Retrieval-augmented generation (RAG) augments large language models (LLMs) with external knowledge to tackle knowledge-intensive question answering. While several benchmarks evaluate multimodal LLMs (MLLMs) under multimodal RAG settings, they predominantly retrieve from textual corpora and do not explicitly assess how models exploit visual evidence during answer generation. Consequently, there still lacks benchmark that cleanly isolates and measures the contribution of retrieved images in a visual knowledge-intensive RAG pipeline. We introduce Visual-RAG, a question-answering benchmark that targets visually-grounded, knowledge-intensive questions in a visual evidence-centric manner. Unlike prior work, Visual-RAG requires text-to-image retrieval and the integration of retrieved clue images whose pixel content explicitly encodes the visual knowledge necessary for answer generation. With Visual-RAG, we evaluate five open-source and three proprietary MLLMs and find that current systems still substantially underutilize the visual information available in retrieved images. Despite clear opportunities for multimodal evidence integration, state-of-the-art models struggle to extract and exploit fine-grained visual knowledge, and text-to-image retrieval itself remains challenging even under constrained entity-level corpora. These results underscore the need for improved visual retrieval, grounding, and attribution in multimodal RAG. Visual-RAG is publicly available at: github.com/visual-rag/visual-rag

Despite increasing research attention to text ranking, most studies focus on monolingual scenarios, with a particular emphasis on English-language contexts. This narrow focus limits the applicability of ranking models in cross-lingual contexts, such as ranking Chinese documents based on English queries. Recent advances in large language models (LLMs) have significantly reduced inter-language barriers through pre-training on extensive multilingual corpora, thus facilitating the study of multilingual text ranking (MTR). In this work, we explore the potential of LLMs in MTR tasks. Specifically, we first introduce an MTR benchmark encompassing both monolingual and cross-lingual scenarios. Then, we propose a two-stage training pipeline to alleviate the misalignment between LLMs and text ranking. Lastly, we adapt this training pipeline to multilingual scenarios from the perspective of training data and methods. Our experiments on the MTR benchmark demonstrate that the proposed multilingual two-stage training pipeline significantly improves LLM ranking performance in both monolingual and cross-lingual scenarios, particularly in out-domain settings. We complement these findings with a thorough analysis to deepen the understanding of our approach.

Named entity recognition (NER) is typically framed as a sequence labeling problem where the entity classes are inherently entangled together because the entity number and classes in a sentence are not known in advance, leaving the N-way K-shot NER problem so far unexplored. In our TKDE paper, we first formally define a more suitable N-way K-shot setting for NER. Then we propose FewNER, a novel meta-learning approach for few-shot NER. FewNER separates the entire network into a task-independent part and a task-specific part. During training in FewNER, the task-independent part is meta-learned across multiple tasks and the task-specific part is learned for each individual task in a low-dimensional space. At test time, FewNER keeps the task-independent part fixed and adapts to a new task via gradient descent by updating only the task-specific part, resulting in it being less prone to overfitting and more computationally efficient. Compared with pre-trained language models (e.g., BERT and ELMo) which obtain the transferability in an implicit manner (i.e., relying on large-scale corpora), FewNER explicitly optimizes the capability of "learning to adapt quickly" through meta-learning. The results demonstrate that FewNER achieves state-of-the-art performance against nine baseline methods by significant margins on three adaptation experiments (i.e., intra-domain cross-type, cross-domain intra-type and cross-domain cross-type).

Named entity recognition (NER) is the task to identify text spans that mention named entities, and to classify them into predefined categories such as person, location, organization, etc. In recent years, deep learning, empowered by continuous real-valued vector representations and semantic composition through nonlinear processing, has been employed in NER systems, yielding stat-of-the-art performance. In our TKDE paper, we provide a comprehensive review on existing deep learning techniques for NER. We first introduce NER resources, including tagged NER corpora and off-the-shelf NER tools. Then, we systematically categorize existing solutions based on a taxonomy along three axes: distributed representations for input, context encoder, and tag decoder. Next, we survey the most representative methods for deep learning in new NER problem settings and applications. Finally, we present readers with the challenges faced by NER systems and outline future directions in this area.

Recent neural architectures in sequence labeling have yielded state-of-the-art performance on single domain data such as newswires. However, they still suffer from (i) requiring massive amounts of training data to avoid overfitting; (ii) huge performance degradation when there is a domain shift in the data distribution between training and testing. In this paper, we investigate the problem of domain adaptation for sequence labeling under homogeneous and heterogeneous settings. We propose MetaSeq, a novel meta-learning approach for domain adaptation in sequence labeling. Specifically, MetaSeq incorporates meta-learning and adversarial training strategies to encourage robust, general and transferable representations for sequence labeling. The key advantage of MetaSeq is that it is capable of adapting to new unseen domains with a small amount of annotated data from those domains. We extensively evaluate MetaSeq on named entity recognition, part-of-speech tagging and slot filling tasks under homogeneous and heterogeneous settings. The experimental results show that MetaSeq achieves state-of-the-art performance against eight baselines. Impressively, MetaSeq surpasses the in-domain performance using only 16.17% and 7% of target domain data on average for homogeneous settings, and 34.76%, 24%, 22.5% of target domain data on average for heterogeneous settings.

Few-shot learning under the$N$-way$K$-shot setting (i.e.,$K$annotated samples for each of$N$classes) has been widely studied in relation extraction (e.g., FewRel) and image classification (e.g., Mini-ImageNet). Named entity recognition (NER) is typically framed as a sequence labeling problem where the entity classes are inherently entangled together because the entity number and classes in a sentence are not known in advance, leaving the$N$-way$K$-shot NER problem so far unexplored. In this paper, we first formally define a more suitable$N$-way$K$-shot setting for NER. Then we proposeFewNER, a novel meta-learning approach for few-shot NER.FewNERseparates the entire network into a task-independent part and a task-specific part. During training inFewNER, the task-independent part is meta-learned across multiple tasks and the task-specific part is learned for each individual task in a low-dimensional space. At test time,FewNERkeeps the task-independent part fixed and adapts to a new task via gradient descent by updating only the task-specific part, resulting in it being less prone to overfitting and more computationally efficient. Compared with pre-trained language models (e.g., BERT and ELMo) which obtain the transferability in an implicit manner (i.e., relying on large-scale corpora),FewNERexplicitly optimizes the capability of “learning to adapt quickly” through meta-learning. The results demonstrate thatFewNERachieves state-of-the-art performance against nine baseline methods by significant margins on three adaptation experiments (i.e., intra-domain cross-type, cross-domain intra-type and cross-domain cross-type).

Text segmentation is a fundamental task in natural language processing. Depending on the levels of granularity, the task can be defined as segmenting a document into topical segments, or segmenting a sentence into elementary discourse units (EDUs). Traditional solutions to the two tasks heavily rely on carefully designed features. The recently proposed neural models do not need manual feature engineering, but they either suffer from sparse boundary tags or cannot efficiently handle the issue of variable size output vocabulary. In light of such limitations, we propose a generic end-to-end segmentation model, namely${\mathrm{S}\scriptstyle{\mathrm{EG}}}{\mathrm{B}\scriptstyle{\mathrm{OT}}}$, which first uses a bidirectional recurrent neural network to encode an input text sequence.${\mathrm{S}\scriptstyle{\mathrm{EG}}}{\mathrm{B}\scriptstyle{\mathrm{OT}}}$then uses another recurrent neural networks, together with a pointer network, to select text boundaries in the input sequence. In this way,${\mathrm{S}\scriptstyle{\mathrm{EG}}}{\mathrm{B}\scriptstyle{\mathrm{OT}}}$does not require any hand-crafted features. More importantly,${\mathrm{S}\scriptstyle{\mathrm{EG}}}{\mathrm{B}\scriptstyle{\mathrm{OT}}}$inherently handles the issue of variable size output vocabulary and the issue of sparse boundary tags. In our experiments,${\mathrm{S}\scriptstyle{\mathrm{EG}}}{\mathrm{B}\scriptstyle{\mathrm{OT}}}$outperforms state-of-the-art models on two tasks: document-level topic segmentation and sentence-level EDU segmentation. As a downstream application, we further propose a hierarchical attention model for sentence-level sentiment analysis based on the outcomes of${\mathrm{S}\scriptstyle{\mathrm{EG}}}{\mathrm{B}\scriptstyle{\mathrm{OT}}}$. The hierarchical model can make full use of both word-level and EDU-level information simultaneously for sentence-level sentiment analysis. In particular, it can effectively exploit EDU-level information, such as the inner properties of EDUs, which cannot be fully encoded in word-level features. Experimental results show that our hierarchical model achieves new state-of-the-art results on the Movie Review and Stanford Sentiment Treebank benchmarks.

Named entity recognition (NER) is the task to identify mentions of rigid designators from text belonging to predefined semantic types such as person, location, organization etc. NER always serves as the foundation for many natural language applications such as question answering, text summarization, and machine translation. Early NER systems got a huge success in achieving good performance with the cost of human engineering in designing domain-specific features and rules. In recent years, deep learning, empowered by continuous real-valued vector representations and semantic composition through nonlinear processing, has been employed in NER systems, yielding stat-of-the-art performance. In this paper, we provide a comprehensive review on existing deep learning techniques for NER. We first introduce NER resources, including tagged NER corpora and off-the-shelf NER tools. Then, we systematically categorize existing works based on a taxonomy along three axes: distributed representations for input, context encoder, and tag decoder. Next, we survey the most representative methods for recent applied techniques of deep learning in new NER problem settings and applications. Finally, we present readers with the challenges faced by NER systems and outline future directions in this area.

In this paper, we focus on named entity boundary detection, which is to detect the start and end boundaries of an entity mention in text, without predicting its type. The detected entities are input to entity linking or fine-grained typing systems for semantic enrichment. We propose BdryBot, a recurrent neural network encoder-decoder framework with a pointer network to detect entity boundaries from a given sentence. The encoder considers both character-level representations and word-level embeddings to represent the input words. In this way, BdryBot does not require any hand-crafted features. Because of the pointer network, BdryBot overcomes the problem of variable size output vocabulary and the issue of sparse boundary tags. We conduct two sets of experiments, in-domain detection and cross-domain detection, on six datasets. Our results show that BdryBot achieves state-of-the-art performance against five baselines. In addition, our proposed approach can be further enhanced when incorporating contextualized language embeddings into token representations.

With the increasing popularity of location-aware social media services, next-Point-of-Interest (POI) recommendation has gained significant research interest. The key challenge of next-POI recommendation is to precisely learn users' sequential movements from sparse check-in data. To this end, various embedding methods have been proposed to learn the representations of check-in data in the Euclidean space. However, their ability to learn complex patterns, especially hierarchical structures, is limited by the dimensionality of the Euclidean space. To this end, we propose a new research direction that aims to learn the representations of check-in activities in a hyperbolic space, which yields two advantages. First, it can effectively capture the underlying hierarchical structures, which are implied by the power-law distributions of user movements. Second, it provides high representative strength and enables the check-in data to be effectively represented in a low-dimensional space. Specifically, to solve the next-POI recommendation task, we propose a novel hyperbolic metric embedding (HME) model, which projects the check-in data into a hyperbolic space. The HME jointly captures sequential transition, user preference, category and region information in a unified approach by learning embeddings in a shared hyperbolic space. To the best of our knowledge, this is the first study to explore a non-Euclidean embedding model for next-POI recommendation. We conduct extensive experiments on three check-in datasets to demonstrate the superiority of our hyperbolic embedding approach over the state-of-the-art next-POI recommendation algorithms. Moreover, we conduct experiments on another four online transaction datasets for next-item recommendation to further demonstrate the generality of our proposed model.

Recent neural architectures in named entity recognition (NER) have yielded state-of-the-art performance on single domain data such as newswires. However, they still suffer from (i) requiring massive amounts of training data to avoid overfitting; (ii) huge performance degradation when there is a domain shift in the data distribution between training and testing. In this paper, we investigate the problem of domain adaptation for NER under homogeneous and heterogeneous settings. We propose MetaNER, a novel meta-learning approach for domain adaptation in NER. Specifically, MetaNER incorporates meta-learning and adversarial training strategies to encourage robust, general and transferable representations for sequence labeling. The key advantage of MetaNER is that it is capable of adapting to new unseen domains with a small amount of annotated data from those domains. We extensively evaluate MetaNER on multiple datasets under homogeneous and heterogeneous settings. The experimental results show that MetaNER achieves state-of-the-art performance against eight baselines. Impressively, MetaNER surpasses the in-domain performance using only 16.17% and 34.76% of target domain data on average for homogeneous and heterogeneous settings, respectively.

In recent years, with the prevalence of social media and smart devices, people causally reveal their locations such as shops, hotels, and restaurants in their tweets. Recognizing and linking such fine-grained location mentions to well-defined location profiles are beneficial for retrieval and recommendation systems. In this paper, we propose DLocRL, a new deep learning pipeline for fine-grained location recognition and linking in tweets, and verify its effectiveness on a real-world Twitter dataset.

Application programming interface (API) documentation well describes an API and how to use it. However, official documentation does not describe "how not to use it" or the different kinds of errors when an API is used wrongly. Programming caveats are negative usages of an API. When these caveats are overlooked, errors may emerge, leading to heavy discussions on Q&A websites like Stack Overflow. In this demonstration, we present API Caveat Explorer, a search system to explore API caveats that are mined from large-scale unstructured discussions on Stack Overflow. API Caveat Explorer takes API-oriented queries such as "HashMap" and retrieves API caveats by text summarization techniques. API caveats are represented by sentences, which are context-independent, prominent, semantically diverse and non-redundant. The system provides a web-based interface that allows users to interactively explore the full picture of all discovered caveats of an API, and the details of each. The potential users of API Caveat Explorer are programmers and educators for learning and teaching APIs.

Negative caveats of application programming interfaces (APIs) are about “how not to use an API,” which are often absent from the official API documentation. When these caveats are overlooked, programming errors may emerge from misusing APIs, leading to heavy discussions on Q&A websites like Stack Overflow. If the overlooked caveats could be mined from these discussions, they would be beneficial for programmers to avoid misuse of APIs. However, it is challenging because the discussions are informal, redundant, and diverse. For this, for example, we propose Disca, a novel approach for automatically Distilling desirable API negativecaveats from unstructured Q&A discussions. Through sentence selection and prominent term clustering, Discaensures that distilled caveats are context‐independent, prominent, semantically diverse, and nonredundant. Quantitative evaluation in our experiments shows that the proposed Discasignificantly outperforms four text‐summarization techniques. We also show that the distilled API negative caveats could greatly augment API documentation through qualitative analysis.