Verifying fact on semi-structured evidence like tables requires the ability to encode structural information and perform symbolic reasoning.
CQG employs a simple method to generate the multi-hop questions that contain key entities in multi-hop reasoning chains, which ensure the complexity and quality of the questions.
The key challenge of question answering over knowledge bases (KBQA) is the inconsistency between the natural language questions and the reasoning paths in the knowledge base (KB).
Recent works on Lottery Ticket Hypothesis have shown that pre-trained language models (PLMs) contain smaller matching subnetworks(winning tickets) which are capable of reaching accuracy comparable to the original models.
A wide range of NLP tasks benefit from the fine-tuning of pretrained language models (PLMs).
Transformer-based pre-trained models like BERT have achieved great progress on Semantic Sentence Matching.
To alleviate this problem, we propose a novel Dual Attention Enhanced BERT (DABERT) to enhance the ability of BERT to capture fine-grained differences in sentence pairs.
Inspired by the human learning process, in this paper, we introduce Imitation DEMOnstration Learning (Imitation-Demo) to strengthen demonstration learning via explicitly imitating human review behaviour, which includes: (1) contrastive learning mechanism to concentrate on the similar demonstrations.
Input distribution shift is one of the vital problems in unsupervised domain adaptation (UDA).
Recently, prompt-based methods have achieved significant performance in few-shot learning scenarios by bridging the gap between language model pre-training and fine-tuning for downstream tasks.
Conversational text-to-SQL aims at converting multi-turn natural language queries into their corresponding SQL (Structured Query Language) representations.
Ranked #2 on Text-To-Sql on SParC
To solve this issue, various data augmentation techniques are proposed to improve the robustness of PLMs.
Learning high-quality sentence representations benefits a wide range of natural language processing tasks.
Weakly supervised machine reading comprehension (MRC) task is practical and promising for its easily available and massive training data, but inevitablely introduces noise.
Most of the existing CRS methods focus on learning effective preference representations for users from conversation data alone.
To tackle this problem, we propose the model S^3-Rec, which stands for Self-Supervised learning for Sequential Recommendation, based on the self-attentive neural architecture.
In this work, we reexamine the inter-related problems of "topic identification" and "text segmentation" for sparse document learning, when there is a single new text of interest.