Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop
Revealing Weaknesses of Vietnamese Language Models Through Unanswerable Questions in Machine Reading Comprehension (2023.eacl-srw)
Copied to clipboard
| Challenge: | Existing problems in Vietnamese Machine Reading Comprehension systems are limited due to multilinguality, which limits the ability of multilingual models to develop state-of-the-art systems. |
| Approach: | They propose to modify the process of annotating unanswerable questions to improve the quality of unanswered questions to a higher level of difficulty for Machine Reading Comprehension systems to solve. |
| Outcome: | The proposed modification improves the quality of unanswerable questions to a higher level of difficulty for Machine Reading Comprehension systems to solve. |
Incorporating Dropped Pronouns into Coreference Resolution: The case for Turkish (2023.eacl-srw)
Copied to clipboard
| Challenge: | PD-MRLs are pro-drop and morphologically rich languages due to dropped pronouns . a representation & evaluation scheme is proposed to incorporate dropped pronomins into coreference resolution . |
| Approach: | They propose a representation & evaluation scheme to incorporate dropped pronouns into coreference resolution and validate it on the Turkish language. |
| Outcome: | The proposed representation & evaluation scheme extends on the Turkish coreference dataset . it includes pre and post processors to enhance the prominent CoNLL coreference scorer . |
Towards Generation and Recognition of Humorous Texts in Portuguese (2023.eacl-srw)
Copied to clipboard
| Challenge: | This PhD thesis focuses on the automatic generation and recognition of verbal punning humor in Portuguese. |
| Approach: | They propose to combine natural language generation and cognitive processing to generate and recognize verbal humor in Portuguese. |
| Outcome: | The proposed methods aim to generate and recognize humor in Portuguese, an underdeveloped language compared to English. |
GAP-Gen: Guided Automatic Python Code Generation (2023.eacl-srw)
Copied to clipboard
| Challenge: | Several previous approaches convert a sentence into a formal statement by mapping verbs to functions in the formal language. |
| Approach: | They propose a Guided Automatic Python Code Generation method based on Python syntactic constraints and semantic constraints. |
| Outcome: | The proposed method achieves better results on automatic Python code generation task than previous methods. |
Development of pre-trained language models for clinical NLP in Spanish (2023.eacl-srw)
Copied to clipboard
| Challenge: | Clinical natural language processing aims to tackle language and prediction tasks using text from medical practice, such as clinical notes, prescriptions, and discharge summaries. |
| Approach: | They propose to build a clinical corpus big enough to implement a functional PLM. |
| Outcome: | The proposed model will be able to handle language and prediction tasks using clinical text while using biomedical and general text. |
Which One Are You Referring To? Multimodal Object Identification in Situated Dialogue (2023.eacl-srw)
Copied to clipboard
| Challenge: | a demand for multimodal dialogue systems is increasing for situated dialogues, where a dialogue agent shares a co-observed vision or physical space with the user. |
| Approach: | They propose three methods to solve multimodal object identification problem using situated dialogue dataset SIMMC 2.1. |
| Outcome: | The proposed method improves by 20% F1-score on the largest situated dialogue dataset, SIMMC 2.1. |
A Unified Framework for Emotion Identification and Generation in Dialogues (2023.eacl-srw)
Copied to clipboard
| Challenge: | Social chatbots have gained immense popularity and can be used to develop and promote social chatbot applications. |
| Approach: | They propose a multi-task framework that jointly identifies the emotion of a given dialogue and generates response in accordance to the identified emotion. |
| Outcome: | The proposed framework outperforms current state-of-the-art models with classification and generation loss. |
Improving and Simplifying Template-Based Named Entity Recognition (2023.eacl-srw)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) is traditionally approached as a sequence labeling task where a tag is predicted for each token. |
| Approach: | They propose to convert a Named Entity Recognition task into a seq2seq task by generating synthetic sentences using templates. |
| Outcome: | The proposed model outperforms the current state-of-the-art approach in resource-rich, low resource and domain transfer settings and the negative examples play an important role in its performance. |
Polite Chatbot: A Text Style Transfer Application (2023.eacl-srw)
Copied to clipboard
| Challenge: | Creating polite chatbots requires complex setups that require reinforcement learning to produce coherent responses. |
| Approach: | They propose a polite chatbot that can generate coherent responses to given contexts by using a model that transfers neutral sentences into polite ones and trains a dialogue model. |
| Outcome: | The proposed method outperforms baselines in producing polite dialogue responses while staying competitive in terms of coherent to the given context. |
Template-guided Grammatical Error Feedback Comment Generation (2023.eacl-srw)
Copied to clipboard
| Challenge: | Writing corrective feedback on learner text is widespread in language education, but it can be time-consuming for teachers. |
| Approach: | They propose to use feedback comment generation to generate explanatory notes for learners by categorizing comments and constraining outputs of noisy classes. |
| Outcome: | The proposed scheme can be used to generate feedback comment corpora using a broader scope than existing typologies focused on error correction. |
Clinical Text Anonymization, its Influence on Downstream NLP Tasks and the Risk of Re-Identification (2023.eacl-srw)
Copied to clipboard
| Challenge: | De-identification and anonymization of clinical data is needed to solve access to clinicaldata. |
| Approach: | They propose to use text anonymization techniques to break the anonymization of clinical data . they propose to apply a re-identification attack to the anonymized text data to break this. |
| Outcome: | The proposed approach can break the anonymization of clinical data, the authors show . |
Automatic Dialog Flow Extraction and Guidance (2023.eacl-srw)
Copied to clipboard
| Challenge: | This PhD thesis aims to increase the efficiency of the human's job without losing human contact. |
| Approach: | They propose to extract information from Portuguese dialogs and use it to describe interactions to create a pipeline for guiding human actions. |
| Outcome: | The proposed solution will be applied to task-oriented dialog transcriptions (e.g. call center) it will use three components: Extraction, for processing dialogs and using the information to describe interactions; Representation, for discovering the most frequent dialog flows; Guidance, for helping the agent during a new dialog. |
Diverse Content Selection for Educational Question Generation (2023.eacl-srw)
Copied to clipboard
| Challenge: | Current automatic Question Generation (QG) systems do not consider content selection as an educational aspect. |
| Approach: | They propose to select content based on relevance and topic diversity for question generation on educational document level. |
| Outcome: | The proposed solution reduces the time and effort required to create questions for students on educational datasets. |
Towards Automatic Grammatical Error Type Classification for Turkish (2023.eacl-srw)
Copied to clipboard
| Challenge: | Existing error types are not universal, resulting in many language specific variants. |
| Approach: | They propose to use a rule-based error type classification pipeline to classify edits into predefined error categories for Turkish . they propose to change existing error categories to suit the inflectional and derivational properties of the language . |
| Outcome: | The proposed system is evaluated on 106 annotated sentences and its performance is measured as 77.04% F0.5 score. |
Theoretical Conditions and Empirical Failure of Bracket Counting on Long Sequences with Linear Recurrent Networks (2023.eacl-srw)
Copied to clipboard
| Challenge: | Existing studies have shown that linear RNNs with unbounded activation functions are difficult to train effectively and do not learn exact counting behaviour. |
| Approach: | They propose to identify the necessary conditions for a linear single-cell RNN to have the ability to count and to investigate how these conditions relate to the empirical behaviour of trained linear RNN models. |
| Outcome: | The proposed model is a linear single-cell RNN with an unbounded activation function and a Dyck-1-like balanced bracket language. |
Addressing Domain Changes in Task-oriented Conversational Agents through Dialogue Adaptation (2023.eacl-srw)
Copied to clipboard
| Challenge: | Recent task-oriented dialogue systems are trained on annotated dialogues, but when domain knowledge changes, the initial model may become obsolete. |
| Approach: | They propose to use an annotated dialogue dataset to train a dialogue model for domain changes . they propose to fine-tune a generative language model on domain changes to reduce performance . |
| Outcome: | The proposed approach reduces performance by 55% by fine-tuning a generative language model on domain changes. |