@inproceedings{VenkateswaranAlFoysalShaiketal., author = {Venkateswaran, Siddarth and Al Foysal, Abdullah and Shaik, Nazeer Basha and B{\"o}ck, Ronald}, title = {Is there Text in Wine? - S+U Learning-based Named Entity Recognition and Triplet Extraction from Wine Aroma Descriptors}, series = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, booktitle = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, editor = {Baumann, Timo}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-325-6}, doi = {10.35096/othr/pub-7093}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-70931}, pages = {157 -- 164}, abstract = {Wine making is usually considered a domain being far off the processing of speech and language. But in a particular aspect, the domains of speech processing and wine making are related, namely, in the description of wine aromas. These descriptors are used for creating wine expertise as well as more general (advertisement-like) textual representations. In the current paper, we use Natural Language Processing techniques, especially Named Entity Recognition, to identify Aspects and Opinions, reflecting wine characteristics. These are combined with analyses of respective relations (triplet extraction) building Aspect-Opinion-Pairs to establish indicative aroma descriptors, also trying to approach the complex interplay amongst these individual statements. In our experiments, we rely on the Falstaff corpus comprising a huge set of wine descriptions. This results in an average F1 score of around 0.85 for Aspect-Opinion classification. For triplet generation multiple strategies were compared, resulting in an average F1 score of 0.67 in this challenging task. For both tasks we rely only on a handful of manually annotated samples, applying pseudo-labeling methods from seed data to achieve automatic labeling.}, language = {en} } @inproceedings{VenkateswaranBoeck, author = {Venkateswaran, Siddarth and B{\"o}ck, Ronald}, title = {Can Language Models Behave Like Wine Sommeliers? - Using Multiple Agents To Evaluate The Quality of Wine Descriptors Generated By Llama 2}, series = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, booktitle = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, editor = {Baumann, Timo}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-325-6}, doi = {10.35096/othr/pub-7091}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-70911}, pages = {141 -- 148}, abstract = {Wines are complex beverages whose taste can be described either numerically or textually, with the former involving the rating of the intensities of different aroma characteristics often with the help of a wine tasting wheel, and the latter with the help of crisp terms often in a poetic fashion. These are often done with the help of wine sommeliers who with one sniff can describe the wine. Usually, each sommelier has a unique style when it comes to textually describing a wine, research has shown that such differences have no negative impact in correctly classifying wines on the basis of their color, grape variety, region etc. Given the recent advancements in the field of Natural Language Processing, especially with the emergence of Large Language Models, we aim to check the capability of Llama 2 in its ability to generate texts pertaining to a specific color of a wine, given a list of aroma intensities as input prompts. In our experiments, we relied on data from Meininger and Falstaff, and on a combination of domain adaptation and pseudo-labeling techniques to create the corpus to train the Llama 2 model on. Also, we relied on a voting scheme of three differently trained classifiers to evaluate the wine-color specific text generation capabilities of Llama 2. Additionally, we employed the services of domain experts to evaluate the quality of a sample set of texts that was generated by Llama 2.}, language = {en} }