Papers with Conditional Random Field

8 papers
Deep neural model with enhanced embeddings for pharmaceutical and chemical entities recognition in Spanish clinical text (D19-57)

Copied to clipboard

Challenge: Currently, the number of biomedical literature is growing at an exponential rate.
Approach: They propose a Deep Learning architecture for pharmaceutical and chemical Named Entity Recognition in Spanish clinical cases texts.
Outcome: The proposed model outperforms the state-of-the-art methods on the PharmaCoNER corpus . the proposed model is based on two bidirectional long-term memory and conditional random field networks .
Towards a Standardized Dataset on Indonesian Named Entity Recognition (2020.aacl-srw)

Copied to clipboard

Challenge: Named entity recognition (NER) tasks in the Indonesian language are still lacking data for the majority of languages, including Indonesian.
Approach: They re-annotated an open dataset with 2,000 sentences and compared the results with a bidirectional long short-term memory and conditional random field approach.
Outcome: The proposed approach improved the prediction score and consistent organization tag for the Indonesian language.
Neural Arabic Text Diacritization: State of the Art Results and a Novel Approach for Machine Translation (D19-52)

Copied to clipboard

Challenge: a number of Arabic text diacritizers use diacritics to convey information about meaning of a word . Arabic text to speech (TTS) requires a complex process to determine the correct diacritical for each character .
Approach: They propose to use Arabic diacritization to enhance machine translation models . they propose to build automatic Arabic text diacritics using two approaches .
Outcome: The proposed models are either better or on par with other models, which require language-dependent post-processing steps, unlike ours.
Speaker-change Aware CRF for Dialogue Act Classification (2020.coling-main)

Copied to clipboard

Challenge: Recent work in Dialogue Act (DA) classification approaches the task as a sequence labeling problem, using neural network models coupled with a Conditional Random Field (CRF) as the last layer.
Approach: They propose to modify the CRF layer to take speaker-change into account and learn meaningful transition patterns conditioned on speaker-changing DA labels.
Outcome: The proposed model outperforms the original model with wide margins for some DA labels.
Masked Conditional Random Fields for Sequence Labeling (2021.naacl-main)

Copied to clipboard

Challenge: Conditional Random Fields (CRF) based neural models are among the most performant for sequence labeling problems, but they can sometimes generate illegal sequences of tags.
Approach: They propose a conditional random field-based model that imposes restrictions on candidate paths during both training and decoding phases.
Outcome: The proposed method improves on existing CRF models with near zero additional cost.
Bridge Video and Text with Cascade Syntactic Structure (C18-1)

Copied to clipboard

Challenge: Using LSTM-CSS, we construct basic syntactic structure by completing syntastic structure.
Approach: They propose a video captioning approach that progressively completes syntactic structure by a conditional random field to construct basic syntaktic structure.
Outcome: The proposed method produces natural sentences with 42.3% and 28.5% accuracy compared to state-of-the-art methods.
Unsupervised Paraphrasing Consistency Training for Low Resource Named Entity Recognition (2021.emnlp-main)

Copied to clipboard

Challenge: Existing methods augment input sequence with token replacement, assuming annotations on the replaced positions are unchanged.
Approach: They propose to use paraphrasing to enhance unsupervised consistency training by replacing tokens with augmented data.
Outcome: The proposed method is especially effective when annotations are limited.
Who Wrote When? Author Diarization in Social Media Discussions (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches for author diarization are unable to detect stylistic shifts in a text .
Approach: They propose a framework that integrates pre-trained neural representations of writing style with author-conditional encoder-decoder diarization.
Outcome: The proposed framework is able to attribute comments in online discussions to individual authors.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations