Papers by Amir Hazem
Books of Hours. the First Liturgical Data Set for Text Segmentation. (2020.lrec-1)
Copied to clipboard
Amir Hazem, Beatrice Daille, Christopher Kermorvant, Dominique Stutzmann, Marie-Laurence Bonhomme, Martin Maarand, Mélodie Boillet
| Challenge: | Until now, the book of hours has been scarcely studied because of its manuscript nature, its length and its complex content. |
| Approach: | They propose to use Handwritten Text Recognition to generate a corpus of Latin transcriptions of 300 books of hours generated by OCR for handwritten and not printed texts. |
| Outcome: | The proposed structure and state-of-the-art methods are compared with existing methods and are based on the results of a systematic evaluation of two books of hours. |
Cross-lingual and Cross-domain Transfer Learning for Automatic Term Extraction from Low Resource Data (2022.lrec-1)
Copied to clipboard
| Challenge: | Automatic Term Extraction (ATE) is a key component for domain knowledge understanding and can be used for further NLP applications. |
| Approach: | They propose to fine-tune pre-trained BERT models for automatic Term Extraction (ATE) using cross-lingual and cross-domain transfer learning to extract single and multi-word terms. |
| Outcome: | The proposed models can capture cross-domain and cross-lingual terminologically-marked contexts shared by terms, opening a new design-pattern for ATE. |
From Technology to Market. Bilingual Corpus on the Evaluation of Technology Opportunity Discovery (2024.lrec-main)
Copied to clipboard
| Challenge: | a large variety of TOD approaches have been proposed to explore emerging technologies and diversify existing products and services. |
| Approach: | They propose to use a technology-market corpus in English and Japanese to construct a market space using a BERT model. |
| Outcome: | The proposed method is based on a fine-tuned BERT model for linking technology to the market. |
Hierarchical Text Segmentation for Medieval Manuscripts (2020.coling-main)
Copied to clipboard
| Challenge: | Until now, text segmentation methods have only addressed data sets lying within the scope of narrative and expository texts or user dialogues texts. |
| Approach: | They propose a bottom-up greedy approach that enhances the results . they argue that books of hours exhibit a complex hierarchical entangled structure . |
| Outcome: | The proposed bottom-up greedy approach significantly enhances the results. |
Word Embedding Approach for Synonym Extraction of Multi-Word Terms (L18-1)
Copied to clipboard
| Challenge: | MWTs are motivated combinations that clearly convey the concept they designate. |
| Approach: | They propose a word-embedding-based approach for automatic acquisition of MWT synonyms that manage length variability. |
| Outcome: | The proposed approach improves on two specialized domain corpora and shows that it is more efficient than baseline approaches. |
PyRATA, Python Rule-based feAture sTructure Analysis (L18-1)
Copied to clipboard
| Challenge: | a new Python module supports rules-based analysis on structured data . the module is available under the Apache V2 license . |
| Approach: | They propose a Python module which supports rules-based analysis on structured data. |
| Outcome: | The proposed module supports rules-based analysis on structured data. |
Leveraging Meta-Embeddings for Bilingual Lexicon Extraction from Specialized Comparable Corpora (C18-1)
Copied to clipboard
| Challenge: | Recent studies on bilingual lexicon extraction from specialized comparable corpora show differences in performance . lack of large specialized corporan to build efficient representations can be partially explained . |
| Approach: | They propose to use character-based embedding models to combine different embeddable models . they emphasize how character-driven embeddance models outperform other models on quality . |
| Outcome: | The proposed model outperforms other models on quality of extracted bilingual lexicons . comparable corpora are an interesting and practical alternative to parallel corporation . |
Data Selection for Bilingual Lexicon Induction from Specialized Comparable Corpora (2020.coling-main)
Copied to clipboard
| Challenge: | Narrow specialized comparable corpora are small in size, making it difficult to build efficient models to acquire translation equivalents. |
| Approach: | They propose to use Tf-Idf and cross entropy to improve bilingual lexicon induction from specialized comparable corpora by a factor of 10 . |
| Outcome: | The proposed methods improve bilingual lexicon induction by a large margin. |
A Multi-Domain Framework for Textual Similarity. A Case Study on Question-to-Question and Question-Answering Similarity Tasks (L18-1)
Copied to clipboard
| Challenge: | Community Question Answering websites are becoming popular and useful source of information for users. |
| Approach: | They propose to use community question answering forum to detect similar questions . they use question-answering similarity task to provide correct answers . |
| Outcome: | The proposed framework provides the first framework on the evaluation of similar questions and question-answering detection on a multi-domain corpora. |