text stringlengths 0 164k |
|---|
<s>[INST] Minimally Supervised Learning of Affective Events Using Discourse Relations [/INST] Affective events BIBREF0 are events that typically affect people in positive or negative ways For example getting money and playing sports are usually positive to the experiencers catching cold and losing ones wallet are negat... |
<s>[INST] PO-EMO: Conceptualization, Annotation, and Modeling of Aesthetic Emotions in German and English Poetry [/INST] 11em 111em 1111em Thomas Haider13 Steffen Eger2 Evgeny Kim3 Roman Klinger3 Winfried Menninghaus1 1Department of Language and Literature Max Planck Institute for Empirical Aesthetics 2NLLG Department ... |
<s>[INST] Community Identity and User Engagement in a Multi-Community Landscape [/INST] If each city is like a game of chess the day when I have learned the rules I shall finally possess my empire even if I shall never succeed in knowing all the cities it contains Italo Calvino Invisible Cities A communitys identityd... |
<s>[INST] Question Answering based Clinical Text Structuring Using Pre-trained Language Model [/INST] Clinical text structuring CTS is a critical task for fetching medical research data from electronic health records EHRs where structural patient medical data such as whether the patient has specific symptoms diseases o... |
<s>[INST] Progress and Tradeoffs in Neural Language Models [/INST] Deep learning has unquestionably advanced the state of the art in many natural language processing tasks from syntactic dependency parsing BIBREF0 to namedentity recognition BIBREF1 to machine translation BIBREF2 The same certainly applies to language ... |
mathbf Z tanh mathbf Wz cdot mathbf X |
mathbf F sigma mathbf Wf cdot mathbf X |
mathbf O sigma mathbf Wo cdot mathbf X |
where sigma denotes the sigmoid function cdot represents masked convolution across time and mathbf Wlbrace z f orbrace in mathbb Rm times k times r are convolution weights with k input channels m output channels and a window size of r In the recurrent pooling layer the convolution outputs are combined sequentiall... |
mathbf ct mathbf ft odot mathbf ct1 1 |
mathbf ft odot mathbf zt |
mathbf ht mathbf ot odot mathbf ct |
Multiple QRNN layers can be stacked for deeper hierarchical representation with the output mathbf h1t being fed as the input into the subsequent layer In language modeling a fourlayer QRNN is a standard architecture BIBREF11 PerplexityRecall Scale Wordlevel perplexity does not have a strictly monotonic relationship ... |
<s>[INST] Stay On-Topic: Generating Context-specific Fake Restaurant Reviews [/INST] Automatically generated fake reviews have only recently become natural enough to fool human readers Yao et al BIBREF0 use a deep neural network a socalled 2layer LSTM BIBREF1 to generate fake reviews and concluded that these fake revi... |
<s>[INST] Saliency Maps Generation for Automatic Text Summarization [/INST] Ever since the LIME algorithm BIBREF0 explanation techniques focusing on finding the importance of input features in regard of a specific prediction have soared and we now have many ways of finding saliency maps also called heatmaps because of... |
Rileftarrow jl l1 dfracwirightarrow jll1textbf zli dfracepsilon textrm signtextbf zl1j textbf bl1jDltextbf zl1j epsilon textrm signtextbf zl1j Rjl1 |
endsplit Eq 7 where wirightarrow jll1 is the networks weight parameter set during training textbf bl1j is the bias for neuron j of layer l1 textbf zli is the activation of neuron i on layer l epsilon is the stabilizing term set to 000001 and Dl is the dimension of the l th layer The relevance of a neuron is then ... |
End of preview. Expand in Data Studio
README.md exists but content is empty.
- Downloads last month
- 3