Prompt-based methods have been widely used in few-shot named entity recognition (NER). In this paper, we first conduct a preliminary experiment and observe that the key to affecting the performance of prompt-based NER models is the capability to detect entity boundaries. However, most existing models fail to boost such capability. To solve the issue, we propose a novel model, ParaBART, which consists of a BART encoder and a specially designed parabiotic decoder. Specifically, the parabiotic decoder includes two BART decoders and a conjoint module. The two decoders are responsible for entity boundary detection and entity type classification, respectively. They are connected by the conjoint module, which is used to replace unimportant tokens’ embeddings in one decoder with the average embedding of all the tokens in the other. We further present a novel boundary expansion strategy to enhance the model’s capability in entity type classification. Experimental results show that ParaBART can achieve significant performance gains over state-of-the-art competitors.

Out-of-domain (OOD) intent detection aims to examine whether the user’s query falls outside the predefined domain of the system, which is crucial for the proper functioning of task-oriented dialogue (TOD) systems. Previous methods address it by fine-tuning discriminative models. Recently, some studies have been exploring the application of large language models (LLMs) represented by ChatGPT to various downstream tasks, but it is still unclear for their ability on OOD detection task.This paper conducts a comprehensive evaluation of LLMs under various experimental settings, and then outline the strengths and weaknesses of LLMs. We find that LLMs exhibit strong zero-shot and few-shot capabilities, but is still at a disadvantage compared to models fine-tuned with full resource. More deeply, through a series of additional analysis experiments, we discuss and summarize the challenges faced by LLMs and provide guidance for future work including injecting domain knowledge, strengthening knowledge transfer from IND(In-domain) to OOD, and understanding long instructions.

Peng Ding, Jun Kuang, Dan Ma, Xuezhi Cao, Yunsen Xian, Jiajun Chen, Shujian Huang. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

Open information extraction (OpenIE) aims to extract the schema-free triplets in the form of (subject, predicate, object) from a given sentence. Compared with general information extraction (IE), OpenIE poses more challenges for the IE models, especially when multiple complicated triplets exist in a sentence. To extract these complicated triplets more effectively, in this paper we propose a novel generative OpenIE model, namely DualOIE, which achieves a dual task at the same time as extracting some triplets from the sentence, i.e., converting the triplets into the sentence. Such dual task encourages the model to correctly recognize the structure of the given sentence and thus is helpful to extract all potential triplets from the sentence. Specifically, DualOIE extracts the triplets in two steps: 1) first extracting a sequence of all potential predicates, 2) then using the predicate sequence as a prompt to induce the generation of triplets. Our experiments on two benchmarks and our dataset constructed from Meituan demonstrate that DualOIE achieves the best performance among the state-of-the-art baselines. Furthermore, the online A/B test on Meituan platform shows that 0.93% improvement of QV-CTR and 0.56% improvement of UV-CTR have been obtained when the triplets extracted by DualOIE were leveraged in Meituan's search system.

Jiduan Liu, Jiahao Liu, Qifan Wang, Jingang Wang, Wei Wu, Yunsen Xian, Dongyan Zhao, Kai Chen, Rui Yan. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

Yutao Mou, Xiaoshuai Song, Keqing He, Chen Zeng, Pei Wang, Jingang Wang, Yunsen Xian, Weiran Xu. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

Weihao Zeng, Keqing He, Yejie Wang, Chen Zeng, Jingang Wang, Yunsen Xian, Weiran Xu. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

Chen Zhang, Yang Yang, Jiahao Liu, Jingang Wang, Yunsen Xian, Benyou Wang, Dawei Song. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

Knowledge Base Question Answering (KBQA) aims to answer natural language questions with factual information such as entities and relations in KBs. However, traditional Pre-trained Language Models (PLMs) are directly pre-trained on large-scale natural language corpus, which poses challenges for them in understanding and representing complex subgraphs in structured KBs. To bridge the gap between texts and structured KBs, we propose a Structured Knowledge-aware Pre-training method (SKP). In the pre-training stage, we introduce two novel structured knowledge-aware tasks, guiding the model to effectively learn the implicit relationship and better representations of complex subgraphs. In downstream KBQA task, we further design an efficient linearization strategy and an interval attention mechanism, which assist the model to better encode complex subgraphs and shield the interference of irrelevant subgraphs during reasoning respectively. Detailed experiments and analyses on WebQSP verify the effectiveness of SKP, especially the significant improvement in subgraph retrieval (+4.08% H@10).

Self-attention, which allows transformers to capture deep bidirectional contexts, plays a vital role in BERT-like pre-trained language models. However, the maximum likelihood pre-training objective of BERT may produce an anisotropic word embedding space, which leads to biased attention scores for high-frequency tokens, as they are very close to each other in representation space and thus have higher similarities. This bias may ultimately affect the encoding of global contextual information. To address this issue, we propose TOCOL, a TOken-Level COntrastive Learning framework for improving the contextual representation of pre-trained language models, which integrates a novel self-supervised objective to the attention mechanism to reshape the word representation space and encourages PLM to capture the global semantics of sentences. Results on the GLUE Benchmark show that TOCOL brings considerable improvement over the original BERT. Furthermore, we conduct a detailed analysis and demonstrate the robustness of our approach for low-resource scenarios.

Xiaoshuai Song, Keqing He, Pei Wang, Guanting Dong, Yutao Mou, Jingang Wang, Yunsen Xian, Xunliang Cai, Weiran Xu. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.

Taxonomy expansion task is essential in organizing the ever-increasing volume of new concepts into existing taxonomies. Most existing methods focus exclusively on using textual semantics, leading to an inability to generalize to unseen terms and the "Prototypical Hypernym Problem." In this paper, we propose Visual Taxonomy Expansion (VTE), introducing visual features into the taxonomy expansion task. We propose a textual hypernymy learning task and a visual prototype learning task to cluster textual and visual semantics. In addition to the tasks on respective modalities, we introduce a hyper-proto constraint that integrates textual and visual semantics to produce fine-grained visual semantics. Our method is evaluated on two datasets, where we obtain compelling results. Specifically, on the Chinese taxonomy dataset, our method significantly improves accuracy by 8.75%. Additionally, our approach performs better than ChatGPT on the Chinese taxonomy dataset.

The sequential recommendation task aims to predict the item that user is interested in according to his/her historical action sequence. However, inevitable random action, i.e. user randomly accesses an item among multiple candidates or clicks several items at random order, cause the sequence fails to provide stable and high-quality signals. To alleviate the issue, we propose the StatisTics-Driven Pre-traing framework (called STDP briefly). The main idea of the work lies in the exploration of utilizing the statistics information along with the pre-training paradigm to stabilize the optimization of recommendation model. Specifically, we derive two types of statistical information: item co-occurrence across sequence and attribute frequency within the sequence. And we design the following pre-training tasks: 1) The co-occurred items prediction task, which encourages the model to distribute its attention on multiple suitable targets instead of just focusing on the next item that may be unstable. 2) We generate a paired sequence by replacing items with their co-occurred items and enforce its representation close with the original one, thus enhancing the model’s robustness to the random noise. 3) To reduce the impact of random on user’s long-term preferences, we encourage the model to capture sequence-level frequent attributes. The significant improvement over six datasets demonstrates the effectiveness and superiority of the proposal, and further analysis verified the generalization of the STDP framework on other models.

Industrial search and recommendation systems mostly follow the classic multi-stage information retrieval paradigm: matching, pre-ranking, ranking, and re-ranking stages. To account for system efficiency, simple vector-product based models are commonly deployed in the pre-ranking stage. Recent works consider distilling the high knowledge of large ranking models to small pre-ranking models for better effectiveness. However, two major challenges in pre-ranking system still exist: (i) without explicitly modeling the performance gain versus computation cost, the predefined latency constraint in the pre-ranking stage inevitably leads to suboptimal solutions; (ii) transferring the ranking teacher's knowledge to a pre-ranking student with a predetermined handcrafted architecture still suffers from the loss of model performance. In this work, a novel framework AutoFAS is proposed which jointly optimizes the efficiency and effectiveness of the pre-ranking model: (i) AutoFAS for the first time simultaneously selects the most valuable features and network architectures using Neural Architecture Search (NAS) technique; (ii) equipped with ranking model guided reward during NAS procedure, AutoFAS can select the best pre-ranking architecture for a given ranking teacher without any computation overhead. Experimental results in our real world search system show AutoFAS consistently outperforms the previous state-of-the-art (SOTA) approaches at a lower computing cost. Notably, our model has been adopted in the pre-ranking module in the search system of Meituan, bringing significant improvements.