paper-with-me

Papers

Language Modeling with Sparse Product of Sememe Experts

2018-10-29 · EMNLP 2018 10 · Yihong Gu, Jun Yan, Hao Zhu, Zhiyuan Liu, Ruobing Xie, Maosong Sun, Fen Lin, Leyu Lin

Most language modeling methods rely on large-scale data to statistically learn the sequential patterns of words. In this paper, we argue that words are atomic language units but not necessarily atomic semantic units. Inspired by HowNet, we use sememes, the minimum semantic units in human languages, to represent the implicit semantics behind words for language modeling, named Sememe-Driven Language Model (SDLM). More specifically, to predict the next word, SDLM first estimates the sememe distribution gave textual context. Afterward, it regards each sememe as a distinct semantic expert, and these experts jointly identify the most probable senses and the corresponding word. In this way, SDLM enables language models to work beyond word-level manipulation to fine-grained sememe-level semantics and offers us more powerful tools to fine-tune language models and improve the interpretability as well as the robustness of language models. Experiments on language modeling and the downstream application of headline gener- ation demonstrate the significant effect of SDLM. Source code and data used in the experiments can be accessed at https:// github.com/thunlp/SDLM-pytorch.

📄 PDF Abstract BibTeX arXiv:1810.12387

Code (1)

thunlp/SDLM-pytorch 공식 구현 pytorch

Tasks

Language ModelingLanguage Modelling

Methods 이 논문이 사용한 방법론

Interpretability 설명 없음

Similar Papers 제목 키워드 기반

Improving Sequence Modeling Ability of Recurrent Neural Networks via Sememes

2019-10-20 · Yujia Qin, Fanchao Qi, Sicong Ouyang, Zhiyuan Liu 외

Sememes, the minimum semantic units of human languages, have been successfully utilized in various natural language processing applications. However, most existing studies exploit sememes in specific tasks and few effort…

Adversarial AttackLanguage ModelingLanguage ModellingNatural Language Inference+1

Enhancing Transformer with Sememe Knowledge

2020-07-01 · WS 2020 7 · Yuhui Zhang, Chenghao Yang, Zhengping Zhou, Zhiyuan Liu

While large-scale pretraining has achieved great success in many NLP tasks, it has not been fully studied whether external linguistic knowledge can improve data-driven models. In this work, we introduce sememe knowledge …

Language ModelingLanguage Modelling

Modeling Semantic Compositionality with Sememe Knowledge

2019-07-10 · ACL 2019 7 · Fanchao Qi, Jun-Jie Huang, Chenghao Yang, Zhiyuan Liu 외

Semantic compositionality (SC) refers to the phenomenon that the meaning of a complex linguistic unit can be composed of the meanings of its constituents. Most related works focus on using complicated compositionality fu…

multi-word expression embeddingmulti-word expression sememe prediction

Glyph Enhanced Chinese Character Pre-Training for Lexical Sememe Prediction

2021-11-01 · Findings (EMNLP) 2021 11 · Boer Lyu, Lu Chen, Kai Yu

Sememes are defined as the atomic units to describe the semantic meaning of concepts. Due to the difficulty of manually annotating sememes and the inconsistency of annotations between experts, the lexical sememe predicti…

Incorporating Sememes into Chinese Definition Modeling

2019-05-16 · Liner Yang, Cunliang Kong, Yun Chen, Yang Liu 외

Chinese definition modeling is a challenging task that generates a dictionary definition in Chinese for a given Chinese word. To accomplish this task, we construct the Chinese Definition Modeling Corpus (CDM), which cont…