Posts

2020, ACL data: CoNLL-2012, GAP task: Coreference Resolution 通过QA方式处理coreference问题，A query is generated for each candidate mention using its surrounding con- text, and a span prediction module is em- ployed to extract the text spans of the corefer- ences within the document using the generated query. 近期的方法有consider all text spans in a document as potential mentions and learn to find an antecedent for each possible mention. There。这种仅依靠mention的做对比的方法的缺点： At the task formalization level： 因为当前数据集有很多遗漏的mention， mentions left out at the mention proposal stage can never be recov- ered since the downstream module only operates on the proposed mentions....

针对样本不平衡问题，除了上下采样，调整样本权重等统计方法，还有可以通过对loss函数进行设计。 对于多分类问题（n选1），一般使用softmax；对于多标签分类问题（n选k），一般是转换为n各sigmoid二分类问题。 ...

2019, ACL data: TWITTER, WEIBO links: https://www.aclweb.org/anthology/N19-1163, https://github.com/DeepBrainAI/ERD task: Rumour Detection 这篇文章采用GRU编码社交媒体posts stream，作为环境的状态表示；训练一个分类器以GRU的状态输出为输入，对文本做二分类判断是否是rumor。用DQN训练agent，根据状态做出是否启动rumor分类器进行判断，并根据分类结果对错给予奖惩。目标就是尽可能准尽可能早地预测出社交媒体posts是否是rumor。 Focuses on the task of rumour detection; particularly, we are in- terested in understanding how early we can detect them. Our model treats social media posts (e.g. tweets) as a data stream and integrates reinforcement learning to learn the number minimum num- ber of posts required before we classify an event as a rumour. Let $E$ denote an event, and it consists of a series of relevant posts $x_i$, where $x_0$ denotes the source message and $x_T$ the last relevant message....

2019, ACL data: KBP37, SemEval 2010 Task 8, TACRED task: Entity and Relation Extraction Build task agnostic relation representations solely from entity-linked text. 缺陷 文章认为网页中, 相同的的实体对一般指代相同的实体关系, 把实体不同的构建为负样本. 这个在单份文件中可能大概率是对的. 但是实体不完全一直不代表这个两对实体的关系不同. 所以这个作为负样本是本质上映射的是实体识别而不是关系. 比较好的方式是把实体不同但是关系一样的也考虑进来. 方法 Define Relation Statement We define a relation statement to be a block of text containing two marked entities. From this, we create training data that contains relation statements in which the entities have been replaced with a special [BLANK]...

2020, NAACL data: ACE 04, ACE 05, SciERC links: https://github.com/princeton-nlp/PURE task: Entity and Relation Extraction 提出了一种简单但是有效的pipeline方法:builds on two independent pre-trained encoders and merely uses the entity model to provide input features for the relation model. 实验说明: validate the importance of learning distinct contextual representations for entities and relations, fusing entity information at the input layer of the relation model, and incorporating global context. 从效果上看, 似乎是因为cross sentence的context加成更大 方法 Input: a sentence X consisting of n tokens x1, ....

2020, EMNLP data: ACE 04, ACE 05, ADE, CoNLL04 links: https://github.com/LorrinWWW/two-are-better-than-one. task: Entity and Relation Extraction In this work, we propose the novel table-sequence encoders where two different encoders – a table encoder and a sequence encoder are designed to help each other in the representation learning process. 这篇ACL 2020文章认为, 之前的Joint learning方法侧重于learning a single encoder (usually learning representation in the form of a table) to capture information required for both tasks within the same space....

2020, ACL data: ACE 05 task: Event Detection Propose a novel Enrichment Knowledge Distillation (EKD) model to efficiently distill external open-domain trigger knowledge to reduce the in-built biases to frequent trigger words in annotations. leverage the wealth of the open-domain trigger knowledge to improve ED propose a novel teacher-student model (EKD) that can learn from both labeled and unlabeled data 缺点 只能对付普遍情况, 即一般性的触发词; 但触发词不是在任何语境下都是触发词. 方法 empower the model with external knowledge called Open-Domain Trigger Knowledge, defined as a prior that specifies which words can trigger events without subject to pre-defined event types and the domain of texts....

2020, ACL Task: MultiMedia Event Extraction Introduce a new task, MultiMedia Event Extraction (M2E2), which aims to extract events and their arguments from multimedia documents. Construct the first benchmark and evaluation dataset for this task, which consists of 245 fully annotated news articles Propose a novel method, Weakly Aligned Structured Embedding (WASE), that encodes structured representations of semantic information from textual and visual data into a common embedding space. which takes advantage of annotated unimodal corpora to separately learn visual and textual event extraction, and uses an image-caption dataset to align the modalities...

深度强化学习DQN和Natural DQN, Double DQN, Dueling DoubleQN, Rainbow DQN 的演变和必看论文. DQN的Overestimate DQN 基于 Q-learning, Q-Learning 中有 Qmax, Qmax 会导致 Q现实 当中的过估计 (overestimate). 而 Double DQN 就是用来解决过估计的. 在实际问题中, 如果你输出你的 DQN 的 Q 值, 可能就会发现, Q 值都超级大. 这就是出现了 overestimate. DQN 的神经网络部分可以看成一个 最新的神经网络 + 老神经网络, 他们有相同的结构, 但内部的参数更新却有时差. Q现实 部分是这样的: $$Y_t^\text{DQN} \equiv R_{t+1} + \gamma \max_a Q(S_{t+1}, a; \theta_t^-)$$ 过估计 (overestimate) 是指对一系列数先求最大值再求平均，通常比先求平均再求最大值要大（或相等，数学表达为： $$E(\max(X_1, X_2, ...)) \ge \max(E(X_1), E(X_2), ...)$$ 一般来说Q-learning方法导致overestimation的原因归结于其更新过程，其表达为： $$Q_{t+1} (s_t, a_t) = Q_t (s_t, a_t) + a_t(s_t, a_t)(r_t + \gamma \max a Q_t(s_{t+1}, a) - Q_t(s_t, a_t))$$ 而更新最优化过程如下...

2017, EMNLP data: FB15K-237, FB15K task: Knowledge Graph Reasoning Use a policy-based agent with continuous states based on knowledge graph embeddings, which reasons in a KG vector space by sampling the most promising relation to extend its path. 方法 RL 系统包含两部分， 第一部分是外部环境，指定了 智能体 和知识图谱之间的动态交互。环境被建模为马尔可夫决策过程。 系统的第二部分，RL 智能体，表示为策略网络，将状态向量映射到随机策略中。神经网络参数通过随机梯度下降更新。相比于 DQN，基于策略的 RL 方法更适合该知识图谱场景。一个原因是知识图谱的路径查找过程，行为空间因为关系图的复杂性可能非常大。这可能导致 DQN 的收敛性变差。另外，策略网络能学习梯度策略，防止 智能体 陷入某种中间状态，而避免基于值的方法如 DQN 在学习策略梯度中遇到的问题。 关系推理的强化学习 行为 给定一些实体对和一个关系，我们想让 智能体 找到最有信息量的路径来连接这些实体对。从源实体开始，智能体 使用策略网络找到最有希望的关系并每步扩展它的路径直到到达目标实体。为了保持策略网络的输出维度一致，动作空间被定义为知识图谱中的所有关系。 状态 知识图谱中的实体和关系是自然的离散原子符号。现有的实际应用的知识图谱例如 Freebase 和 NELL 通常有大量三元组，不可能直接将所有原子符号建模为状态。为了捕捉这些符号的语义信息，我们使用基于平移的嵌入方法，例如 TransE 和 TransH 来表示实体和关系。这些嵌入将所有符号映射到低维向量空间。在该框架中，每个状态捕捉 智能体 在知识图谱中的位置。在执行一个行为后，智能体 会从一个实体移动到另一个实体。两个状态通过刚执行的行为（关系）由 智能体 连接。第 t 步的状态向量：...