Titlebook: Chinese Computational Linguistics; 21st China National Maosong Sun,Yang Liu,Yubo Chen Conference proceedings 2022 The Editor(s) (if applic

Hot-Flash

ConIsI: A Contrastive Framework with Inter-sentence Interaction for Self-supervised Sentence Represection strategies to explore its effect. We conduct experiments on seven Semantic Textual Similarity (STS) tasks. The experimental results show that our ConIsI models based on . and . achieve state-of-the-art performance, substantially outperforming previous best models SimCSE-. and SimCSE-. by 2.05%

Abominate

Terminal

Using Extracted Emotion Cause to Improve Content-Relevance for Empathetic Conversation Generation emotion cause into the generation process. To this end, we present an emotion cause extractor using a semi-supervised training method and an empathetic conversation generator using a biased self-attention mechanism to overcome these two issues. Experimental results indicate that our proposed emotio

知識(shí)

To Adapt or to Fine-Tune: A Case Study on Abstractive Summarizationtuning under extremely low-resource conditions. We further provide insights on multilinguality, model convergence, and robustness, hoping to shed light on the pragmatic choice of fine-tuning or adapters in abstractive summarization.

habitat

Improving Event Temporal Relation Classification via Auxiliary Label-Aware Contrastive Learning and design three patient strategies. Thirdly we design a label-aware contrastive learning loss function. Extensive experimental results show that our TempACL effectively adapts contrastive learning to supervised learning tasks which remain a challenge in practice. TempACL achieves new state-of-the-

炸壞

Towards Making the Most of Pre-trained Translation Model for Quality Estimationoise to the target side of parallel data, and the model is trained to detect and recover the introduced noise. Both strategies can adapt the pre-trained translation model to the QE-style prediction task. Experimental results show that our model achieves impressive results, significantly outperformin

咽下

expunge

DIFM: An Effective Deep Interaction and Fusion Model for Sentence Matchingations in natural language processing tasks such as reading comprehension, question and answer systems. The main approach is to compute the interaction between text representations and sentence pairs through an attention mechanism, which can extract the semantic information between sentence pairs we

heterogeneous

ConIsI: A Contrastive Framework with Inter-sentence Interaction for Self-supervised Sentence Represeined high-quality sentence representation based on contrastive learning from pre-trained models. However, these works suffer the inconsistency of input forms between the pre-training and fine-tuning stages. Also, they typically encode a sentence independently and lack feature interaction between sen

oracle

Data Synthesis and Iterative Refinement for Neural Semantic Parsing without Annotated Logical Formsabeled data. In this paper, we propose a data synthesis and iterative refinement framework for neural semantic parsing, which can build semantic parsers without annotated logical forms. We first generate a naive corpus by sampling logic forms from knowledge bases and synthesizing their canonical utt