Papers by Serge Sharoff
Enhancing Image-to-Text Generation in Radiology Reports through Cross-modal Multi-Task Learning (2024.lrec-main)
Copied to clipboard
| Challenge: | Image-to-text generation relies on independent models for image understanding and natural language generation, which often exhibit a semantic gap between visual and textual information. |
| Approach: | They propose a multi-task learning framework to leverage both visual and non-imaging data for generating radiology reports. |
| Outcome: | The proposed framework improves performance over single-task baselines across language generation metrics and mitigates overfitting in auxiliary tasks. |
Recognizing Semantic Relations by Combining Transformers and Fully Connected Models (2020.lrec-1)
Copied to clipboard
| Challenge: | Current approaches to recognizing semantic relations between words are limited and require a word-path model. |
| Approach: | They propose a distributional approach that is based on an attention-based transformer and a word path model that combines useful properties of a convolutional network with a fully connected language model. |
| Outcome: | The proposed model outperforms the state-of-the-art in terms of performance and data sources. |
A Multilingual Dataset for Evaluating Parallel Sentence Extraction from Comparable Corpora (L18-1)
Copied to clipboard
| Challenge: | BUCC Shared Task aims to extract parallel sentences from comparable corporad . resulting corpus contains about 3.5 million distinct sentences in english, french, german, Russian, and Chinese . |
| Approach: | They present challenges faced to build a parallel sentences dataset from comparable corporad . they emphasize issues faced to include Chinese as one of the languages . |
| Outcome: | The 2017 BUCC Shared Task was a first for this task . the dataset contains 3.5 million sentences in English, French, German, Russian, and Chinese . |
Investigating the Influence of Bilingual MWU on Trainee Translation Quality (L18-1)
Copied to clipboard
| Challenge: | a method for automatic extraction of bilingual multiword units (BMWUs) from a parallel corpus has been shown to be useful for estimating human translation quality. |
| Approach: | They applied a method for automatic extraction of bilingual multiword units from a parallel corpus in order to investigate their contribution to translation quality in terms of adequacy and fluency. |
| Outcome: | The method is based on generalized additive modelling and it shows that normalized BMWU ratios can be useful for estimating human translation quality. |
BERT Goes Off-Topic: Investigating the Domain Transfer Challenge using Genre Classification (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Pretrained language models have improved performance of text classification tasks, but they still suffer from spurious domain-specific clues. |
| Approach: | They propose a method to augment pretrained language models by generating texts in any desired genre and on any desired topic. |
| Outcome: | The proposed method improves on genre classification tasks while showing no improvement for other topics. |
Multimodal Pipeline for Collection of Misinformation Data from Telegram (2022.lrec-1)
Copied to clipboard
| Challenge: | a large portion of misinformation is spread via multimodal means, such as images and videos . a new pipeline for collecting misinformation from Telegram allows us to collect a greater variety of mis-information examples . |
| Approach: | They propose to use AI to understand misinformation flow across social media platforms . they collect data from Telegram groups which promote COVID-19 misinformation . |
| Outcome: | The proposed dataset contains almost one million messages from 2k different public channels related to spreading COVID-19 misinformation. |
Know thy Corpus! Robust Methods for Digital Curation of Web corpora (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing methods for estimating the lexicon of Web corpora have not been used to train pre-trained models. |
| Approach: | They propose a framework for digital curation of Web corpora to provide robust estimation of their parameters. |
| Outcome: | The proposed framework provides robust estimation of Web corpora's composition and lexicon . the proposed framework is similar to the BNC and ELMO models, but lacks curated categories . |
Estimating Confidence of Predictions of Individual Classifiers and TheirEnsembles for the Genre Classification Task (2022.lrec-1)
Copied to clipboard
| Challenge: | Genre identification is a kind of non-topic text classification. genre is defined as a functional space. |
| Approach: | They propose to use SOTA to identify genres in non-topic texts . genres are functional and cannot be expressed just by some keywords . |
| Outcome: | The proposed models show that they perform better than their individual models in large datasets. |
Controlling Out-of-Domain Gaps in LLMs for Genre Classification and Generated Text Detection (2025.coling-main)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models (LLMs) have pushed the boundaries of natural language processing, but their consistency is often limited when applied to unfamiliar domains. |
| Approach: | They propose a method that controls which predictive indicators are used and which are excluded during classification. |
| Outcome: | The proposed method reduces the OOD gap by up to 20 percentage points in a few-shot setup. |
Applying Natural Annotation and Curriculum Learning to Named Entity Recognition for Under-Resourced Languages (2022.coling-1)
Copied to clipboard
| Challenge: | Existing approaches to build NLP models for low-resourced languages rely on machine translation or cross-lingual transfer. |
| Approach: | They propose to use natural annotations to build synthetic training sets from resources not originally designed for the target downstream task. |
| Outcome: | The proposed model achieves the F1 score of 0.78 for Belarusian starting from zero resources compared to the baseline of 0.63 for English . the proposed model can be fine-tuned to reflect linguistic properties, such as the grammatical case and gender, for the Slavic languages. |
Sentence Level Human Translation Quality Estimation with Attention-based Neural Networks (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing methods for assessing translation quality rely on manual features and external knowledge. |
| Approach: | They propose to use a neural model without feature engineering to detect which parts in sentence pairs are most relevant for assessing quality. |
| Outcome: | The proposed model outperforms feature-based methods on a large human annotated dataset. |
BERTology for Machine Translation: What BERT Knows about Linguistic Difficulties for Translation (2022.lrec-1)
Copied to clipboard
| Challenge: | Pre-trained transformer-based models have shown excellent performance in most benchmark tests, but lack a good understanding of the linguistic knowledge of BERT in Neural Machine Translation (NMT). |
| Approach: | They propose to use QE models to analyze BERT's syntactic dependencies and their impact on machine translation quality. |
| Outcome: | The proposed model is able to model with self-attention in the pre-training phase, which improves generalization ability. |
BERT-based Classical Arabic Poetry Authorship Attribution (2025.coling-main)
Copied to clipboard
| Challenge: | AA in Arabic poetry has been a significant issue since the 9th century due to the loss of pre-Islamic poetry and the misattribution of post-Islamical works to earlier poets. |
| Approach: | They propose a computational approach to authorship attribution in Arabic poetry using the entire Classical Arabic Poetry corpus for the first time. |
| Outcome: | The proposed model achieves F1 scores ranging from 0.97 to 1.0 and was applied to four pre-Islamic misattribution cases. |
Language adaptation experiments via cross-lingual embeddings for related languages (L18-1)
Copied to clipboard
| Challenge: | Language Adaptation is a general approach to extend existing resources from a better resourced language to a lesser resourced one. |
| Approach: | They propose to exploit lexical and grammatical similarity between languages when they are related by using orthographic similarity. |
| Outcome: | The proposed method improves the state of the art in induction of bilingual lexicons . it also improves induction performance in the Named-Entity Recognition task . |
Cross-lingual Terminology Extraction for Translation Quality Estimation (L18-1)
Copied to clipboard
| Challenge: | Using common statistical measures for termhood and unithood, we identify terms from monolingual texts and investigate the contribution of terminology to translation quality. |
| Approach: | They propose to use common statistical measures for termhood and unithood as features to train classifiers for identifying terms in cross-domain and cross-language settings. |
| Outcome: | The proposed method has shown some reliability in automatically identifying terms in human translations, but drawbacks in handling low frequency terms and term variations shall be dealt with in the future. |