Schema-adaptable Knowledge Graph Construction

Conventional Knowledge Graph Construction (KGC) approaches typically follow the static information extraction paradigm with a closed set of pre-defined schema . As a result, such approaches fall short when applied to dynamic scenarios or domains, whereas a new type of knowledge emerges. This necessitates a sys-tem that can handle evolving schema automatically to extract information for KGC. To address this need, we propose a new task called schema-adaptable KGC, which aims to continually extract entity, relation, and event based on a dynamically changing schema graph without re-training. We first split and convert existing datasets based on three principles to build a benchmark, i.e., horizontal schema expansion, vertical schema expansion, and hybrid schema expansion; then investigate the schema-adaptable performance of several well-known approaches such as Text2Event, TANL, UIE and GPT-3.5. We further propose a simple yet effective baseline dubbed A DA KGC, which contains schema-enriched prefix instructor and schema-conditioned dynamic decoding to better handle evolving schema. Comprehensive experimental results illustrate that A DA KGC can outperform baselines but still have room for improvement. We hope the proposed work can deliver benefits to the community 1 .

Note that existing information extraction systems can only handle a fixed number of classes by pre-defined schema and performing once-and-forall training on a fixed framework.It is desirable to respond to changes (e.g., evolving schema) to existing KGs, making the system act more "proactively" like humans who can handle flexible knowledge updates.Early, several approaches introduce incremental learning (Cao et al., 2020;Wang et al., 2019;Shen et al., 2020;Cui et al., 2021b) to learn new classes continually.In this case, the extraction system learns from the class incremental data stream but usually suffers significant performance degradation on the old class when adapting to the new class.Stated differently, previous studies put emphasis on struggling against catastrophic forgetting (Thrun, 1998).However, for the schemaevolving scenarios, the dynamic generalizability of extraction models plays a vital role and needs to be inspected from an ontology evolution perspective.
Therefore, we propose a novel KGC task dubbed schema-adaptable KGC, where the models are required to have the ability to represent and adapt to complement knowledge extraction.We first construct datasets according to three principles of evolutionary schema directions (Horizontal Schema Expansion, Vertical Schema Expansion, and Hybrid Schema Expansion) on three tasks of NER, RE 2 , and EE.Through empirical analysis, we notice that approaches of Text2Event (Lu et al., 2021), TANL (Paolini et al., 2021), UIE (Lu et al., 2022), and GPT-3.5 (Ouyang et al., 2022) cannot effectively extract the information given complex evolving schema.We argue that the major issues lie in the following: 1) How to learn dynamic and generalizable schema representations as conditions for extraction; 2) How to precisely extract new instances constrained with newly updated schema.
To this end, we propose a simple baseline dubbed ADAKGC, which introduces Schemaenriched Prefix Instructors (SPI) to represent and transfer the learnable schema-specific knowledge.At each iteration stage, we linearly convert from the current schema graph to learnable prompts, initialized with the ontology name and connected to taskspecific prefixes.To encourage the decoder to understand the dynamic schema, we utilize a Schemaconditioned Dynamic Decoding (SDD) strategy that constructs a decoding path of schema-specific vocabulary to the output space.When the schema changes, we dynamically construct a new trie-tree to adjust the output space.Note that ADAKGC is model agnostic and can handle a variety of challenging schema evolution scenarios.We summarize the contribution of this work as: • We introduce a new task of the schemaadaptable KGC to meet the schema evolution requirements, which is a new branch that has not been well-explored to the best of our knowledge.
• We propose a new baseline ADAKGC, which includes schema-enriched prefix instructors and schema-conditioned dynamic decoding strategy, and experimentally demonstrate the adaptability.
• We release the schema-adaptable KGC benchmark, which imposes new challenges and 2 We regard RE as relational triple extraction in this paper.
presents new research opportunities for the NLP community.
2 Problem Statement and Overview 2.1 Background of KGC KGC has been a promising research challenge (Lu et al., 2022;Zhang et al., 2022b), and existing benchmarks utilize a well-defined schema for directing knowledge graph construction, focusing on generating domain-specific knowledge graphs or aggregating heterogeneous structured databases.
For example, FEW-NERD (Ding et al., 2021) consists of coarse-grained and fine-grained entity type definitions to locate and classify named entities from unstructured natural language.NYT (Riedel et al., 2010a) extracts relational triple instances specifically from textual data sources according to a specific taxonomy structure.ACE2005 (Ntroduction) identifies triggers and event types based on context, and each has its own event arguments, described in a slot-filling way.In addition, TAC-KBP (Ellis et al., 2014) is designed to leverage existing generic domain structured data sources and extend entity links employing descriptive text as additional information.OAEI (Euzenat et al., 2011) creates an integrated ontology based on an alignment between two or more existing ontologies or knowledge graphs.In this paper, we focus on the work of extracting knowledge instances from unstructured text, which is regarded as the schema-constraint prediction (structure prediction) task.

Definition of Schema-adaptable KGC
In the real world, the KGC system extracts structured knowledge from unstructured text and normalizes it to the instance graph according to a frequently adjusted schema.Given a set of schema graphs S = {s 1 , s 2 , ..., s n }, the task of schemaadaptable KGC is to generate a set of schemaconstraint instances G = {g 1 , g 2 , ..., g n } for each iteration.Suppose there is a model M θ = LM (D 1 train |S 1 ) trained on the initial training set, after which labeled data for updated schema are not available.A schema-adaptable data stream D (1) , D (2) , . . ., D (N ) is provided to evaluate the adaptability of model for the dynamic updates of schema.Each D (k)  expected to perform well in each iteration of the test set D k test , which contains the golden instances changed for the updated schema.

Dataset Construction Process
As shown in Figure 2, we design three principles regarding different types of schema evolution and apply Algorithm 1 to build the dataset for evaluation: (1) Horizontal Schema Expansion requires the schema to add new class nodes of the same level, which can be considered a form of classincremental learning without new classe instances as training data.Based on the generalization effect on the neighboring new classes, we can assess the transfer capabilities of the schema feature.(2) Vertical Schema Expansion requires the schema to add subclasses of father classes.Based on the generalization effect on subclasses, we can assess the inheritance and derivation capabilities of the schema feature.(3) Hybrid Schema Expansion requires the schema to randomly expands nodes horizontally or vertically at each iteration, which summarizes schema graphs and represents their potential co-evolutionary pattern.More details are in Appendix A.1, besides the above structural extensions, we further explore analogous node replacement from the perspective of semantics.

Schema-adaptable KGC Benchmark
There are two challenges for schema-adaptable KGC.Firstly, since the schema is updated in each iteration, the schema evolution information needs to be dynamically injected into the model.Secondly, since the output target of KGC is often demandspecific, the extraction results should be adaptively Ouput iteration i dataset schema S i = S, instance D (i) = {D i dev , D i test } 8: end for adjusted according to the schema.We detail several vanilla baselines as follows and introduce the proposed ADAKGC in §3.
Vanilla Baselines: Schema-adaptable KGC can be thought of as a structured prediction language task that transfers information between class nodes through the generalizability of the structure.TANL (Paolini et al., 2021) introduces an augmented natural language translation task from which information related to the schema can be implicitly extracted.TEXT2EVENT (Lu et al., 2021) is a unified sequence-to-structure architecture for event extraction with a constrained decoding algorithm for event schema knowledge injection during in- ference.UIE (Lu et al., 2022) is a unified text-tostructure generation framework that enables unified modeling of different IE tasks and adaptively generates target sequences by a schema-based prompting mechanism.GPT-3 (Brown et al., 2020), a largescale language model (LLM), can serve as a baseline for schema-adaptable KGC.Although current works focusing on structured extraction can achieve excellent performance with static types of knowledge, they are typically unaware of schema evolution.To clarify this issue, we introduce a simple yet effective baseline dubbed schema-ADAptive Knowledge Graph Construction ADAKGC.

Overview
As shown in Figure 3, ADAKGC utilizes a pretrained encoder-decoder language model (LM) T5 (Raffel et al., 2020a) as the basic architecture for the schema-adaptable KGC task.Specifically, let encoder input X en = [S; X] be the concatenation of schema S and input X.In the decoding process, the LM calculates the conditioned probability of generating a new token y t given the previous token We initialize the model using the pre-trained parameter θ.Here, p θ is a trainable language model distribution.In the k-th iteration, we perform a gradient update on the following log-likelihood objective: where h t is the activation vector at decoding time step t.
is a concatenation of all activation layers, and h (j) t is the activation vector of the j-th layer at time step t.

Schema-enriched Prefix Instructor
Inspired by prefix-tuning (Li and Liang, 2021), we use task-specific prefix instructors to indicate task information, which are pairs of transformeractivated differentiable sequences {si en , si de }, each containing p consecutive D-dim vectors for encoder and decoder.Since using a discrete natural language task instruction in the context (e.g., "The schema used for the task is:") may guide the LM to produce a sub-optimal generated sequence, we optimize the instructions as a continuous soft prompt, propagating upward to all transformer activation layers and rightward to subsequent tokens.
Due to schema changes with iterations, we present schema-specific prefix instructors to instruct the encoding process.Specifically, we formalize the schema graph as linearized text.Assume given the constrained schema of RE task s k = {(h 1 , r 1 , t 1 ), ...(h n , r n , t n )} and tpc i = (h i , r i , t i ) denotes the i-th triple prefix constraint.By concatenating these schema prefix constraints initialized by word embedding, spc can be dynamically adjusted as the schema evolves, and added padding tokens to be a fixed length when instructing the LM: Thus, the schema-enriched prefix instructor provides a two-part prefix combination Z = {si en , spc c ; si de }, where ";" separates the respective prefix instructors for encoder and decoder.We recursively activate the decoder transformer activation vector h t , which is the connection of all layers, at time step t in the LM.
The training parameters of our model contain the LM parameters θ, the encoder-decoder task-specific prefix instructor{si en , si de }, and the schema-specific constraint instructor spc.For stable optimization, we follow Li and Liang (2021 ) with a smaller matrix M ′ ϕ consisting of a large feedforward neural network M LP ϕ , which can alleviate the optimization instability caused by directly updating the prefix parameters and is applied to {si en , si de ; spc}.We train the parameters of the model in the following steps: (1) First, freeze other parameters, fine-tune the prefix instructor {si en , si de } to learn task-specific prompts; (2) Secondly, freeze {si en , si de }, optimize the schema-specific instructor spc for the given schema graph; (3) Finally, we unfreeze the LM parameter θ and collaboratively optimize all parameters to capture the association between the prefix instructor and model parameters.

Schema-conditioned Dynamic Decoding
Previous works leverage a greedy decoding algorithm to generate linearized instance predictions token by token for the hidden sequence h t , which selects the token with the highest prediction probability p (y t | y <t , S, X) at each vanilla decoding step t.Unfortunately, when the schema changes, this decoding algorithm does not guarantee the generated instances are consistent with the latest schema.In other words, it may result in out-of-date or invalid types being generated due to the lack of labeled data fine-tuning the model to adapt the probability distribution to the current schema constraints.In addition, the greedy decoding algorithm neglects useful schema knowledge that can effectively guide the decoding process.
In the schema-conditioned decoding process, we apply a trie-based decoding mechanism that dynamically constructs a trie-tree by leveraging the latest schema.An intuitive interpretation is that the schema contains rich semantic information (e.g., instance types) and structural information (e.g., relational edges between instance types) so that the decoding process can be constrained to ensure that the generated token is valid.Specifically, we constrain the model to generate the type tokens consistently with the existing schema at the type location.We pursue the LM output to be a sequence of RE following pattern and optimized using the standard seq2seq objective function: where refer to the n-th generated head entity, tail entity, and their respective types while R (n) refer to relation.

Experimental Settings
Datasets.We conduct experiments on KGC tasks, including NER, RE and EE.The used datasets includes FEW-NERD (Ding et al., 2021), NYT (Riedel et al., 2010b) and ACE2005 (Walker et al., 2006).In our work, we need to construct schema as well as golden validation/test sets dynamically.For each dataset, we build three types of evaluation settings based on §2.3.Therefore for original datasets, we use a certain proportion of the schema as initialization to conduct schema expansion regarding three schema evolution categories in Appendix A.1.Evaluation.We use span-based Micro-F1 as the primary metric.Rel-S means that the relation is correct if the relation type is correct and the string and entity types of the related entity mentions are correct.For each iteration experiment, we report the average performance over 3 random seeds.UIE is implemented without pre-training by directly using T5-v1.1-baseas the backbone for a fair comparison.More details are in Appendix A.2.

Main Results
We report empirical results regarding horizontal schema expansion, vertical schema expansion and hybrid schema expansion settings to compare our proposed methods with the baselines.The performance over all iterations during the whole schemaadaptable KGC process is presented in Table 1-3.From the results, we can observe that: Schema adaptive generalization challenge.On all three expansion categories, the model performances tend to decrease as the iterations increase.TANL achieves lower performance which employs an augmented language and implicitly trains the model to learn schema information.
TEXT2EVENT utilizes schema as constraint information on the decoding side and outperforms other models in some iterations.Although ADAKGC and UIE obtain optimal or suboptimal performance, the performance of iteration 1 and iteration 7 has a significant drop.We believe that the implicit schema evolution rules can help future work to develop adaptive generalization capabilities for schema-adaptable KGC.
Schema-enhanced modules boost the performances.Compared to other models, ADAKGC is improved with schema-enhanced modules on both the encoder and decoder, which allows it to achieve the best performance in most settings.On the ACE2005 hybrid schema expansion dataset,  ADAKGC improves 0.71% on trigger extraction and 3.65% on event argument extraction, indicating that ADAKGC can capture schema-specific information under evolutionary schema.
LLMs can understand schema adaption patterns better.To explore the performance of LLMs (Qiao et al., 2023) on the proposed tasks, we per-  form comparative experiments with GPT-3.5 on NYT.Since we cannot utilize all training instances, we report in-context learning performance given 20-shot demonstrations as shown in Appendix A.5.
From Figure 4, we notice that GPT-3.5 is capable of producing instances that conform to the dynamically changing schema but still yield low performance due to the low-shot issue.Likewise, we sample several cases and use ChatGPT 3 to evaluate schema-adaptable KGC (See Figure 7 and 8 in Appendix A.6), which surprisingly demonstrates stable generalization ability with evolving schema.
These findings indicate a promising future work of schema-adaptable KGC to develop alignment prompts with LLMs.

Ablation Study on ADAKGC
To prove the effects of the schema-enriched prefix instructor and schema-conditioned dynamic decod- ing, we conduct the ablation study, and the results are shown in Figure 5. From two evolutionary categories, we observe that: (1) Both schema-enriched prefix instructor and schema-conditioned dynamic decoding can help the schema-adaptable learning process; (2) Efficiently encoding schema evolution information is more important, which achieves improvements of 0.77% on horizontal schema expansion and 0.36% on vertical schema expansion.

Case Study
As shown in Figure 6, we randomly select 8 types and observe that: (1) The types that appear in the initial schema mostly degrade performance, indicating that the model causes slight confusion as the schema expands.
(2) Due to the structural inheritance relationship in the vertical expansion of the schema, our model can effectively transfer the labels of the father node to the child nodes when new child nodes are added.
To further analyze the drawbacks of our model  5 Related Work

Conclusion
This paper introduces a new task of schemaadaptable KGC with benchmark datasets and a new baseline ADAKGC.We illustrate the task difficulties with previous baselines on three principles of schema expansion patterns (horizontal, vertical, hybrid) and demonstrate the effectiveness of the proposed ADAKGC.

Limitations
The proposed work still contains several limitations, as follows: Datasets: Note that several datasets, such as ACE2005, cannot be released due to LICENCE issues; we release the code to build the datasets and provide all the pre-processed publicly available datasets (e.g., Few-NERD, NYT) We use several existing datasets to construct schema-adaptable benchmarks; however, previous datasets may have limited schema structures (the schema pattern in some datasets is very simple).We plan to build more datasets via crowdsourcing for comprehensive evaluation.In addition, we will continue to promote the construction of multimodal schema adaptive graphs, which leverage the dynamic evolution of schema to integrate visual and textual knowledge into a self-learning graph extraction system.
Baselines and Proposed ADAKGC: Note that the proposed one, although better than previous approaches, including Text2Event (Lu et al., 2021), TANL (Paolini et al., 2021), UIE (Lu et al., 2022), still suffers from poor generalization ability.However, we notice a very stable performance with LLM (though deficient performance), indicating a new promising solution for schema-adatable KGC.

Ethical Considerations
Intended use.The dataset and model in this paper are indented to be used for exploratory analysis of schema-adaptable KGC.
Biases.We collect data from existing datasets (e.g., Few-NERD: CC BY-SA 4.0 license.),which may contain some data with offensive language or discriminatory.

A Appendix
This section describes the details of experiments, including dataset construction and evaluation on downstream tasks.

A.1.1 Construction Process
In each task, we execute three schema evolution strategies.The raw dataset statistics are shown in Table 5, where it can be seen that they have a two-level schema structure, leaving the research of a more hierarchical schema structure for future work.As shown in Algorithm 2-4, we describe in detail the specific construction process of horizontal schema extension, vertical schema extension and hybrid schema extension.
In particular, we also release additional datasets from a semantic substitution perspective.As shown in Algorithm 5, analogous schema expansion requires schema replacement for semantically similar new nodes.Based on the performance of the old class transfer to the new semantic class, we can evaluate the semantic invariance capability.Horizontal Schema Expansion.Neighboring nodes of the specified type that have high-level similarity values in the same framework are also adjacent when projected into the semantic space (Huang et al., 2018).Existing research efforts have developed many rich libraries of ontologies (e.g.FrameNet (Baker and Sato, 2003), VerbNet (Kipper et al., 2008), Propbank (Palmer et al., 2005), and OntoNotes (Pradhan et al., 2007)), where each ontology type is associated with a set of pre-defined neighboring ontologies.(1) Searching the ontology library to retrieve candidate nodes W f associated with target nodes W s at the same hierarchy.
(2) The similarity metric is obtained by calculating the cosine vector similarity of all candidate nodes W f to the target node W s (Eq.5).( 3) Selecting the appropriate threshold of node pairs to confirm the sorted addition of horizontal nodes.
(4) Updating the schema with horizontal nodes and adding the golden validation set and test set in the dataset.
Vertical Schema Expansion.Structural similarity needs to be exploited when adding schema hierarchy nodes as new classes.( 1) For search convenience, we link the hypernym ontology under a root node so that the schema forms a tree structure.
(2) Starting at the root node, we utilize a child selection strategy by recursively applying through the tree until reaching the deepest node.A node could be expandable when it represents a non-terminal state or has hyponyms in semantics (e.g., location->country).
(3) According to the available hyponyms, one (or more) child nodes are added to expand the current schema tree.(4) Updating the schema with vertical nodes and adding the golden validation set and test set in the dataset.Hybrid Schema Expansion.It is necessary to hybrid horizontal and vertical expansion to form a comprehensive structural topology, which is more consistent with real scenarios.(1) Setting the threshold α for random selection.
(2) Executing horizontal expansion iteration below the threshold α, or vertical node expansion above the threshold α.Note that when the father node of added nodes does not exist, we also add the father node to maintain the schema hierarchy.(3) Updating the schema with the corresponding nodes and adding the golden validation set and test set in the dataset.Analogous Schema Expansion.To detect the semantic node sensitivity of the schema, we randomly replace similar semantic expressions for the nodes.
(1) Random selection of candidate nodes to obtain word expressions W C .(2) Candidate nodes are created by pairing W C with all words in the corpus word list W L .The consistency between individual words is calculated by the normalized point-bypoint mutual information (NPMI) of w i and w j (Eq.6), where adding smooth ϵ and γ controls for log p (w i , w j ) weights for higher NPMI values (Eq.7).( 3) Adopting candidate nodes that exceed the threshold to replace the schema and updating the golden validation set and test set in the dataset.

A.1.2 Schema-adaptable Datasets Statistic
We set the number N of total iterations, and initialize the original number of schema nodes.We show the statistics of schema-adaptable datasets for each task in Table 6.

A.2 Evaluation
We use span-based Micro-F1 as the major metric to evaluate the model and adopt the same evaluation metrics as previous work: * Named Entity Recognition: an entity mention is correct if its strings and type match a reference entity.Table 6: Schema-adaptable datasets statistics.#Init indicates the number of initial subclasses, #Add is the number of subclasses added per iteration, and #N is the total number of iterations.

A.4 Analogous Schema Expansion Experiment
As shown in Figure 7, our ADAKGC also has powerful semantic transplantation capabilities, which achieves competitive performance with baselines.With the schema-enriched prefix instructor, ADAKGC achieves an improvement of 7.70% on average over TEXT2EVENT on the event trigger extraction task and 4.87% on the event argument extraction task.This verifies the proposed schemaenriched prefix instructor and decoding modules can learn general schema-adaptable ability even the schema evolution knowledge is rarely in the pretraining stage.Note that TANL achieves the best performance on the NYT dataset, indicating that language models have the ability to learn schema semantic transfer implicitly as an augmented natural language prediction task.Therefore we believe that in addition to the schema structure perception modules, semantic robustness modules for analogous node expansion scenarios are also essential.
A.5 GPT-3.5 Experiment Details GPT-3.5 is a large autoregressive language model with 175 billion parameters.To explore the performance of GPT-3.5 on the schema-adaptive KGC task, we follow the input format of few-shot learning using OpenAI API4 .As shown in Table 12, we utilize a fixed manual template to generate a contextual window suitable for the model, including natural language task descriptions (text in blue), linearized schemas (text in purple), 20 examples in the model's context, and task prompts (text in red).

A.6 ChatGPT Results
ChatGPT 5 trains an initial model using supervised fine-tuning and further utilizes reinforcement learning systems to rank by quality for human feedback rewards.We handle Schema-adaptable KGC tasks Algorithm 2 The construction process of horizontal schema expansion.
for node between S raw and S 7: Pick out top n iter schema node, S = S ∪ S raw [: end for by asking questions to the chatbot in a conversational mode.First, we present the task description and the 20 demonstrations as shown in Figure 7. Then we give a paragraph text to test whether the chatbot can extract the corresponding triples based on the same schema as the demonstration examples comply with.From Figure 8 we can find that some of the facts are well extracted, indicating that ChatGPT can understand the task and perform extraction consistent with the schema.Finally, we add three new nodes "profession" "place founded" "founders" to the previous schema under a horizontal schema expansion iteration.Output results in Figure 8 show that ChatGPT not only adapts the output to the updated schema but also deduces reasonable facts by a chain-of-thought approach.
Algorithm 3 The construction process of vertical schema expansion.Input: The Belgrade district court said that Markovic will be tried along with 10 other Milosevic-era officials who face similar charges of 'inappropriate use of state property' that carry a sentence of up to five years in jail.

Transport[arrived] Meet[brief]
Table 9: Adaptive evolution of vertical schema expansion on ACE2005 dataset.Underlined classes refer to major classes, which will be covered by refined sub classes.
Input: The charismatic leader of Turkey's governing party was named prime minister Tuesday, a step that probably boosts chances that the United States will get permission to deploy troops in the country along Iraq's northern border.

Transport[deploy] Elect[named]
Input: Webb also said details of the breakdowns of the Welches' previous marriages were likely to come up , and cited reports of alleged extramarital affairs by both.

GPT-3.5 Input Example:
There are some relation extraction samples, relation must be taken from schema, head entity and tail entity must be taken from context.Relation, head entity and tail entity may have multiple.schema: ["people", "country", "religion", "major shareholder of", "industry", "contains", "brith place", "location", "nationality", "advisors", "neighborhood of", "place lived", "capital", "geographic distribution", "teams", "major shareholders", "place of death", "children", "company", "profession", "place founded", "founders"] Context: In Queens, North Shore Towers, near the Nassau border, supplanted a golf course, and housing replaced a gravel quarry in Douglaston.The relation involved in the above sentence are: 1.The head entity is Douglaston, relation is neighborhood of, tail entity is Queens; 2. The head entity is Queens, relation is contains, tail entity is Douglaston.Context: Martin, the district attorney for Lehigh County in Pennsylvania, said that after his office's review of the records, he was satisfied with Mr. Cullen's denials.The relation involved in the above sentence are: 1.The head entity is Pennsylvania, relation is contains, tail entity is Lehigh County.Context: Mr.Brown has demeaned Mr.Bush as "a cheerleader," declared that Homeland Security Secretary Michael Chertoff did not know "the first thing about running a disaster," and called critics like Representative Gene Taylor, Democrat of Mississippi, "a little twerp" and Senator Norm Coleman, Republican of Minnesota, an unprintable vulgarity (both in Playboy).The relation involved in the above sentence are: 1.The head entity is Gene Taylor, relation is place lived, tail entity is Mississippi.... Do you understand how to do relation extraction based on schema?Now it's your turn to do relation extraction.schema: ["people", "country", "religion", "major shareholder of", "industry", "contains", "birth place", "location", "nationality", "advisors", "neighborhood of", "place lived", "capital", "geographic distribution", "teams", "major shareholders", "place of death", "children", "company", "profession", "place founded", "founders"] Context: But that spasm of irritation by a master intimidator was minor compared with what Bobby Fischer, the erratic former world chess champion, dished out in March at a news conference in Reykjavik, Iceland.The relation involved in the above sentence are: GPT-3.5 Output Example: The relation involved in the above sentence are: 1.The head entity is Bobby Fischer, relation is place lived, tail entity is Iceland; 2. The head entity is Iceland, relation is contains, tail entity is Reykjavik; 3. The head entity is Iceland, relation is capital, tail entity is Reykjavik.
Golden Output Example: The relation involved in the above sentence are: 1.The head entity is Bobby Fischer, relation is nationality, tail entity is Iceland; 2. The head entity is Iceland, relation is capital, tail entity is Reykjavik; 3. The head entity is Iceland, relation is contains, tail entity is Reykjavik; 4. The head entity is Bobby Fischer, relation is place of death, tail entity is Reykjavik.
Table 12: Examples of GPT-3.5 experiment on NYT dataset.A total of 20 demonstrations are given to the model.

Figure 1 :
Figure 1: Knowledge Graph Construction (KGC) with dynamic updates of schema.

Figure 3 :
Figure 3: The overview of ADAptive Knowledge Graph Construction ADAKGC.

Figure 5 :
Figure 5: Ablation study on NERD horizontal schema expansion dataset, with the average result of 7 iterations.
Professor Dr.Weldon with his son Charles traveled throughout the world, living in Paris, France.
contains dev/test data D k dev , D k test and schema graph s k .Note that the model will not be re-trained but hope to pick up on the ability of information extraction with evolving schema.The challenge is that the model is Algorithm 1 Dataset Construction Process.Input: iteration N , raw schema S raw , and raw dataset {D raw train , D raw dev , D raw test } Output: Schema S N ,{D N train , D N dev , D N test } 1: Randomly initialize n init nodes in S raw as S 1 2: Pick out the instance associated with schema S as D (1) = {D 1 train , D 1 dev , D 1 test } 3: for iteration i = 2, ..., n do s ) for candidate schema S5:Vertical Schma Expansion: Select n iter sub node whose father node belongs to S

Table 1 :
Horizontal schema expansion results in schema-adaptable knowledge graph construction.

Table 2 :
Vertical schema expansion results in schema-adaptable knowledge graph construction.

Table 3 :
Hybrid schema expansion results in schema-adaptable knowledge graph construction.
Kelly, the US assistant secretary for East Asia and Pacific Affairs, arrived in Seoul from Beijing Friday to brief Yoon, the foreign minister.

Table 4 :
Error analysis on all ACE2005 schema expansion datasets.andpromotefuture works of schema-adaptable KGC, we count incorrect instances and classify them into five categories below, as shown in Table4: (1) Weak Transfer.Despite schema expansion, the model is prevented from updating labels by old model parameters.(2) Inheritance Deficiency.The label is not inherited in time when subdividing the father node.(3) Relevance Neglect.The lack of on- tology relevance leads to the absence of correlated event extraction.(4)ClassImbalance.Models suffering from unbalanced class learning problems tend to depend on similarly in-context sentences to judge high-frequency labels.(5)Potential Annotation.Some example outputs suggest potential errors or omitted annotation.
#Maj indicates the number of major classes, #Sub is the number of subclasses, and #Val #Test is the number of sentences.
Set sampling seed θ, total iteration N , raw schema S raw , and raw dataset {D raw train , D raw dev , D raw test } 2: Initialize blank schema S, blank dataset {D train , D dev , D test } and initial node number n init , node number n iter per iteration 3: Randomly select n init nodes in S raw , S = S ∪ init node, S 1 = S,S raw = S raw − S 1:

Table 7 :
Set sampling seed θ, total iteration N , raw schema S raw , and raw dataset {D raw train , D raw dev , D raw test } 2: Initialize blank schema S, blank dataset {D train , D dev , D test } and initial node number n init , node number n iter per iteration 3: for major node in S raw do Randomly select n init nodes in S raw , S = S ∪ init node, S 1 = S,S raw = S raw − S S = S ∪ S raw [: n iter ], S raw = S raw − S raw [: n iter ] Analogous schema replacement results in schema-adaptable knowledge graph construction. 1:

Table 8 :
Adaptive evolution of horizontal schema expansion on ACE2005 dataset.