Zobrazeno 1 - 10
of 36
pro vyhledávání: '"Adams, Griffin"'
Over the last few years, multi-vector retrieval methods, spearheaded by ColBERT, have become an increasingly popular approach to Neural IR. By storing representations at the token level rather than at the document level, these methods have demonstrat
Externí odkaz:
http://arxiv.org/abs/2409.14683
Autor:
Subbiah, Melanie, Ladhak, Faisal, Mishra, Akankshya, Adams, Griffin, Chilton, Lydia B., McKeown, Kathleen
Human evaluation has been the gold standard for checking faithfulness in abstractive summarization. However, with a challenging source domain like narrative, multiple annotators can agree a summary is faithful, while missing details that are obvious
Externí odkaz:
http://arxiv.org/abs/2407.06501
Autor:
Adams, Griffin
The rapid adoption of Electronic Health Records (EHRs)--electronic versions of a patient's medical history--has been instrumental in streamlining administrative tasks, increasing transparency, and enabling continuity of care across providers. An unin
Clinician must write a lengthy summary each time a patient is discharged from the hospital. This task is time-consuming due to the sheer number of unique clinical concepts covered in the admission. Identifying and covering salient entities is vital f
Externí odkaz:
http://arxiv.org/abs/2401.02369
Selecting the ``right'' amount of information to include in a summary is a difficult task. A good summary should be detailed and entity-centric without being overly dense and hard to follow. To better understand this tradeoff, we solicit increasingly
Externí odkaz:
http://arxiv.org/abs/2309.04269
Two-step approaches, in which summary candidates are generated-then-reranked to return a single summary, can improve ROUGE scores over the standard single-step approach. Yet, standard decoding methods (i.e., beam search, nucleus sampling, and diverse
Externí odkaz:
http://arxiv.org/abs/2305.17779
Autor:
Adams, Griffin, Nguyen, Bichlien H, Smith, Jake, Xia, Yingce, Xie, Shufang, Ostropolets, Anna, Deb, Budhaditya, Chen, Yuan-Jyue, Naumann, Tristan, Elhadad, Noémie
Summarization models often generate text that is poorly calibrated to quality metrics because they are trained to maximize the likelihood of a single reference (MLE). To address this, recent work has added a calibration step, which exposes a model to
Externí odkaz:
http://arxiv.org/abs/2305.07615
Long-form clinical summarization of hospital admissions has real-world significance because of its potential to help both clinicians and patients. The faithfulness of summaries is critical to their safe usage in clinical settings. To better understan
Externí odkaz:
http://arxiv.org/abs/2303.03948
Autor:
Adams, Griffin, Shing, Han-Chin, Sun, Qing, Winestock, Christopher, McKeown, Kathleen, Elhadad, Noémie
In real-world scenarios with naturally occurring datasets, reference summaries are noisy and may contain information that cannot be inferred from the source text. On large news corpora, removing low quality samples has been shown to reduce model hall
Externí odkaz:
http://arxiv.org/abs/2204.10290
Autor:
Tang, Xiangru, Fabbri, Alexander, Li, Haoran, Mao, Ziming, Adams, Griffin Thomas, Wang, Borui, Celikyilmaz, Asli, Mehdad, Yashar, Radev, Dragomir
Current pre-trained models applied to summarization are prone to factual inconsistencies which either misrepresent the source text or introduce extraneous information. Thus, comparing the factual consistency of summaries is necessary as we develop im
Externí odkaz:
http://arxiv.org/abs/2109.09195