Papers by Sharid Loáiciga
Is Incoherence Surprising? Targeted Evaluation of Coherence Prediction from Language Models (2021.naacl-main)
Copied to clipboard
| Challenge: | a common approach to coherence evaluation is shuffling the sentence order of a text, creating incoherent text samples that need to be discriminated from the original. |
| Approach: | They propose an extendable set of test suites addressing different aspects of discourse and dialogue coherence. |
| Outcome: | The proposed evaluation paradigm is suited to evaluate linguistic qualities that contribute to the notion of coherence. |
New or Old? Exploring How Pre-Trained Language Models Represent Discourse Entities (2022.coling-1)
Copied to clipboard
| Challenge: | Recent research shows pre-trained language models learn to encode syntactic knowledge to a certain degree. |
| Approach: | They propose to investigate the information-status of entities as discourse-new or discourse-old . they use binary classification and sequence labeling to investigate their ability to encode syntactic knowledge . |
| Outcome: | The proposed models encode information on whether an entity has been introduced before or not in the discourse. |
Exploiting Cross-Lingual Hints to Discover Event Pronouns (2020.lrec-1)
Copied to clipboard
| Challenge: | Non-nominal co-reference is much less studied than nominal coreference because of the lack of annotated corpora. |
| Approach: | They propose to use parallel multilingual corpora to create artificially labeled data for the classification of three different readings of the English pronoun ‘it’: entity, event or pleonastic. |
| Outcome: | The proposed method can be used to classify three different readings of the English pronoun ‘it’ from their translation in several languages. |
Multilingual Models for ASR in Chibchan Languages (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing algorithms for low resource-intensive languages are not available for these languages . a paper comparing the performance of different models and algorithms for these extremely low resource languages is presented. |
| Approach: | They propose to fine-tune four ASR algorithms to create monolingual models for Bribri and Cabécar . they then use the best performing algorithm to train joint and transfer learning models for both languages . |
| Outcome: | The proposed algorithms are effective in both Bribri and Cabécar, but especially in Bribri. |
Analysing concatenation approaches to document-level NMT in two different domains (D19-65)
Copied to clipboard
| Challenge: | a recent study has shown that discourse-related biases affect neural MT performance. |
| Approach: | They propose a comparative evaluation scheme that contrasts coherent context with artificially scrambled documents and absent context. |
| Outcome: | The proposed evaluation scheme contrasts coherent context with artificially scrambled documents and absent context on two popular datasets. |