Challenge: Unlike English letters, Chinese characters have rich and specific meanings.
Approach: They propose to model Chinese words' internal structures as dependency trees with 11 labels for distinguishing syntactic relationships.
Outcome: The proposed model of Chinese word-internal structures shows it can be used to parse sentences . it shows that the model can be applied to a sentence-level task with a competitive dependency parser.

Similar Papers

Character-Level Chinese Dependency Parsing via Modeling Latent Intra-Word Structure (2024.findings-acl)

Copied to clipboard

Challenge: Existing word-level dependency parsing methods in Chinese lack explicit word boundaries due to the lack of word boundaries.
Approach: They propose to model latent internal structures within Chinese words by constrained Eisner algorithm . they propose to guarantee a single root for intra-word structures and establish inter-word dependencies .
Outcome: The proposed model outperforms existing models on Chinese treebanks and shows that it can predict plausible intra-word structures.
Test Sets for Chinese Nonlocal Dependency Parsing (L18-1)

Copied to clipboard

Challenge: Chinese is a language rich in nonlocal dependencies.
Approach: They use trace annotations in the Penn Chinese Treebank to generate test sets of Chinese nonlocal dependencies which occur in different grammatical constructions.
Outcome: The proposed test sets can be used to evaluate nonlocal dependency recovery in Chinese.
Annotating Chinese Light Verb Constructions according to PARSEME guidelines (L18-1)

Copied to clipboard

Challenge: Using existing resources, we can annotate Chinese multiword expressions using PARSEME guidelines.
Approach: They propose to use an existing resource containing Chinese light verbs to make an annotation of a Chinese UD treebank in two steps.
Outcome: The proposed annotations are based on an existing treebank containing Chinese light verbs and are consistent with the proposed guidelines.
L1-L2 Parallel Treebank of Learner Chinese: Overused and Underused Syntactic Structures (L18-1)

Copied to clipboard

Challenge: Currently, the treebank consists of 600 L2 sentences and 697 L1 sentences.
Approach: They propose to use "L1-L2 parallel treebanks" to facilitate analyses of learner language.
Outcome: The proposed treebank consists of 600 L2 sentences and 697 L1 sentences.
Does Chinese BERT Encode Word Structure? (2020.coling-main)

Copied to clipboard

Challenge: Existing work has focused on analyzing the features captured by representative models such as BERT . however, little work has investigated word features for character languages such as Chinese .
Approach: They investigate Chinese BERT using attention weight distribution statistics and probing tasks to understand word features.
Outcome: The proposed model improves syntactic, semantic and word sense knowledge on a wide range of NLP tasks.
State-of-the-art Chinese Word Segmentation with Bi-LSTMs (D18-1)

Copied to clipboard

Challenge: A wide variety of neural-network architectures have been proposed for the task of Chinese word segmentation.
Approach: They propose a bidirectional LSTM model with standard deep learning techniques and best practices for the task of Chinese word segmentation.
Outcome: The proposed model outperforms models based on standard deep learning techniques and best practices on Chinese word segmentation datasets.
Neural Chinese Address Parsing (N19-1)

Copied to clipboard

Challenge: Recent research shows that systems that perform address parsing can be useful for building e-commerce or product recommendation systems.
Approach: They propose a task of parsing Chinese addresses into semantically meaningful chunks using a linear-chain structure.
Outcome: The proposed model is able to capture complex dependencies between labels that cannot be readily captured by a simple linear-chain structure.
Incorporating Chinese Characters of Words for Lexical Sememe Prediction (P18-1)

Copied to clipboard

Challenge: Existing methods of lexical sememe prediction rely on external context information of words to represent meaning.
Approach: They propose a character-enhanced sememe prediction framework for Chinese language that takes advantage of internal character information and external context information.
Outcome: The proposed framework outperforms state-of-the-art methods on a Chinese sememe knowledge base and maintains robust performance even for low-frequency words.
Building an Ellipsis-aware Chinese Dependency Treebank for Web Text (L18-1)

Copied to clipboard

Challenge: ellipsis is a common linguistic phenomenon that some words are left out as they are understood from the context, especially in oral utterance.
Approach: They propose to use a Chinese dependency treebank to facilitate the parsing of web text . they propose to restore omissions and reserve contexts in the web text to improve dependency parsers .
Outcome: The proposed framework enables the parsing of web text from online microblogs.
Exploiting Syntactic Structure for Better Language Modeling: A Syntactic Distance Approach (2020.acl-main)

Copied to clipboard

Challenge: incorporating syntactic structure into language models has been a challenge since the 1990s.
Approach: They propose to use syntactic information to integrate syntastic structure into neural language models by providing ground truth parse trees as additional training signals.
Outcome: The proposed model achieves lower perplexity and better quality when ground truth parse trees are provided as training signals.

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