paper-with-me

홈 › Papers

SASICM A Multi-Task Benchmark For Subtext Recognition

2021-06-13 · Hua Yan, Feng Han, Junyi An, Weikang Xiao, Jian Zhao, Furao Shen

Subtext is a kind of deep semantics which can be acquired after one or more rounds of expression transformation. As a popular way of expressing one's intentions, it is well worth studying. In this paper, we try to make computers understand whether there is a subtext by means of machine learning. We build a Chinese dataset whose source data comes from the popular social media (e.g. Weibo, Netease Music, Zhihu, and Bilibili). In addition, we also build a baseline model called SASICM to deal with subtext recognition. The F1 score of SASICMg, whose pretrained model is GloVe, is as high as 64.37%, which is 3.97% higher than that of BERT based model, 12.7% higher than that of traditional methods on average, including support vector machine, logistic regression classifier, maximum entropy classifier, naive bayes classifier and decision tree and 2.39% higher than that of the state-of-the-art, including MARIN and BTM. The F1 score of SASICMBERT, whose pretrained model is BERT, is 65.12%, which is 0.75% higher than that of SASICMg. The accuracy rates of SASICMg and SASICMBERT are 71.16% and 70.76%, respectively, which can compete with those of other methods which are mentioned before.

📄 PDF Abstract BibTeX arXiv:2106.06944

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Adam 설명 없음
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
GloVe GloVe Embeddings are a type of word embedding that encode the co-occurrence probability ratio between two words as vector differences. GloVe uses a weighted least squares…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

CSD: A Chinese Dataset for Subtext Problem

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Subtext is a kind of deep semantics which can be acquired after one or more rounds of expression transformation. As a popular way of expressing one's intentions, it is well worth studying. In this paper, we propose two s…

Beneath the Surface: Investigating LLMs' Capabilities for Communicating with Subtext

2026-04-07 · Kabir Ahuja, Yuxuan Li, Andrew Kyle Lampinen arxiv

Human communication is fundamentally creative, and often makes use of subtext -- implied meaning that goes beyond the literal content of the text. Here, we systematically study whether language models can use subtext in …

Reading Subtext: Evaluating Large Language Models on Short Story Summarization with Writers

2024-03-02 · Melanie Subbiah, Sean Zhang, Lydia B. Chilton, Kathleen McKeown

We evaluate recent Large Language Models (LLMs) on the challenging task of summarizing short stories, which can be lengthy, and include nuanced subtext or scrambled timelines. Importantly, we work directly with authors t…

Specificity

ViMU: Benchmarking Video Metaphorical Understanding

2026-05-14 · Qi Li, Xinchao Wang arxiv

Any new medium, once it emerges, is used for more than the transmission of overt content alone. The information it carries typically operates on two levels: one is the content directly presented, while the other is the s…

Fine-Grained Spatially Varying Material Selection in Images

2025-06-10 · Julia Guerrero-Viu, Michael Fischer, Iliyan Georgiev, Elena Garces 외

Selection is the first step in many image editing processes, enabling faster and simpler modifications of all pixels sharing a common modality. In this work, we present a method for material selection in images, robust t…