Entity resolution has been an essential and well-studied task in data cleaning research for decades. Existing work has discussed the feasibility of utilizing pre-trained language models to perform entity resolution and achieved promising results. However, few works have discussed injecting domain knowledge to improve the performance of pre-trained language models on entity resolution tasks. In this study, we propose Knowledge Augmented Entity Resolution (KAER), a novel framework named for augmenting pre-trained language models with external knowledge for entity resolution. We discuss the results of utilizing different knowledge augmentation and prompting methods to improve entity resolution performance. Our model improves on Ditto, the existing state-of-the-art entity resolution method. In particular, 1) KAER performs more robustly and achieves better results on "dirty data", and 2) with more general knowledge injection, KAER outperforms the existing baseline models on the textual dataset and dataset from the online product domain. 3) KAER achieves competitive results on highly domain-specific datasets, such as citation datasets, requiring the injection of expert knowledge in future work.
Chatbots are expected to be knowledgeable across multiple domains, e.g. for daily chit-chat, exchange of information, and grounding in emotional situations. To effectively measure the quality of such conversational agents, a model-based automatic dialogue evaluation metric (ADEM) is expected to perform well across multiple domains. Despite significant progress, an ADEM that works well in one domain does not necessarily generalize to another. This calls for a dedicated network architecture for domain generalization. To tackle the multi-domain dialogue evaluation task, we propose a Panel of Experts (PoE), a multitask network that consists of a shared transformer encoder and a collection of lightweight adapters. The shared encoder captures the general knowledge of dialogues across domains, while each adapter specializes in one specific domain and serves as a domain expert. To validate the idea, we construct a high-quality multi-domain dialogue dataset leveraging data augmentation and pseudo-labeling. The PoE network is comprehensively assessed on 16 dialogue evaluation datasets spanning a wide range of dialogue domains. It achieves state-of-the-art performance in terms of mean Spearman correlation over all the evaluation datasets. It exhibits better zero-shot generalization than existing state-of-the-art ADEMs and the ability to easily adapt to new domains with few-shot transfer learning.
Numerous Graph Neural Networks (GNNs) have been developed to tackle the challenge of Knowledge Graph Embedding (KGE). However, many of these approaches overlook the crucial role of relation information and inadequately integrate it with entity information, resulting in diminished expressive power. In this paper, we propose a novel knowledge graph encoder that incorporates tensor decomposition within the aggregation function of Relational Graph Convolutional Network (R-GCN). Our model enhances the representation of neighboring entities by employing projection matrices of a low-rank tensor defined by relation types. This approach facilitates multi-task learning, thereby generating relation-aware representations. Furthermore, we introduce a low-rank estimation technique for the core tensor through CP decomposition, which effectively compresses and regularizes our model. We adopt a training strategy inspired by contrastive learning, which relieves the training limitation of the 1-N method inherent in handling vast graphs. We outperformed all our competitors on two common benchmark datasets, FB15k-237 and WN18RR, while using low-dimensional embeddings for entities and relations.
Knowledge graph reasoning (KGR), aiming to deduce new facts from existing facts based on mined logic rules underlying knowledge graphs (KGs), has become a fast-growing research direction. It has been proven to significantly benefit the usage of KGs in many AI applications, such as question answering, recommendation systems, and etc. According to the graph types, existing KGR models can be roughly divided into three categories, i.e., static models, temporal models, and multi-modal models. Early works in this domain mainly focus on static KGR, and recent works try to leverage the temporal and multi-modal information, which are more practical and closer to real-world. However, no survey papers and open-source repositories comprehensively summarize and discuss models in this important direction. To fill the gap, we conduct a first survey for knowledge graph reasoning tracing from static to temporal and then to multi-modal KGs. Concretely, the models are reviewed based on bi-level taxonomy, i.e., top-level (graph types) and base-level (techniques and scenarios). Besides, the performances, as well as datasets, are summarized and presented. Moreover, we point out the challenges and potential opportunities to enlighten the readers. The corresponding open-source repository is shared on GitHub https://github.com/LIANGKE23/Awesome-Knowledge-Graph-Reasoning.
Recently, domain-specific PLMs have been proposed to boost the task performance of specific domains (e.g., biomedical and computer science) by continuing to pre-train general PLMs with domain-specific corpora. However, this Domain-Adaptive Pre-Training (DAPT; Gururangan et al. (2020)) tends to forget the previous general knowledge acquired by general PLMs, which leads to a catastrophic forgetting phenomenon and sub-optimal performance. To alleviate this problem, we propose a new framework of General Memory Augmented Pre-trained Language Model (G-MAP), which augments the domain-specific PLM by a memory representation built from the frozen general PLM without losing any general knowledge. Specifically, we propose a new memory-augmented layer, and based on it, different augmented strategies are explored to build the memory representation and then adaptively fuse it into the domain-specific PLM. We demonstrate the effectiveness of G-MAP on various domains (biomedical and computer science publications, news, and reviews) and different kinds (text classification, QA, NER) of tasks, and the extensive results show that the proposed G-MAP can achieve SOTA results on all tasks.
Deep transfer learning (DTL) has formed a long-term quest toward enabling deep neural networks (DNNs) to reuse historical experiences as efficiently as humans. This ability is named knowledge transferability. A commonly used paradigm for DTL is firstly learning general knowledge (pre-training) and then reusing (fine-tuning) them for a specific target task. There are two consensuses of transferability of pre-trained DNNs: (1) a larger domain gap between pre-training and downstream data brings lower transferability; (2) the transferability gradually decreases from lower layers (near input) to higher layers (near output). However, these consensuses were basically drawn from the experiments based on natural images, which limits their scope of application. This work aims to study and complement them from a broader perspective by proposing a method to measure the transferability of pre-trained DNN parameters. Our experiments on twelve diverse image classification datasets get similar conclusions to the previous consensuses. More importantly, two new findings are presented, i.e., (1) in addition to the domain gap, a larger data amount and huge dataset diversity of downstream target task also prohibit the transferability; (2) although the lower layers learn basic image features, they are usually not the most transferable layers due to their domain sensitivity.
Software has been developed for knowledge discovery, prediction and management for over 30 years. However, there are still unresolved pain points when using existing project development and artifact management methodologies. Historically, there has been a lack of applicable methodologies. Further, methodologies that have been applied, such as Agile, have several limitations including scientific unfalsifiability that reduce their applicability. Evident, a development methodology rooted in the philosophy of logical reasoning and EKB, a knowledge base topology, are proposed. Many pain points in data mining, machine learning and general knowledge management are alleviated conceptually. Evident can be extended potentially to accelerate philosophical exploration, science discovery, education as well as knowledge sharing & retention across the globe. EKB offers one solution of storing information as knowledge, a granular level above data. Related topics in computer history, software engineering, database, sensor, philosophy, and project & organization & military managements are also discussed.
DETR is a novel end-to-end transformer architecture object detector, which significantly outperforms classic detectors when scaling up the model size. In this paper, we focus on the compression of DETR with knowledge distillation. While knowledge distillation has been well-studied in classic detectors, there is a lack of researches on how to make it work effectively on DETR. We first provide experimental and theoretical analysis to point out that the main challenge in DETR distillation is the lack of consistent distillation points. Distillation points refer to the corresponding inputs of the predictions for student to mimic, and reliable distillation requires sufficient distillation points which are consistent between teacher and student. Based on this observation, we propose a general knowledge distillation paradigm for DETR(KD-DETR) with consistent distillation points sampling. Specifically, we decouple detection and distillation tasks by introducing a set of specialized object queries to construct distillation points. In this paradigm, we further propose a general-to-specific distillation points sampling strategy to explore the extensibility of KD-DETR. Extensive experiments on different DETR architectures with various scales of backbones and transformer layers validate the effectiveness and generalization of KD-DETR. KD-DETR boosts the performance of DAB-DETR with ResNet-18 and ResNet-50 backbone to 41.4$\%$, 45.7$\%$ mAP, respectively, which are 5.2$\%$, 3.5$\%$ higher than the baseline, and ResNet-50 even surpasses the teacher model by $2.2\%$.
Recently it has been shown that without any access to the contextual passage, multiple choice reading comprehension (MCRC) systems are able to answer questions significantly better than random on average. These systems use their accumulated "world knowledge" to directly answer questions, rather than using information from the passage. This paper examines the possibility of exploiting this observation as a tool for test designers to ensure that the use of "world knowledge" is acceptable for a particular set of questions. We propose information-theory based metrics that enable the level of "world knowledge" exploited by systems to be assessed. Two metrics are described: the expected number of options, which measures whether a passage-free system can identify the answer a question using world knowledge; and the contextual mutual information, which measures the importance of context for a given question. We demonstrate that questions with low expected number of options, and hence answerable by the shortcut system, are often similarly answerable by humans without context. This highlights that the general knowledge 'shortcuts' could be equally used by exam candidates, and that our proposed metrics may be helpful for future test designers to monitor the quality of questions.
Dominance-based Rough Approach (DRSA) has been proposed as a machine learning and knowledge discovery methodology to handle Multiple Criteria Decision Aiding (MCDA). Due to its capacity of asking the decision maker (DM) for simple preference information and supplying easily understandable and explainable recommendations, DRSA gained much interest during the years and it is now one of the most appreciated MCDA approaches. In fact, it has been applied also beyond MCDA domain, as a general knowledge discovery and data mining methodology for the analysis of monotonic (and also non-monotonic) data. In this contribution, we recall the basic principles and the main concepts of DRSA, with a general overview of its developments and software. We present also a historical reconstruction of the genesis of the methodology, with a specific focus on the contribution of Roman S{\l}owi\'nski.
Deep learning-based language models (LMs) have transcended the gold standard (human baseline) of SQuAD 1.1 and GLUE benchmarks in April and July 2019, respectively. As of 2022, the top five LMs on the SuperGLUE benchmark leaderboard have exceeded the gold standard. Even people with good general knowledge will struggle to solve problems in specialized fields such as medicine and artificial intelligence. Just as humans learn specialized knowledge through bachelor’s, master’s, and doctoral courses, LMs also require a process to develop the ability to understand domain specific knowledge. Thus, this study proposes SciDeBERTa and SciDeBERTa(CS) as a pre-trained LM (PLM) specialized in the science technology domain. We further pretrain the DeBERTa, which was trained with a general corpus, with the science technology domain corpus. Experiments verified that SciDeBERTa(CS) continually pre-trained in the computer science domain achieved 3.53% and 2.17% higher accuracies than SciBERT and S2ORC-SciBERT, respectively, which are science technology domain specialized PLMs, in the task of recognizing entity names in SciERC dataset. In the JRE task of the SciERC dataset, SciDeBERTa(CS) demonstrated a 6.7% higher performance than baseline SCIIE. In the Genia dataset, SciDeBERTa achieved the best performance compared to S2ORC-SciBERT, SciBERT, BERT, DeBERTa and SciDeBERTa(CS). Furthermore, re-initialization technology and optimizers after Adam were explored during fine-tuning to verify the language understanding of PLMs.
Knowledge graphs (KG) are used in a wide range of applications. The automation of KG generation is very desired due to the data volume and variety in industries. One important approach of KG generation is to map the raw data to a given KG schema, namely a domain ontology, and construct the entities and properties according to the ontology. However, the automatic generation of such ontology is demanding and existing solutions are often not satisfactory. An important challenge is a trade-off between two principles of ontology engineering: knowledge-orientation and data-orientation. The former one prescribes that an ontology should model the general knowledge of a domain, while the latter one emphasises on reflecting the data specificities to ensure good usability. We address this challenge by our method of ontology reshaping, which automates the process of converting a given domain ontology to a smaller ontology that serves as the KG schema. The domain ontology can be designed to be knowledge-oriented and the KG schema covers the data specificities. In addition, our approach allows the option of including user preferences in the loop. We demonstrate our on-going research on ontology reshaping and present an evaluation using real industrial data, with promising results.
Prompt Transfer (PoT) is a recently-proposed approach to improve prompt-tuning, by initializing the target prompt with the existing prompt trained on similar source tasks. However, such a vanilla PoT approach usually achieves sub-optimal performance, as (i) the PoT is sensitive to the similarity of source-target pair and (ii) directly fine-tuning the prompt initialized with source prompt on target task might lead to forgetting of the useful general knowledge learned from source task. To tackle these issues, we propose a new metric to accurately predict the prompt transferability (regarding (i)), and a novel PoT approach (namely PANDA) that leverages the knowledge distillation technique to alleviate the knowledge forgetting effectively (regarding (ii)). Extensive and systematic experiments on 189 combinations of 21 source and 9 target datasets across 5 scales of PLMs demonstrate that: 1) our proposed metric works well to predict the prompt transferability; 2) our PANDA consistently outperforms the vanilla PoT approach by 2.3% average score (up to 24.1%) among all tasks and model sizes; 3) with our PANDA approach, prompt-tuning can achieve competitive and even better performance than model-tuning in various PLM scales scenarios. We have publicly released our code in https://github.com/WHU-ZQH/PANDA.
With the emergence of large pre-trained vison-language model like CLIP, transferable representations can be adapted to a wide range of downstream tasks via prompt tuning. Prompt tuning tries to probe the beneficial information for downstream tasks from the general knowledge stored in the pre-trained model. A recently proposed method named Context Optimization (CoOp) introduces a set of learnable vectors as text prompt from the language side. However, tuning the text prompt alone can only adjust the synthesized "classifier", while the computed visual features of the image encoder can not be affected , thus leading to sub-optimal solutions. In this paper, we propose a novel Dual-modality Prompt Tuning (DPT) paradigm through learning text and visual prompts simultaneously. To make the final image feature concentrate more on the target visual concept, a Class-Aware Visual Prompt Tuning (CAVPT) scheme is further proposed in our DPT, where the class-aware visual prompt is generated dynamically by performing the cross attention between text prompts features and image patch token embeddings to encode both the downstream task-related information and visual instance information. Extensive experimental results on 11 datasets demonstrate the effectiveness and generalization ability of the proposed method. Our code is available in https://github.com/fanrena/DPT.
A recent trend in binary code analysis promotes the use of neural solutions based on instruction embedding models. An instruction embedding model is a neural network that transforms sequences of assembly instructions into embedding vectors. If the embedding network is trained such that the translation from code to vectors partially preserves the semantic, the network effectively represents an assembly code model. In this paper we present BinBert, a novel assembly code model. BinBert is built on a transformer pre-trained on a huge dataset of both assembly instruction sequences and symbolic execution information. BinBert can be applied to assembly instructions sequences and it is fine-tunable, i.e. it can be re-trained as part of a neural architecture on task-specific data. Through fine-tuning, BinBert learns how to apply the general knowledge acquired with pre-training to the specific task. We evaluated BinBert on a multi-task benchmark that we specifically designed to test the understanding of assembly code. The benchmark is composed of several tasks, some taken from the literature, and a few novel tasks that we designed, with a mix of intrinsic and downstream tasks. Our results show that BinBert outperforms state-of-the-art models for binary instruction embedding, raising the bar for binary code understanding.
We present an overview of the design and first proof-of-concept implementation for AIDA, an autonomous intelligent developer agent that develops software from scratch. AIDA takes a software requirements specification and uses reasoning over a semantic knowledge graph to interpret the requirements, then designs and writes software to satisfy them. AIDA uses both declarative and procedural knowledge in the core domains of data, algorithms, and code, plus some general knowledge. The reasoning codebase uses this knowledge to identify needed components, then designs and builds the necessary information structures around them that become the software. These structures, the motivating requirements, and the resulting source code itself are all new knowledge that are added to the knowledge graph, becoming available for future reasoning. In this way, AIDA also learns as she writes code and becomes more efficient when writing subsequent code.
While vision-and-language models perform well on tasks such as visual question answering, they struggle when it comes to basic human commonsense reasoning skills. In this work, we introduce WinoGAViL: an online game of vision-and-language associations (e.g., between werewolves and a full moon), used as a dynamic evaluation benchmark. Inspired by the popular card game Codenames, a spymaster gives a textual cue related to several visual candidates, and another player tries to identify them. Human players are rewarded for creating associations that are challenging for a rival AI model but still solvable by other human players. We use the game to collect 3.5K instances, finding that they are intuitive for humans (>90% Jaccard index) but challenging for state-of-the-art AI models, where the best model (ViLT) achieves a score of 52%, succeeding mostly where the cue is visually salient. Our analysis as well as the feedback we collect from players indicate that the collected associations require diverse reasoning skills, including general knowledge, common sense, abstraction, and more. We release the dataset, the code and the interactive game, allowing future data collection that can be used to develop models with better association abilities.
Life-long learning aims at learning a sequence of tasks without forgetting the previously acquired knowledge. However, the involved training data may not be life-long legitimate due to privacy or copyright reasons. In practical scenarios, for instance, the model owner may wish to enable or disable the knowledge of specific tasks or specific samples from time to time. Such flexible control over knowledge transfer, unfortunately, has been largely overlooked in previous incremental or decremental learning methods, even at a problem-setup level. In this paper, we explore a novel learning scheme, termed as Learning wIth Recoverable Forgetting (LIRF), that explicitly handles the task- or sample-specific knowledge removal and recovery. Specifically, LIRF brings in two innovative schemes, namely knowledge deposit and withdrawal, which allow for isolating user-designated knowledge from a pre-trained network and injecting it back when necessary. During the knowledge deposit process, the specified knowledge is extracted from the target network and stored in a deposit module, while the insensitive or general knowledge of the target network is preserved and further augmented. During knowledge withdrawal, the taken-off knowledge is added back to the target network. The deposit and withdraw processes only demand for a few epochs of finetuning on the removal data, ensuring both data and time efficiency. We conduct experiments on several datasets, and demonstrate that the proposed LIRF strategy yields encouraging results with gratifying generalization capability.
The Chinese character riddle is a unique form of cultural entertainment specific to the Chinese language. It typically comprises two parts: the riddle description and the solution. The solution to the riddle is a single character, while the riddle description primarily describes the glyph of the solution, occasionally supplemented with its explanation and pronunciation. Solving Chinese character riddles is a challenging task that demands understanding of character glyph, general knowledge, and a grasp of figurative language. In this paper, we construct a \textbf{C}hinese \textbf{C}haracter riddle dataset named CC-Riddle, which covers the majority of common simplified Chinese characters. The construction process is a combination of web crawling, language model generation and manual filtering. In generation stage, we input the Chinese phonetic alphabet, glyph and meaning of the solution character into the generation model, which then produces multiple riddle descriptions. The generated riddles are then manually filtered and the final CC-Riddle dataset is composed of both human-written riddles and these filtered, generated riddles. In order to assess the performance of language models on the task of solving character riddles, we use retrieval-based, generative and multiple-choice QA strategies to test three language models: BERT, ChatGPT and ChatGLM. The test results reveal that current language models still struggle to solve Chinese character riddles. CC-Riddle is publicly available at \url{https://github.com/pku0xff/CC-Riddle}.
Cross-domain recommendation (CDR) can help customers find more satisfying items in different domains. Existing CDR models mainly use common users or mapping functions as bridges between domains but have very limited exploration in fully utilizing extra knowledge across domains. In this paper, we propose to incorporate the knowledge graph (KG) for CDR, which enables items in different domains to share knowledge. To this end, we first construct a new dataset AmazonKG4CDR from the Freebase KG and a subset (two domain pairs: movies-music, movie-book) of Amazon Review Data. This new dataset facilitates linking knowledge to bridge within- and cross-domain items for CDR. Then we propose a new framework, KG-aware Neural Collective Matrix Factorization (KG-NeuCMF), leveraging KG to enrich item representations. It first learns item embeddings by graph convolutional autoencoder to capture both domain-specific and domain-general knowledge from adjacent and higher-order neighbours in the KG. Then, we maximize the mutual information between item embeddings learned from the KG and user-item matrix to establish cross-domain relationships for better CDR. Finally, we conduct extensive experiments on the newly constructed dataset and demonstrate that our model significantly outperforms the best-performing baselines.