Entity-Relation Extraction as Multi-turn Question Answering
- 发现领域内的问题
-
task formalization level
- 三元组本身的知识表达能力有限,比如,Musk case里的hierarchical dependency,时间、地点、职位、人物需要在一个更高维度的空间表达
-
algorithm level
- 输入:a raw sentence with two marked mentions
输出:whether a relation holds between the two mentions
- hard for neural models to capture all the lexical, semantic and syntactic cues in this formalization
- (1) entities are far away;
(2) one entity is involved in** multiple triplets;**
or (3) relation spans have overlaps
- (1) entities are far away;
- 输入:a raw sentence with two marked mentions
-
- related work
- Extracting Entities and Relations
- pipelined approach
- 优点:**flexibility **of integrating different data sources and learning algorithms
- 缺点:suffer significantly from error propagation
- joint approach
- through various dependencies
- constraints solved by integer linear programming
- card-pyramid parsing
- global probabilistic graphical models
- structured perceptron with efficient beamsearch
- table-filling approach
- search orders in decoding and global features
- shared parameters,end-to-end approach that extract entities and their relations using neural network models
- neural tagging model,multi-class classification model based on tree LSTMs
- multi-level attention CNNs
- seq2seq models to generate entity-relation triples
- through various dependencies
- reinforcement learning or Minimum Risk Training
- a global loss function to jointly train the two models under the framework work of Minimum Risk Training
- hierarchical reinforcement learning
- pipelined approach
- Machine Reading Comprehension, predicting answer spans given context
- 主要做的是 extract text spans in passages given queries
- 一种思路可以简化成 two multi-class classification tasks
- 另一种思路,对于multi-passage MRC, directly concatenating passages, first rank the passages and then run single-passage MRC on the selected passage
- 其他有用的:Pretraining methods like BERT or Elmo
- 趋势:a tendency of casting non-QA NLP tasks as QA tasks
- 具体的比如
- BiDAF、QANet
- Extracting Entities and Relations
- 本论文的工作
-
inspiration 来源
- identifying the relation between two predefined entities and the authors formalize the task of relation extraction as a single-turn QA task
Levy et al. (2017). Levy et al. (2017) and McCann et al. (2018)
- identifying the relation between two predefined entities and the authors formalize the task of relation extraction as a single-turn QA task
-
Idea
- model hierarchical tag dependency in multi-turn QA, identifying answer spans from the context
each entity type and relation type is characterized by a question answering template, and entities and relations are extracted by answering template questions
- question query encodes
- jointly modeling entity and relation
- exploit the well developed machine reading comprehension (MRC) models
- multi-step reasoning to construct entity dependencies
- model hierarchical tag dependency in multi-turn QA, identifying answer spans from the context
-
advantages
- capture the** hierarchical dependency of tags**, progressively obtain the entities we need for the next turn , closely akin to** the multi-turn slot filling dialogue system**
- the question query encodes important** prior information** for the relation class we want to identify
- the QA framework provides a natural way to simultaneously extract entities and relations: most MRC models support outputting special NONE tokens, indicating that there is no answer to the question
-
dataset
- ACE04, ACE05 and the CoNLL04 corpora
- a newly developed dataset RESUME in Chinese
extract biographical information of individuals from raw texts. The construction of structural knowledge base from RESUME requires four or five turns of QA
* 最大的特点:one person can work for **different **companies during **different **periods of time and that one person can hold **different **positions in **different **periods of time for the **same **company -
model
- 分解成了两个子任务:a multi-answer task for head-entity extraction + a single-answer task for joint relation and tail-entity extraction
- 第一阶段:head-entity extraction,extract this starting entity, we** transform each entity type to a question** using EntityQuesTemplates
- 这个阶段抽取到的不一定就是head entities
- 第二阶段:The relation and the tail-entity extraction,定义了relations chain用于multi-turn QA,因为一些的抽取取决于其他的抽取
-
Generating Questions using Templates
- type-specific
- natural language questions or pseudo-questions
-
Extracting Answer Spans via MRC
- backbone:BERT,基于多轮问答的问题对Traditional MRC models做了调整:predict a BMEO (beginning, inside, ending and outside) label
- Training and Test
- L = ( 1 − λ ) L ( head-entity ) + λ L ( tail-entity, rel ) \mathcal{L} = ( 1 - \lambda ) \mathcal{L} ( \text { head-entity } ) + \lambda \mathcal{L} ( \text { tail-entity, rel} ) L=(1−λ)L( head-entity )+λL( tail-entity, rel)
- 训练的时候两个共享参数,测试的时候head-entities and tail-entities are extracted separately,λ 控制两个子任务的 tradeoff
-
Reinforcement Learning
- 一个turn中抽取的答案还会影响downstream turns,也影响later accuracies
- 由于multi-turn dialogue generation的结果比较好,所以打算也用reinforcement learning
(Mrkˇsi´c et al., 2015; Li et al., 2016; Wen et al., 2016)
- action:selecting a text span in each turn
- policy:probability of selecting a certain span given the question and the context
p ( y ( w 1 , … , w n ) = answer ∣ question, s ) = p ( w 1 = B ) × p ( w n = E ) ∏ i ∈ [ 2 , n − 1 ] p ( w i = M ) \left. \begin{array} { l } { p ( y ( w _ { 1 } , \ldots , w _ { n } ) = \text { answer } | \text { question, } s ) } \\ { = p ( w _ { 1 } = \mathrm{B} ) \times p ( w _ { n } = \mathrm{E} ) \prod _ { i \in [ 2 , n - 1 ] } p ( w _ { i } = \mathrm{M} ) } \end{array} \right. p(y(w1,…,wn)= answer ∣ question, s)=p(w1=B)×p(wn=E)∏i∈[2,n−1]p(wi=M) - Reward:特定句子,用正确抽取的triples作为奖励 ,maximizes the expected reward E π [ R ( w ) ] E _ { \pi } [ R ( w ) ] Eπ[R(w)],通过sampling from the policy π π π来近似
- gradient的计算:likelihood ratio:
$\nabla E ( \theta ) \approx [ R ( w ) - b ] \nabla \log \pi ( y ( w ) | \text { question } s ) ) $
b 是 baseline value(所有之前奖励的平均), 每轮答对就奖励+1,final reward是所有轮次积累的奖励 - policy networks initialization:pre-trained head-entity and tail-entity extraction model
- experience replay strategy:for each batch, half of the examples are simulated and the other half is randomly selected from previously generated examples.
- strategy of curriculum learning 用在了 RESUME dataset 上,gradually increase the number of turns from 2 to 4 at training
-
Experimental Results( SOTA results)
- 指标:micro-F1 scores, precision and recall
- 自己搞的数据集RESUME上的结果
- 先确定一个baseline:tagging+relation,entity+dependency
- entities 部分用BERT tagging models,relations部分用 CNN to representations output by BERT transformers
- 这个任务akin to a dependency parsing task at the tag-level rather than the word-level
- 具体做法:通过BERT tagging model给每个word分配tagging labels, 然后调整SOTA dependency parsing model Biaffine来construct dependencies between tags(jointly trained)
- 比较常用的ACE04, ACE05 and CoNLL04上的结果
-
Ablation Studies
-
Effect of Question Generation Strategy:natural language questions会比pseudo-questions更好,因为提供的是more fine-grained semantic information
-
Effect of Joint Training: λ 间隔0.1地测了10个数据,其中,entity-extraction并不是在 λ = 0 的时候最好(说明relation extraction的部分可以提升entity extraction的效果)
-
Case Study:和SOTA MRT model对比,可以识别出相隔比较远的实体; 当句子里包含两对相同关系的时候,也可以识别出来
-
-
后续发展空间
- could easilty integrate reinforcement learning (just as in multi-turn dialog systems)
-