1 |
TopiOCQA: Open-domain Conversational Question Answering with Topic Switching
|
|
|
|
In: Transactions of the Association for Computational Linguistics, Vol 10, Pp 468-483 (2022) (2022)
|
|
Abstract:
AbstractIn a conversational question answering scenario, a questioner seeks to extract information about a topic through a series of interdependent questions and answers. As the conversation progresses, they may switch to related topics, a phenomenon commonly observed in information-seeking search sessions. However, current datasets for conversational question answering are limiting in two ways: 1) they do not contain topic switches; and 2) they assume the reference text for the conversation is given, that is, the setting is not open-domain. We introduce TopiOCQA (pronounced Tapioca), an open-domain conversational dataset with topic switches based on Wikipedia. TopiOCQA contains 3,920 conversations with information-seeking questions and free-form answers. On average, a conversation in our dataset spans 13 question-answer turns and involves four topics (documents). TopiOCQA poses a challenging test-bed for models, where efficient retrieval is required on multiple turns of the same conversation, in conjunction with constructing valid responses using conversational history. We evaluate several baselines, by combining state-of-the-art document retrieval methods with neural reader models. Our best model achieves F1 of 55.8, falling short of human performance by 14.2 points, indicating the difficulty of our dataset. Our dataset and code are available at https://mcgill-nlp.github.io/topiocqa.
|
|
Keyword:
Computational linguistics. Natural language processing; P98-98.5
|
|
URL: https://doi.org/10.1162/tacl_a_00471 https://doaj.org/article/b6d9583b08d54f0db0c68948315bdbd5
|
|
BASE
|
|
Hide details
|
|
2 |
PADA: Example-based Prompt Learning for on-the-fly Adaptation to Unseen Domains
|
|
|
|
In: Transactions of the Association for Computational Linguistics, Vol 10, Pp 414-433 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
3 |
VILA: Improving Structured Content Extraction from Scientific PDFs Using Visual Layout Groups
|
|
|
|
In: Transactions of the Association for Computational Linguistics, Vol 10, Pp 376-392 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
4 |
LOT: A Story-Centric Benchmark for Evaluating Chinese Long Text Understanding and Generation
|
|
|
|
In: Transactions of the Association for Computational Linguistics, Vol 10, Pp 434-451 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
5 |
Data-driven Model Generalizability in Crosslinguistic Low-resource Morphological Segmentation
|
|
|
|
In: Transactions of the Association for Computational Linguistics, Vol 10, Pp 393-413 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
6 |
Time-Aware Language Models as Temporal Knowledge Bases
|
|
|
|
In: Transactions of the Association for Computational Linguistics, Vol 10, Pp 257-273 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
7 |
Neuro-symbolic Natural Logic with Introspective Revision for Natural Language Inference
|
|
|
|
In: Transactions of the Association for Computational Linguistics, Vol 10, Pp 240-256 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
8 |
Les débuts de la phraséologie et les premières « phraséologies historiques » italo-françaises
|
|
|
|
In: Linguistik Online, Vol 113, Iss 1 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
9 |
Formen und Funktionen des Konjunktivs II in historischen ostoberdeutschen Predigten.
|
|
|
|
In: Linguistik Online, Vol 114, Iss 2 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
10 |
Zur Sprachdynamik des Konjunktivs im Bairischen in Österreich
|
|
|
|
In: Linguistik Online, Vol 114, Iss 2 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
11 |
Die Konjunktiv-II-Bildung im Kontext von Partikelverben in den Basisdialekten Salzburgs
|
|
|
|
In: Linguistik Online, Vol 114, Iss 2 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
12 |
Evaluating Explanations: How Much Do Explanations from the Teacher Aid Students?
|
|
|
|
In: Transactions of the Association for Computational Linguistics, Vol 10, Pp 359-375 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
13 |
Informationen zu den Beitragenden/Information about the authors
|
|
|
|
In: Linguistik Online, Vol 113, Iss 1 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
14 |
A Coordenação na Gramática Discursivo-Funcional
|
|
|
|
In: Linguistik Online, Vol 113, Iss 1 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
15 |
Der Konjunktiv II in den ruralen Basisdialekten Österreichs.
|
|
|
|
In: Linguistik Online, Vol 114, Iss 2 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
16 |
Konjunktiv II-Variation im urbanen Sprachgebrauch in Österreich
|
|
|
|
In: Linguistik Online, Vol 114, Iss 2 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
17 |
Der Konjunktiv II in Salzburger Varietäten: Grammatik, Gebrauch, soziale Faktoren
|
|
|
|
In: Linguistik Online, Vol 114, Iss 2 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
18 |
Informationen zu den Beitragenden/Information about the authors
|
|
|
|
In: Linguistik Online, Vol 115, Iss 3 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
19 |
„Frische Brot, lecker Brot, taze Brot“ – Eigene Muster in der Adjektivverwendung auf einem mehrsprachigen Wochenmarkt
|
|
|
|
In: Linguistik Online, Vol 115, Iss 3 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
20 |
Ein Modell zur systematischen Erfassung genuenischer Phraseme in Wörterbüchern, illustriert am Beispiel der Forschungsprojekte GEPHRAS und GEPHRAS2
|
|
|
|
In: Linguistik Online, Vol 115, Iss 3 (2022) (2022)
|
|
BASE
|
|
Show details
|
|
|
|