Automatic Detection of Sentence Fragments

Yeung, Chak Yan; Lee, John

doi:10.3115/v1/p15-2099

Cited by 2 publications

(2 citation statements)

References 10 publications

(5 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This group of methods solves STC with consideration of context information. It includes a parsing-based classifier (PARPOS) that uses the parse tree patterns and POS tags as text features (Yeung and Lee 2015); a two-layer RNN+CNN network (TLRCN) that incorporates context information (Lee and Dernoncourt 2016); and the state-of-the-art STC solution (CNNDAC) that uses a hierarchical CNN+RNN model for dialog act classification (Liu, Han, and others 2017). • General Sequence Labelers.…”

Section: Discussionmentioning

confidence: 99%

“…STC has been studied extensively within various NLP tasks with different text granularities, including part-of-speech (POS) tagging (Ratnaparkhi 1996), named entity recognition (NER) (Zhou and Su 2002), semantic roles labeling (SRL) (Gildea and Jurafsky 2002) and dialogue act tagging (Ji and Bilmes 2005). Some feature-based methods classify each fragment independently, i.e., each fragment is viewed as an individual text (Blatat, Mrakova, and Popelinsky 2004;Yeung and Lee 2015). However, this strategy relies on a set of handcrafted features and/or does not take into account the inherent dependencies across fragments.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Solving Sequential Text Classification as Board-Game Playing

Chen

Feng

Wen

et al. 2020

AAAI

View full text Add to dashboard Cite

Sequential Text Classification (STC) aims to classify a sequence of text fragments (e.g., words in a sentence or sentences in a document) into a sequence of labels. In addition to the intra-fragment text contents, considering the inter-fragment context dependencies is also important for STC. Previous sequence labeling approaches largely generate a sequence of labels in left-to-right reading order. However, the need for context information in making decisions varies across different fragments and is not strictly organized in a left-to-right order. Therefore, it is appealing to label the fragments that need less consideration of context information first before labeling the fragments that need more. In this paper, we propose a novel model that labels a sequence of fragments in jumping order. Specifically, we devise a dedicated board-game to develop a correspondence between solving STC and board-game playing. By defining proper game rules and devising a game state evaluator in which context clues are injected, at each round, each player is effectively pushed to find the optimal move without position restrictions via considering the current game state, which corresponds to producing a label for an unlabeled fragment jumpily with the consideration of the contexts clues. The final game-end state is viewed as the optimal label sequence. Extensive results on three representative datasets show that the proposed approach outperforms the state-of-the-art methods with statistical significance.

show abstract

Section: Discussionmentioning

confidence: 99%