Entity-Relation Extraction as Multi-turn Question Answering

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
• 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
    • 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
  • 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
• 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)

  • 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

  • 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
        • $\mathcal{L}=(1-\lambda )\mathcal{L}(\text{ head-entity })+\lambda \mathcal{L}(\text{ tail-entity, rel})$
        • 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
        $\begin{array}{l}p(y(w_1,\dots ,w_n)=\text{ answer }|\text{ question, }s)\\ =p(w_1=\mathrm{B})\times p(w_n=\mathrm{E}){\prod }_{i\in [2,n-1]}p(w_i=\mathrm{M})\end{array}$
      • Reward：特定句子，用正确抽取的triples作为奖励 ，maximizes the expected reward $E_{\pi }[R(w)]$，通过sampling from the policy $\pi$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)