-resource settings.

Automated speech recognition of Indonesian-English language lessons on YouTube using transfer learning

Linguistic variability poses a challenge to many modern ASR systems, particularly Dialectical Arabic (DA) ASR systems dealing with low-resource dialects and resulting morphological and orthographic variations in text and speech. Traditional evaluation metrics such as the word error rate (WER) inadequately capture these complexities, leading to an incomplete assessment of DA ASR performance. We propose AraDiaWER, an ASR evaluation metric for Dialectical Arabic (DA) speech recognition systems, focused on the Egyptian dialect. AraDiaWER uses language model embeddings for the syntactic and semantic aspects of ASR errors to identify their root cause, not captured by traditional WER. MiniLM generates the semantic score, capturing contextual differences between reference and predicted transcripts. CAMeLBERT-Mix assigns morphological and lexical tags using a fuzzy matching algorithm to calculate the syntactic score. Our experiments validate the effectiveness of AraDiaWER. By incorporating language model embeddings, AraDiaWER enables a more interpretable evaluation, allowing us to improve DA ASR systems. We position the proposed metric as a complementary tool to WER, capturing syntactic and semantic features not represented by WER. Additionally, we use UMAP analysis to observe the quality of ASR embeddings in the proposed evaluation framework.

AraDiaWER: An Explainable Metric For Dialectical Arabic ASR

This study investigates the clustering of words into Part-of-Speech (POS) classes in Kolyma Yukaghir. In grammatical descriptions, lexical items are assigned to POS classes based on their morphological paradigms. Discursively, however, these classes share a fair amount of morphology. In this study, we turn to POS induction to evaluate if classes based on quantification of the distributions in which roots and affixes are used can be useful for language description purposes, and, if so, what those classes might be. We qualitatively compare clusters of roots and affixes based on four different definitions of their distributions. The results show that clustering is more reliable for words that typically bear more morphology. Additionally, the results suggest that the number of POS classes in Kolyma Yukaghir might be smaller than stated in current descriptions. This study thus demonstrates how unsupervised learning methods can provide insights for language description, particularly for highly inflectional languages.

Unsupervised part-of-speech induction for language description: Modeling documentation materials in Kolyma Yukaghir

The Speech Database (Speech-DB: URL: https://speech-db.altlab.app) is an on-
line platform for language documentation, written and spoken language validation, and speech exploration; its code-base is available as open source. In its current state, Speech-DB has expanded to contain content for several Indigenous languages spoken in Western Canada, having started with audio for the dialect of Plains Cree spoken in Maskwacîs, Alberta, Canada. Currently, it is used primarily for validation and storage. It can be accessed by anyone with an internet connection in six levels of access rights. What follows is the rationale for the development of speech-DB, an exploration of its features, and a description of usage scenarios, as well as initial user feedback on the application.

Speech Database (Speech-DB) – An on-line platform for storing, validating, searching, and recording spoken language data

Automatic Speech Recognition (ASR) models can aid field linguists by facilitating the creation of text corpora from oral material. Training ASR systems for low-resource languages can be a challenging task not only due to lack of resources but also due to the work required for the preparation of a training dataset. We present a pipeline for data processing and ASR model training for low-resourced languages, based on the language family. As a case study, we collected recordings of Pomak, an endangered South East Slavic language variety spoken in Greece. Using the proposed pipeline, we trained the first Pomak ASR model.

Downloads

Next from EACL 2023

Enriching Multiword Terms in Wiktionary with Pronunciation Information