Articles

AbstractIn this paper, we present the KU x Upstage team’s submission for the Special Task on Formality Control on Spoken Language Translation, which involves translating English into four languages with diverse grammatical formality markers. Our methodology comprises two primary components: 1) a language-specific data-driven approach, and 2) the generation of …...

AbstractThis system description paper introduces the systems submitted by Xiaomi AI Lab to the three tracks of the IWSLT 2023 Evaluation Campaign, namely the offline speech translation (Offline-ST) track, the offline speech-to-speech translation (Offline-S2ST) track, and the simultaneous speech translation (Simul-ST) track. All our submissions for these three tracks only …...

AbstractIn this paper, we describe our submission to the Simultaneous Track at IWSLT 2023. This year, we continue with the successful setup from the last year, however, we adopt the latest methods that further improve the translation quality. Additionally, we propose a novel online policy for attentional encoder-decoder models. The …...

AbstractThis paper describes the submission of the UPC Machine Translation group to the IWSLT 2023 Offline Speech Translation task. Our Speech Translation systems utilize foundation models for speech (wav2vec 2.0) and text (mBART50). We incorporate a Siamese pretraining step of the speech and text encoders with CTC and Optimal Transport, …...

AbstractIn this paper, we present our submission to the IWSLT 2023 Simultaneous Speech-to-Speech Translation competition. Our participation involves three language directions: English-German, English-Chinese, and English-Japanese. Our solution is a cascaded incremental decoding system, consisting of an ASR model, an MT model, and a TTS model. By adopting the strategies used …...

AbstractIn this paper, we present our submission to the IWSLT 2023 Simultaneous Speech-to-Text Translation competition. Our participation involves three language directions: English-German, English-Chinese, and English-Japanese. Our proposed solution is a cascaded incremental decoding system that comprises an ASR model and an MT model. The ASR model is based on the …...

AbstractThis paper provides an overview of NVIDIA NeMo’s speech translation systems for the IWSLT 2023 Offline Speech Translation Task. This year, we focused on end-to-end system which capitalizes on pre-trained models and synthetic data to mitigate the problem of direct speech translation data scarcity. When trained on IWSLT 2022 constrained …...

AbstractFor the 2023 IWSLT Maltese Speech Translation Task, UM-DFKI jointly presents a cascade solution which achieves 0.6 BLEU. While this is the first time that a Maltese speech translation task has been released by IWSLT, this paper explores previous solutions for other speech translation tasks, focusing primarily on low-resource scenarios. …...

AbstractNeural language models play an increasingly central role for language processing, given their success for a range of NLP tasks. In this study, we compare some canonical strategies in language modeling for low-resource scenarios, evaluating all models by their (finetuned) performance on a POS-tagging downstream task. We work with five …...

AbstractRecent advances in natural language processing (NLP) have led to the development of large language models (LLMs) such as ChatGPT. This paper proposes a methodology for developing and evaluating ChatGPT detectors for French text, with a focus on investigating their robustness on out-of-domain data and against common attack schemes. The …...

AbstractThis paper proposes a novel approach to French patent classification leveraging data-centric strategies. We compare different approaches for the two deepest levels of the IPC hierarchy: the IPC group and subgroups. Our experiments show that while simple ensemble strategies work for shallower levels, deeper levels require more sophisticated techniques such …...

According to data from the World Meteorological Organization, the temperature on Earth has risen by nearly 1°C from 1850 to 2020, causing global climate anomalies and seriously affecting the melting of Antarctic ice and Greenland ice. In the next 100 years, if the ice completely melts, the sea level will …...

While argument mining has garnered attention over the years, its application in the financial sector remains nascent. This study presents a BERT-based ensemble learning approach tailored for sentiment analysis grounded in financial narratives, specifically focusing on unearthing arguments. For a nuanced analysis, we dissect the challenge into two pivotal subtasks …...

In this paper, we explore compact convolutional neural networks (CNNs) for end-to-end key- word spotting from raw audio to final recogni- tion results, without using traditional feature extraction based on spectrogram. Such fully CNN models reach 90.5% accuracy, an im- provement of 12.15% over traditional meth- ods with similar structures, …...

Contemporary large language mod- els (LLMs) have made significant advancements, capable of generating fluent conversations with humans and accomplishing various tasks such as programming and question answering (QA). Nevertheless, current LLMs are still faced with numerous challenges, including generating hallucinations, lacking the latest information, suffering from biases, and others. In …...

The objective of Sentence-level Revision (SentRev) is to enhance the fluency of En- glish writing; however, the performance of the three baseline methods is notably suboptimal. In this study, we propose a method utilizing neural reinforcement learning, tailored to the specific character- istics of this task, which has resulted in …...

In this study, we assess ChatGPT, OpenAI’s latest conversational chatbot and large lan- guage model (LLM), on its performance in elementary-grade arithmetic and logic prob- lems. Despite its impressive coherence in nat- ural language processing and ability to follow instructions, our findings indicate that Chat- GPT still has room for …...

Zhangzhou Southern Min is theoretically assumed to have 7320 possible syllables but more than 70% of them are not attested in the empirical data, implying that substantial constraints have been governing the segmental sequencing and segmental-suprasegmental alignment. This study explores phonotactic constraints on syllable onsets. It addresses two important issues …...

Automatic generation of questions about the given context is useful for the adaptation of question-answering systems or to support edu- cation. We trained and evaluated a model that generates a question in the Slovak language. We have designed an automatic metric where an additional question-answering model is used to evaluate …...

This paper introduces the Cross-lingual Fact Extraction and VERification (XFEVER) dataset designed for benchmarking the fact ver- ification models across different languages. We constructed it by translating the claim and ev- idence texts of the Fact Extraction and VERi- fication (FEVER) dataset released by Thorne et al. (2018) into six …...