Open-vocabulary slots, such as file name, album name, or schedule title, significantly degrade the performance of neural-based slot filling models since these slots can take on values from a virtually unlimited set and have no semantic restriction nor a length limit.
Abstractive dialogue summarization suffers from a lots of factual errors, which are due to scattered salient elements in the multi-speaker information interaction process.
Although abstractive summarization models have achieved impressive results on document summarization tasks, their performance on dialogue modeling is much less satisfactory due to the crude and straight methods for dialogue encoding.
Discovering Out-of-Domain(OOD) intents is essential for developing new skills in a task-oriented dialogue system.
Based on the artificial dataset, we train an evaluation model that can not only make accurate and robust factual consistency discrimination but is also capable of making interpretable factual errors tracing by backpropagated gradient distribution on token embeddings.
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).
In this paper, we propose a robust contrastive alignment method to align text classification features of various domains in the same feature space by supervised contrastive learning.
The most advanced abstractive dialogue summarizers lack generalization ability on new domains and the existing researches for domain adaptation in summarization generally rely on large-scale pre-trainings.
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.
Previous dialogue summarization datasets mainly focus on open-domain chitchat dialogues, while summarization datasets for the broadly used task-oriented dialogue haven't been explored yet.
Zero-shot cross-domain slot filling alleviates the data dependence in the case of data scarcity in the target domain, which has aroused extensive research.
In this paper, we propose an adversarial disentangled debiasing model to dynamically decouple social bias attributes from the intermediate representations trained on the main task.
Detecting Out-of-Domain (OOD) or unknown intents from user queries is essential in a task-oriented dialog system.
Existing slot filling models can only recognize pre-defined in-domain slot types from a limited slot set.
Learning high-quality sentence representations benefits a wide range of natural language processing tasks.
In this paper, we present a Knowledge Graph Enhanced Dual-Copy network (KGEDC), a novel framework for abstractive dialogue summarization with conversational structure and factual knowledge.
Detecting out-of-domain (OOD) input intents is critical in the task-oriented dialog system.
In this paper, we propose a Contrastive Zero-Shot Learning with Adversarial Attack (CZSL-Adv) method for the cross-domain slot filling.
A masked graph self-attention mechanism is used to integrate cross-sentence information flows and focus more on the related utterances, which makes it better to understand the dialogue.
Large-scale knowledge graphs (KGs) are shown to become more important in current information systems.
In this paper, we propose a salient-context based semantic matching method to improve relevance ranking in information retrieval.
Then, we introduce a Key Information Guide Network (KIGN), which encodes the keywords to the key information representation, to guide the process of generation.
Ranked #10 on Text Summarization on CNN / Daily Mail (Anonymized)
Distant supervision can effectively label data for relation extraction, but suffers from the noise labeling problem.
The experimental results show that the proposed strategy significantly improves the performance of distant supervision comparing to state-of-the-art systems.
For Chinese word segmentation, the large-scale annotated corpora mainly focus on newswire and only a handful of annotated data is available in other domains such as patents and literature.
Word representation models have achieved great success in natural language processing tasks, such as relation classification.
Instead of directly relying on word alignment results, this framework combines advantages of rule-based methods and deep learning methods by implementing two steps: First, generates a high-confidence entity annotation set on IL side with strict searching methods; Second, uses this high-confidence set to weakly supervise the model training.