Papers by Hongzhi Xu
Benchmarking the Performance of Machine Translation Evaluation Metrics with Chinese Multiword Expressions (2024.lrec-main)
Copied to clipboard
| Challenge: | Multiword Expressions (MWEs) are hard nuts for many natural language processing tasks. |
| Approach: | They annotate 28 types of Chinese MWEs and then examine 31 MTE metrics on groups of sentences containing different MWE. |
| Outcome: | The results show that MT systems and MTE metrics still suffer from MWEs . |
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. |
A Deep Analysis of the Impact of Multiword Expressions and Named Entities on Chinese-English Machine Translations (2024.findings-emnlp)
Copied to clipboard
| Challenge: | a study on the impact of multiword expressions and multiword named entities (NEs) on the performance of Chinese-English machine translation systems is presented. |
| Approach: | They propose to use Chinese multiword expressions and multiword named entities (NEs) to evaluate machine translation performance. |
| Outcome: | The proposed methods show that Chinese-English machine translation systems perform significantly worse on Chinese sentences with most kinds of MWEs and NEs. |
Modeling Morphological Typology for Unsupervised Learning of Language Morphology (2020.acl-main)
Copied to clipboard
| Challenge: | Existing approaches to morphological analysis relied on hand-built rules to identify word-internal structures. |
| Approach: | They propose a language-independent model for fully unsupervised morphological analysis that exploits a universal framework leveraging morphology. |
| Outcome: | The proposed model outperforms existing systems on nine typologically and genetically diverse languages and shows superior performance over leading systems. |
Large-Scale Relation Learning for Question Answering over Knowledge Bases with Pre-trained Language Models (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing KBQA methods focus on the natural language but ignore textual information carried by the nodes and edges. |
| Approach: | They propose to perform relation extraction, relation matching, and relation reasoning tasks to align the natural language expressions to the relations in the KB and reason over the missing connections. |
| Outcome: | Experiments on WebQSP show that the proposed model outperforms baselines even when the KB is incomplete. |
Morphological Segmentation for Low Resource Languages (2020.lrec-1)
Copied to clipboard
Justin Mott, Ann Bies, Stephanie Strassel, Jordan Kodner, Caitlin Richter, Hongzhi Xu, Mitchell Marcus
| Challenge: | a new corpus of annotated morphological data is described for the DARPA LORELEI Program . the data is annotating 9 low resource languages and root information for 7 of the languages . |
| Approach: | This paper describes a new morphology resource created by Linguistic Data Consortium and the University of Pennsylvania for the DARPA LORELEI Program. |
| Outcome: | The annotated corpus provides a gold standard for unsupervised morphological segmenters and analyzers . the language-specific annotation guidelines were language-independent, but included morphology paradigms and other specifications. |
Annotating Chinese Word Senses with English WordNet: A Practice on OntoNotes Chinese Sense Inventories (2024.lrec-main)
Copied to clipboard
| Challenge: | a recent study has shown that large language models can be useful for cross-lingual applications. |
| Approach: | They propose to annotate Chinese word senses using English WordNet synsets . they examine the relationship between two annotators and find patterns among synset . |
| Outcome: | The proposed method shows that the annotators agree on 38% of the synsets compared with the original synset . the results highlight similarities between the synnotated synset and the WordNet structure . |
Unsupervised Morphology Learning with Statistical Paradigms (C18-1)
Copied to clipboard
| Challenge: | Existing models treat words as concatenation of morphemes, but some use transformations like rewrite rules to recognize dependencies between morphs. |
| Approach: | They propose an unsupervised model that exploits the notion of paradigms for morphological segmentation that can be applied to a homogeneous set of words. |
| Outcome: | The proposed model significantly improves on the Morpho-Challenge dataset in English, Turkish, and Finnish. |