Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2507.17709 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908462601994240 |
|---|---|
| author | Riley, Parker Shakeri, Siamak Ammar, Waleed Clark, Jonathan H. |
| author_facet | Riley, Parker Shakeri, Siamak Ammar, Waleed Clark, Jonathan H. |
| contents | We present TyDi QA-WANA, a question-answering dataset consisting of 28K examples divided among 10 language varieties of western Asia and northern Africa. The data collection process was designed to elicit information-seeking questions, where the asker is genuinely curious to know the answer. Each question in paired with an entire article that may or may not contain the answer; the relatively large size of the articles results in a task suitable for evaluating models' abilities to utilize large text contexts in answering questions. Furthermore, the data was collected directly in each language variety, without the use of translation, in order to avoid issues of cultural relevance. We present performance of two baseline models, and release our code and data to facilitate further improvement by the research community. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_17709 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TyDi QA-WANA: A Benchmark for Information-Seeking Question Answering in Languages of West Asia and North Africa Riley, Parker Shakeri, Siamak Ammar, Waleed Clark, Jonathan H. Computation and Language We present TyDi QA-WANA, a question-answering dataset consisting of 28K examples divided among 10 language varieties of western Asia and northern Africa. The data collection process was designed to elicit information-seeking questions, where the asker is genuinely curious to know the answer. Each question in paired with an entire article that may or may not contain the answer; the relatively large size of the articles results in a task suitable for evaluating models' abilities to utilize large text contexts in answering questions. Furthermore, the data was collected directly in each language variety, without the use of translation, in order to avoid issues of cultural relevance. We present performance of two baseline models, and release our code and data to facilitate further improvement by the research community. |
| title | TyDi QA-WANA: A Benchmark for Information-Seeking Question Answering in Languages of West Asia and North Africa |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2507.17709 |