Chen Gong, Saihao Huang, Houquan Zhou, Zhenghua Li, Min Zhang, Zhefeng Wang, Baoxing Huai, Nicholas Jing Yuan
| 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. |