Дискриминативные модели
Related Papers
Investigating Loss Functions and Optimization Methods for Discriminative Learning of Label Sequences
Discriminative models have been of inter- est in the NLP community in recent years. Previous research has shown that they are advantageous over generative mod- els. In this paper, we …...
Improved Discriminative Bilingual Word Alignment
For many years, statistical machine trans- lation relied on generative models to pro- vide bilingual word alignments. In 2005, several independent efforts showed that discriminative models could be used to …...
Lessons Learned in Part-of-Speech Tagging of Conversational Speech
This paper examines tagging models for spon- taneous English speech transcripts. We ana- lyze the performance of state-of-the-art tag- ging models, either generative or discrimi- native, left-to-right or bidirectional, with …...
Discriminative state tracking for spoken dialog systems
In spoken dialog systems, statistical state tracking aims to improve robustness to speech recognition errors by tracking a posterior distribution over hidden dialog states. Current approaches based on gener- ative …...
Fine-grained Opinion Mining with Recurrent Neural Networks and Word Embeddings
The tasks in fine-grained opinion mining can be regarded as either a token-level se- quence labeling problem or as a semantic compositional task. We propose a gen- eral class of …...
Improving Update Summarization via Supervised ILP and Sentence Reranking
Integer Linear Programming (ILP) based sum- marization methods have been widely adopted recently because of their state-of-the-art per- formance. This paper proposes two new mod- ifications in this framework for …...
When and why are log-linear models self-normalizing?
Several techniques have recently been pro- posed for training “self-normalized” discrimi- native models. These attempt to find parameter settings for which unnormalized model scores approximate the true label probability. How- …...
Neural Net Models of Open-domain Discourse Coherence
AbstractDiscourse coherence is strongly associated with text quality, making it important to natural language generation and understanding. Yet existing models of coherence focus on measuring individual aspects of coherence (lexical …...
Discriminatively-Tuned Generative Classifiers for Robust Natural Language Inference
AbstractWhile discriminative neural network classifiers are generally preferred, recent work has shown advantages of generative classifiers in term of data efficiency and robustness. In this paper, we focus on natural …...
A Generative Approach for Mitigating Structural Biases in Natural Language Inference
AbstractMany natural language inference (NLI) datasets contain biases that allow models to perform well by only using a biased subset of the input, without considering the remainder features. For instance, …...
ConEntail: An Entailment-based Framework for Universal Zero and Few Shot Classification with Supervised Contrastive Pretraining
AbstractA universal classification model aims to generalize to diverse classification tasks in both zero and few shot settings. A promising way toward universal classification is to cast heterogeneous data formats …...