Zobrazeno 1 - 10
of 34
pro vyhledávání: '"Laha, Anirban"'
Publikováno v:
Computational Linguistics, Vol 45, Iss 4, Pp 737-763 (2020)
We present a framework for generating natural language description from structured data such as tables; the problem comes under the category of data-to-text natural language generation (NLG). Modern data-to-text NLG systems typically use end-to-end s
Externí odkaz:
https://doaj.org/article/c299025513b0412fac5991bdd91c4765
Autor:
Laha, Anirban
Gene prioritization involves ranking genes by possible relevance to a disease of interest. This is important in order to narrow down the set of genes to be investigated biologically, and over the years, several computational approaches have been prop
Externí odkaz:
http://hdl.handle.net/2005/2866
http://etd.ncsi.iisc.ernet.in/abstracts/3725/G26678-Abs.pdf
http://etd.ncsi.iisc.ernet.in/abstracts/3725/G26678-Abs.pdf
Autor:
Laha, Anirban, Chemmengath, Saneem A., Agrawal, Priyanka, Khapra, Mitesh M., Sankaranarayanan, Karthik, Ramaswamy, Harish G.
Converting an n-dimensional vector to a probability distribution over n objects is a commonly used component in many machine learning tasks like multiclass classification, multilabel classification, attention mechanisms etc. For this, several probabi
Externí odkaz:
http://arxiv.org/abs/1810.11975
The paper presents a first attempt towards unsupervised neural text simplification that relies only on unlabeled text corpora. The core framework is composed of a shared encoder and a pair of attentional-decoders and gains knowledge of simplification
Externí odkaz:
http://arxiv.org/abs/1810.07931
We present a framework for generating natural language description from structured data such as tables; the problem comes under the category of data-to-text natural language generation (NLG). Modern data-to-text NLG systems typically employ end-to-en
Externí odkaz:
http://arxiv.org/abs/1810.02889
Autor:
Jain, Parag, Laha, Anirban, Sankaranarayanan, Karthik, Nema, Preksha, Khapra, Mitesh M., Shetty, Shreyas
Structured data summarization involves generation of natural language summaries from structured input data. In this work, we consider summarizing structured data occurring in the form of tables as they are prevalent across a wide variety of domains.
Externí odkaz:
http://arxiv.org/abs/1804.07790
Autor:
Nema, Preksha, Shetty, Shreyas, Jain, Parag, Laha, Anirban, Sankaranarayanan, Karthik, Khapra, Mitesh M.
In this work, we focus on the task of generating natural language descriptions from a structured table of facts containing fields (such as nationality, occupation, etc) and values (such as Indian, actor, director, etc). One simple choice is to treat
Externí odkaz:
http://arxiv.org/abs/1804.07789
Much work has been done in understanding human creativity and defining measures to evaluate creativity. This is necessary mainly for the reason of having an objective and automatic way of quantifying creative artifacts. In this work, we propose a reg
Externí odkaz:
http://arxiv.org/abs/1707.05499
Autor:
Jain, Parag, Agrawal, Priyanka, Mishra, Abhijit, Sukhwani, Mohak, Laha, Anirban, Sankaranarayanan, Karthik
Existing Natural Language Generation (NLG) systems are weak AI systems and exhibit limited capabilities when language generation tasks demand higher levels of creativity, originality and brevity. Effective solutions or, at least evaluations of modern
Externí odkaz:
http://arxiv.org/abs/1707.05501
Abstractive summarization aims to generate a shorter version of the document covering all the salient points in a compact and coherent fashion. On the other hand, query-based summarization highlights those points that are relevant in the context of a
Externí odkaz:
http://arxiv.org/abs/1704.08300