Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Luheng He"'
Understanding tables is an important aspect of natural language understanding. Existing models for table understanding require linearization of the table structure, where row or column order is encoded as an unwanted bias. Such spurious biases make t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::de8611173e88a9065f7e10f59da6c698
http://arxiv.org/abs/2203.00274
http://arxiv.org/abs/2203.00274
The dominant paradigm for semantic parsing in recent years is to formulate parsing as a sequence-to-sequence task, generating predictions with auto-regressive sequence decoders. In this work, we explore an alternative paradigm. We formulate semantic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e6ba4c088685e53248264c8b57f34186
http://arxiv.org/abs/2109.04587
http://arxiv.org/abs/2109.04587
Publikováno v:
ACL/IJCNLP (1)
Everyday conversations require understanding everyday events, which in turn, requires understanding temporal commonsense concepts interwoven with those events. Despite recent progress with massive pre-trained language models (LMs) such as T5 and GPT-
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::01bb164f4070acaab69b18fbb9792225
https://doi.org/10.18653/v1/2021.acl-long.549
https://doi.org/10.18653/v1/2021.acl-long.549
Publikováno v:
NAACL-HLT
Few-shot learning arises in important practical scenarios, such as when a natural language understanding system needs to learn new semantic labels for an emerging, resource-scarce domain. In this paper, we explore retrieval-based methods for intent c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8ac9db1a0e88f5e19f0c264931636344
https://doi.org/10.18653/v1/2021.naacl-main.59
https://doi.org/10.18653/v1/2021.naacl-main.59
Publikováno v:
ACL/IJCNLP (2)
Slot-filling is an essential component for building task-oriented dialog systems. In this work, we focus on the zero-shot slot-filling problem, where the model needs to predict slots and their values, given utterances from new domains without trainin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b21a82164d7d0267993607cd3d94aebb
https://doi.org/10.18653/v1/2021.acl-short.83
https://doi.org/10.18653/v1/2021.acl-short.83
Publikováno v:
NAACL-HLT (1)
We introduce a general framework for several information extraction tasks that share span representations using dynamically constructed span graphs. The graphs are constructed by selecting the most confident entity spans and linking these nodes with
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7413b85e9b67a771afb1ead0a118385d
http://arxiv.org/abs/1904.03296
http://arxiv.org/abs/1904.03296
Publikováno v:
NAACL-HLT (1)
Existing paraphrase identification datasets lack sentence pairs that have high lexical overlap without being paraphrases. Models trained on such data fail to distinguish pairs like flights from New York to Florida and flights from Florida to New York
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::432c0ead66de24b045d8fe536c1eaaba
https://doi.org/10.18653/v1/n19-1131
https://doi.org/10.18653/v1/n19-1131
Publikováno v:
EMNLP/IJCNLP (1)
Reading comprehension models have been successfully applied to extractive text answers, but it is unclear how best to generalize these models to abstractive numerical answers. We enable a BERT-based reading comprehension model to perform lightweight
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3552d53ed3879524468ce094e117a384
https://doi.org/10.18653/v1/d19-1609
https://doi.org/10.18653/v1/d19-1609
Publikováno v:
ACL (2)
Recent BIO-tagging-based neural semantic role labeling models are very high performing, but assume gold predicates as part of the input and cannot incorporate span-level features. We propose an end-to-end approach for jointly predicting all predicate
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f963dbc7afbce86d0c4e79c5b2ebee46
http://arxiv.org/abs/1805.04787
http://arxiv.org/abs/1805.04787
Publikováno v:
ACL (1)
We present a new large-scale corpus of Question-Answer driven Semantic Role Labeling (QA-SRL) annotations, and the first high-quality QA-SRL parser. Our corpus, QA-SRL Bank 2.0, consists of over 250,000 question-answer pairs for over 64,000 sentences
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::35eb45cc56fabe60651c9edeacfd09dc