Articles

AbstractAutomatic translations with critical errors may lead to misinterpretations and pose several risks for the user. As such, it is important that Machine Translation (MT) Evaluation systems are robust to these errors in order to increase the reliability and safety of Machine Translation systems. Here we introduce SMAUG a novel …...

AbstractThe most widely used metrics for machine translation tackle sentence-level evaluation. However, at least for professional domains such as legal texts, it is crucial to measure the consistency of the translation of the terms throughout the whole text. This paper introduces an automated metric for the term consistency evaluation in …...

Chinese word segmentation has entered the deep learning era which greatly reduces the hassle of feature engineering. Recently, some researchers attempted to treat it as character- level translation, which further simplified model designing, but there is a performance gap between the translation-based approach and other methods. This motivates our work, …...

We study the information retrieval task to identify the relevant law articles for a query on a legal issue in when the legal system in question is statute law. In recent years, the mainstream approach has been to calculate the similarity between the query and each article using pre-trained language …...

Automatic Minuting consists of automati- cally creating minutes from multiparty meet- ing transcripts. In this paper, we solve two rel- evant problems of this domain (1) given a pair of meeting transcript and minute, the task is to identify whether the minutes belongs to the transcript. (2) given a pair …...

An enormous amount of research has been undertaken to overcome the severe impact of COVID-19 pandemic. These scientific findings are being reported in biomedical literature at a significant rate of 10,000 articles/month. In this paper, we tackle automated topic annotation for COVID-19 literature using SPECTER, Bioformer, and PubMedBERT embeddings using …...

In this paper, we present an approach and im- pact of isometric neural machine translation on the automatic dubbing process. The length of generated isometric translated sentences ranges within a ±10% of the source text. We propose a hierarchical and multilingual approach toward generating isometric translation via publicly available MUST-C, …...

Paraphrase detection allows identifying the degree of likelihood between source and suspect sentences. It is a critical machine learning problem in computational linguistics. This is due to the expression variability and ambiguities especially in Arabic language. Previous neural models have yielded promising results, but are computationally expensive. They cannot directly …...

In this paper, we present a pipeline for auto- matic minuting. This pipeline is an end-to-end system for minuting the multiparty dialogues of meetings. It provides multilingual com- munication and collaboration, with a specific focus on Natural Language Processing (NLP) technologies: Automatic Speech Recognition (ASR), Machine Translation (MT), Automatic Minuting …...

This study investigated the do-constructions in Chinese, Russian, and Czech, a predicate- argument structure comprised of the light verb ‘to do’ - zuò in Chinese, delat' in Russian, and dělat in Czech - and a verbal noun as the head in the accusative role, considering the linguistic traits and pragmatic …...

Community Question Answering (CQA) fo- rums are a popular place for open-ended question-answers and discussions by the pub- lic. Popular question answering sites have become a one-stop solution for the diverse information-seeking needs of the netizens. However, it is quite common that users some- times ask the same question which …...

We present the PagkataoKo Dataset, a new dataset for Filipino Automatic Personal- ity Recognition (APR) containing demo- graphic, personality trait, and social media data sourced from 3,128 Filipino Instagram and/or Twitter users. As APR is focused on processing an individual’s observable ac- tions, we improve upon the previous Fil- ipino …...

This paper investigates deverbal com- pounds in Japanese. Previous stud- ies have discussed the classification of deverbal compounds, which can be classified according to their structure. Some former investigations discovered some generalizations on accents, ren- daku, and direct verbalization. Here I propose a generalization on direct ver- balization and deaccentuation, …...

As Natural Language Processing is evolving rapidly, it is used to analyze domain spe- cific large text corpora. Applying Natural Language Processing in a domain with un- common vocabulary and unique semantics requires techniques specifically designed for that domain. The legal domain is such an area with unique vocabulary and …...

Within the figurative repertoire of the genre of wine reviews, anthropomorphic metaphor is the most recurring pattern in many languages. However, few studies studied the metaphors in wine reviews in the Chinese language nor focused on the synesthetic metaphors as well as the synesthetic directionality in the wine discourse. This …...

The paper proposes “Critical Presuppositions-To-Theory” (C-PRETTY) research as a new form of qualitative inquiry due to the realized challenges of grounded theory and the seemingly barren domain of theory building. The C-PRETTY serves as a special type of qualitative inquiry that focuses on critical presuppositional framework and critical presuppositions as …...

Most Word-Sense Disambiguation (WSD) systems rely on machine learning approaches that require large-scale corpora for effective training. So, the quality of a WSD system degrades when trained in a low-resource lan- guage such as Arabic. To improve WSD, we design a novel data augmentation technique by properly fine-tuning GPT-2 to …...

While prospect theory (Kahneman and Tver- sky, 1979) has been widely used as a de- scriptive theory to explain various phenom- ena such as insurance and the relation be- tween spending and saving, no studies have been found to look at prospect theory from linguistic prospective to investigate near syn- …...

This study is unique because it focuses on language consultants’ perceptions of their life satisfaction. This paper looks into their well-being and how it reflects their culture. The questions addressed were, "Are you happy with your life right now?" and "How can you ensure yours and your children's well-being?" After …...

Saji et al. (2021) integrated a neural-based NLI model and a symbolic one into a framework to get the best of both worlds. This framework is based on a tableau method, which is a proof system for formal logic; however, it has a re- maining issue that its theoretical limitations …...