开放式语义理解相关论文调查

Posted on   |   In

前言

调查目的

进行这次论文调查的目的是了解目前对于开放式（多领域）的语义和知识理解及表示的研究方向、进度和重点，从而博采众长以助我们研究。

过去（包括目前）的语义理解以及问答系统并不具有泛化的理解能力，并且难以在理解和生成时引入知识。数据驱动的方法在人类学习语言的过程中并不是唯一的途径。很大程度上，我们的学习过程是利用知识作为指导的。比如对联创作，我们首要的是学习格律和章法。虽然泛读对于语言提高有帮助，但是我们的老师也常常提醒我们要用分析的方法去精读才能有更大的提高。这种分析的方法就是对知识的运用，掌握了知识才能更容易举一反三。

因此，开放式语义理解调研主要从三个方面进行：

  • 领域迁移 (Domain Transfer/Adaptation)
  • 泛化的语义解析 (General Semantic Parsing)
  • 语义表达 (Semantic Representation)

为了有的放矢，在详读论文之前，俞老师建议我先比较多地收集一些相关论文（标题和摘要），然后通过讨论筛选或者增补，最后再进行论文的阅读。本文就罗列了我收集的论文，我只看过摘要，希望大家看后能够给一些意见比如哪些合适哪些不适合。同时还希望大家能把自己觉得适合而我没有收录的文章推荐给我。

强烈欢迎补充和意见！！！ xueyangwu@yeah.net
强烈欢迎补充和意见！！！ xueyangwu@yeah.net
强烈欢迎补充和意见！！！ xueyangwu@yeah.net

论文选拔思路

这一部分讲述我选择论文的方法，因为个人思路有限，应该有很多遗漏，希望大家能补充。

1. 从研究组选择：

  • Stanford Percy Liang， 主要是semantic parsing
  • 清华大学 孙茂松，主要是Knowledge Representation

2. Google搜索关键词：

  • PHD thesis transfer/domain、domain adaptation/transfer
  • (general) semantic parsing
  • knowledge/semantic representation

3. 会议（ACL, EMNLP, IJCAI, AAAI, NIPS）：

  • 我只找了近两年（15、16）的会议的论文。
  • EMNLP2016 (EMNLP2016的这几篇我还找不到下载)
    • Exploring Semantic Representation in Brain Activity Using Word Embeddings
    • Learning Sentence Embeddings with Auxiliary Tasks for Cross-Domain Sentiment Classification
    • De-Conflating Semantic Representations of Words by Exploiting Knowledge from Semantic Networks
    • A General Regularization Framework for Domain Adaptation

汇总

除了上述提到的三个分类，我在找论文的过程中还发现了一些比较有趣但是并不符合某一分类的论文，放在最后，一共有8篇。领域迁移的部分相关论文我没有找到很多，如果大家平常有看到，求推荐！

表格的每一列表示上面提到的三个分类的论文数量统计；每一行是不同的具体任务，但是这个任务的区分不是很严格，因为有些论文并不针对某一个任务。有些更难区分的我就放在Others里面了。

具体任务\领域 Domain Transfer General Semantic Parser Semantic Representation 总计
Sentiment Analysis 1 - - 1
Word Representation 3 - 3 6
Logical - 2 1 3
LU&DS 3 1 1 5
QA - 3 - 3
Extraction - - - -
Others - 3 2 5
总计 7 9 7 23

论文信息及摘要

Domain Transfer

1. Fangzhao Wu and Yongfeng Huang. Sentiment domain adaptation with multiple sources. ACL2016.

Domain adaptation is an important research topic in sentiment analysis area. Existing domain adaptation methods usually transfer sentiment knowledge from only one source domain to target domain. In this paper, we propose a new domain adaptation approach which can exploit sentiment knowledge from multiple source domains. We first extract both global and domain-specific sentiment knowledge from the data of multiple source domains using multi-task learning. Then we transfer them to target domain with the help of words’ sentiment polarity relations extracted from the unlabeled target domain data. The similarities between target domain and different source domains are also incorporated into the adaptation process. Experimental results on benchmark dataset show the effectiveness of our approach in improving cross-domain sentiment classification performance.

2. Bollegala, Danushka, Takanori Maehara, and Ken-ichi Kawarabayashi. “Unsupervised cross-domain word representation learning.” ACL2015.

Meaning of a word varies from one domain to another. Despite this important domain dependence in word semantics, existing word representation learning methods are bound to a single domain. Given a pair of \emph{source}-\emph{target} domains, we propose an unsupervised method for learning domain-specific word representations that accurately capture the domain-specific aspects of word semantics. First, we select a subset of frequent words that occur in both domains as \emph{pivots}. Next, we optimize an objective function that enforces two constraints: (a) for both source and target domain documents, pivots that appear in a document must accurately predict the co-occurring non-pivots, and (b) word representations learnt for pivots must be similar in the two domains. Moreover, we propose a method to perform domain adaptation using the learnt word representations. Our proposed method significantly outperforms competitive baselines including the state-of-the-art domain-insensitive word representations, and reports best sentiment classification accuracies for all domain-pairs in a benchmark dataset.

3. Yun-Nung Chen, William Yang Wang, and Alexander I. Rudnicky. Leveraging Frame Semantics And Distributional Semantics For Unsupervised Semantic Slot Induction In Spoken Dialogue Systems. SLT2014

Although the spoken dialogue system community in speech and the semantic parsing community in natural language processing share many similar tasks and approaches, they have progressed independently over years with few interactions. This paper connects two worlds to automatically induce the semantic slots for spoken dialogue systems using frame and distributional semantic theories. Given a collection of unlabeled audio, we exploit continuous-valued word embeddings to augment a probabilistic frame-semantic parser that identifies key semantic slots in an unsupervised fashion. Our experiments on a real-world spoken dialogue dataset show that distributional word representation significantly improves adaptation from FrameNet-style parses of recognized utterances to the target semantic space, that comparing to a state-of-the-art baseline, a 12% relative mean average precision improvement is achieved, and that the proposed technology can be used to reduce the costs for designing task-oriented spoken dialogue systems

4. Yun-Nung Chen and Alexander I. Rudnicky. Dynamically supporting unexplored domains in conversational interactions by enriching semantics with neural word embeddings. SLT2014

Spoken language interfaces are being incorporated into various devices (e.g. smart-phones, smart TVs, etc). However, current technology typically limits conversational interactions to a few narrow predefined domains/topics. For example, dialogue systems for smartphone operation fail to respond when users ask for functions not supported by currently installed applications. We propose to dynamically add application-based domains according to users’ requests by using descriptions of applications as a retrieval cue to find relevant applications. The approach uses structured knowledge resources (e.g. Freebase, Wikipedia, FrameNet) to induce types of slots for generating semantic seeds, and enriches the semantics of spoken queries with neural word embeddings, where semantically related concepts can be additionally included for acquiring knowledge that does not exist in the predefined domains. The system can then retrieve relevant applications or dynamically suggest users install applications that support unexplored domains. We find that vendor descriptions provide a reliable source of information for this purpose.

5. Yun-Nung Chen, William Yang Wang, et al. Matrix Factorization with Knowledge Graph Propagation for Unsupervised Spoken Language Understanding. ACL2015

Spoken dialogue systems (SDS) typically require a predefined semantic ontology to train a spoken language understanding (SLU) module. In addition to the annotation cost, a key challenge for designing such an ontology is to define a coherent slot set while considering their complex relations. This paper introduces a novel matrix factorization (MF) approach to learn latent feature vectors for utterances and semantic elements without the need of corpus annotations. Specifically, our model learns the semantic slots for a domain-specific SDS in an unsupervised fashion, and carries out semantic parsing using latent MF techniques. To further consider the global semantic structure, such as inter-word and inter-slot relations, we augment the latent MF-based model with a knowledge graph propagation model based on a slot-based semantic graph and a word-based lexical graph. Our experiments show that the proposed MF approaches produce better SLU models that are able to predict semantic slots and word patterns taking into account their relations and domain-specificity in a joint manner.

6. Ming Sun, Yun-Nung Chen and Alexander I. Rudnicky. HELPR: A Framework to Break the Barrier across Domains in Spoken Dialog Systems. IWSDS 2016.

People usually interact with intelligent agents (IAs) when they have certain goals to be accomplished. Sometimes these goals are complex and may require interacting with multiple applications, which may focus on different domains. Current IAs may be of limited use in such cases and the user needs to directly manage the task at hand. An ideal personal agent would be able to learn, over time, these tasks spanning different resources. In this paper, we address the problem of crossdomain task assistance in the context of spoken dialog systems, and describe our approach about discovering such tasks and how IAs learn to talk to users about the task being carried out. Specifically we investigate how to learn user activity patterns in a smartphone environment that span multiple apps and how to incorporate users’ descriptions about their high-level intents into human-agent interaction

7. Yun-Nung Chen, Dilek Hakkani-Tur and Xiaodong He. ZERO-SHOT LEARNING OF INTENT EMBEDDINGS FOR EXPANSION BY CONVOLUTIONAL DEEP STRUCTURED SEMANTIC MODELS. ICASSP2016

The recent surge of intelligent personal assistants motivates spoken language understanding of dialogue systems. However, the domain constraint along with the inflexible intent schema remains a big issue. This paper focuses on the task of intent expansion, which helps remove the domain limit and make an intent schema flexible. A convolutional deep structured semantic model (CDSSM) is applied to jointly learn the representations for human intents and associated utterances. Then it can flexibly generate new intent embeddings without the need of training samples and model-retraining, which bridges the semantic relation between seen and unseen intents and further performs more robust results. Experiments show that CDSSM is capable of performing zero-shot learning effectively, e.g. generating embeddings of previously unseen intents, and therefore expand to new intents without re-training, and outperforms other semantic embeddings. The discussion and analysis of experiments provide a future direction for reducing human effort about annotating data and removing the domain constraint in spoken dialogue systems.

General Semantic Parsing

1. Robin Jia, Percy Liang. Data recombination for neural semantic parsing. ACL2016.

Modeling crisp logical regularities is crucial in semantic parsing, making it difficult for neural models with no task-specific prior knowledge to achieve good results. In this paper, we introduce data recombination, a novel framework for injecting such prior knowledge into a model. From the training data, we induce a highprecision synchronous context-free grammar, which captures important conditional independence properties commonly found in semantic parsing. We then train a sequence-to-sequence recurrent network (RNN) model with a novel attention-based copying mechanism on datapoints sampled from this grammar, thereby teaching the model about these structural properties. Data recombination improves the accuracy of our RNN model on three semantic parsing datasets, leading to new state-of-the-art performance on the standard GeoQuery dataset for models with comparable supervision.

2. Percy Liang. Learning executable semantic parsers for natural language understanding. Communications of the ACM, 2016.

For building question answering systems and natural language interfaces, semantic parsing has emerged as an important and powerful paradigm. Semantic parsers map natural language into logical forms, the classic representation for many important linguistic phenomena. The modern twist is that we are interested in learning semantic parsers from data, which introduces a new layer of statistical and computational issues. This article lays out the components of a statistical semantic parser, highlighting the key challenges. We will see that semantic parsing is a rich fusion of the logical and the statistical world, and that this fusion will play an integral role in the future of natural language understanding systems.

3. Panupong Pasupat and Percy Liang. Compositional semantic parsing on semi-structured tables. ACL2015.

Two important aspects of semantic parsing for question answering are the breadth of the knowledge source and the depth of logical compositionality. While existing work trades off one aspect for another, this paper simultaneously makes progress on both fronts through a new task: answering complex questions on semi-structured tables using question-answer pairs as supervision. The central challenge arises from two compounding factors: the broader domain results in an open-ended set of relations, and the deeper compositionality results in a combinatorial explosion in the space of logical forms. We propose a logical-form driven parsing algorithm guided by strong typing constraints and show that it obtains significant improvements over natural baselines. For evaluation, we created a new dataset of 22,033 complex questions on Wikipedia tables, which is made publicly available.

4. Yushi Wang, Jonathan Berant, Percy Liang. Building a semantic parser overnight. ACL2015.

How do we build a semantic parser in a new domain starting with zero training examples? We introduce a new methodology for this setting: First, we use a simple grammar to generate logical forms paired with canonical utterances. The logical forms are meant to cover the desired set of compositional operators, and the canonical utterances are meant to capture the meaning of the logical forms (although clumsily). We then use crowdsourcing to paraphrase these canonical utterances into natural utterances. The resulting data is used to train the semantic parser. We further study the role of compositionality in the resulting paraphrases. Finally, we test our methodology on seven domains and show that we can build an adequate semantic parser in just a few hours.

*5. Bowman, Samuel R., et al. A fast unified model for parsing and sentence understanding. ACL2016.

Tree-structured neural networks exploit valuable syntactic parse information as they interpret the meanings of sentences. However, they suffer from two key technical problems that make them slow and unwieldy for large-scale NLP tasks: they usually operate on parsed sentences and they do not directly support batched computation. We address these issues by introducing the Stack-augmented Parser-Interpreter Neural Network (SPINN), which combines parsing and interpretation within a single tree-sequence hybrid model by integrating tree-structured sentence interpretation into the linear sequential structure of a shift-reduce parser. Our model supports batched computation for a speedup of up to 25 times over other tree-structured models, and its integrated parser can operate on unparsed data with little loss in accuracy. We evaluate it on the Stanford NLI entailment task and show that it significantly outperforms other sentence-encoding models.

6. Jin-woo Park, Seung-won Hwang, Haixun Wang. Fine-Grained Semantic Conceptualization of FrameNet. AAAI2016.

Understanding verbs is essential for many natural language tasks. To this end, large-scale lexical resources such as FrameNet have beenmanually constructed to annotate the semantics of verbs (frames) andtheir arguments (frame elements or FEs) in example sentences. Our goal is to “semantically conceptualize” example sentences by connecting FEs to knowledge base (KB) concepts. For example, connecting Employer FE to company concept in the KB enables the understanding thatany (unseen) company can also be FE examples.However, a naive adoption of existing KB conceptualization technique, focusingon scenarios of conceptualizing a few terms,cannot 1) scale to many FE instances (average of 29.7 instances for all FEs) and 2) leverage interdependence betweeninstances and concepts.We thus propose a scalable k-truss clusteringand a Markov Random Field (MRF) model leveraging interdependence betweenconcept-instance, concept-concept, and instance-instance pairs. Our extensive analysis with real-life data validates that our approachimproves not only the quality of the identified concepts for FrameNet, but alsothat of applications such as selectional preference.

7. Wen-tau Yih, Ming-Wei Chang, Xiaodong He, and Jianfeng Gao. Semantic Parsing via Staged Query Graph Generation: Question Answering with Knowledge Base. ACL2015.

We propose a novel semantic parsing framework for question answering using a knowledge base. We define a query graph that resembles subgraphs of the knowledge base and can be directly mapped to a logical form. Semantic parsing is reduced to query graph generation, formulated as a staged search problem. Unlike traditional approaches, our method leverages the knowledge base in an early stage to prune the search space and thus simpli- fies the semantic matching problem. By applying an advanced entity linking system and a deep convolutional neural network model that matches questions and predicate sequences, our system outperforms previous methods substantially, and achieves an F1 measure of 52.5% on the WEBQUESTIONS dataset.

8. Siva Reddy, Mirella Lapata, and Mark Steedman. Large-scale Semantic Parsing without Question-Answer Pairs. ACL2014.

In this paper we introduce a novel semantic parsing approach to query Freebase in natural language without requiring manual annotations or question-answer pairs. Our key insight is to represent natural language via semantic graphs whose topology shares many commonalities with Freebase. Given this representation, we conceptualize semantic parsing as a graph matching problem. Our model converts sentences to semantic graphs using CCG and subsequently grounds them to Freebase guided by denotations as a form of weak supervision. Evaluation experiments on a subset of the FREE917 and WEBQUESTIONS benchmark datasets show our semantic parser improves over the state of the art.

9. Jonathan Berant, Andrew Chou, Roy Frostig and Percy Liang. Semantic Parsing on Freebase from Question-Answer Pairs. EMNLP2013.

In this paper, we train a semantic parser that scales up to Freebase. Instead of relying on annotated logical forms, which is especially expensive to obtain at large scale, we learn from question-answer pairs. The main challenge in this setting is narrowing down the huge number of possible logical predicates for a given question. We tackle this problem in two ways: First, we build a coarse mapping from phrases to predicates using a knowledge base and a large text corpus. Second, we use a bridging operation to generate additional predicates based on neighboring predicates. On the dataset of Cai and Yates (2013), despite not having annotated logical forms, our system outperforms their state-of-the-art parser. Additionally, we collected a more realistic and challenging dataset of question-answer pairs and improves over a natural baseline.

Semantic Representation

1. Fereshte Khani, Martin Rinard, Percy Liang. Unanimous prediction for 100% precision with application to learning semantic mappings. ACL2016.

Can we train a system that, on any new input, either says “don’t know” or makes a prediction that is guaranteed to be correct? We answer the question in the affirmative provided our model family is well specified. Specifically, we introduce the unanimity principle: only predict when all models consistent with the training data predict the same output. We operationalize this principle for semantic parsing, the task of mapping utterances to logical forms. We develop a simple, efficient method that reasons over the infinite set of all consistent models by only checking two of the models. We prove that our method obtains 100% precision even with a modest amount of training data from a possibly adversarial distribution. Empirically, we demonstrate the effectiveness of our approach on the standard GeoQuery dataset.

2. 刘知远, 孙茂松, 林衍凯, 谢若冰. 知识表示学习研究进展. 计算机研究与发展, 2016, 53(2): 247-261.

摘要：人们构建的知识库通常被表示为网络形式,节点代表实体,连边代表实体间的关系.在网络表示形式下,人们需要设计专门的图算法存储和利用知识库,存在费时费力的缺点,并受到数据稀疏问题的困扰.最近,以深度学习为代表的表示学习技术受到广泛关注.表示学习旨在将研究对象的语义信息表示为稠密低维实值向量,知识表示学习则面向知识库中的实体和关系进行表示学习.该技术可以在低维空间中高效计算实体和关系的语义联系,有效解决数据稀疏问题,使知识获取、融合和推理的性能得到显著提升.介绍知识表示学习的最新进展,总结该技术面临的主要挑战和可能解决方案,并展望该技术的未来发展方向与前景.

3. Ruobing Xie, Zhiyuan Liu, Maosong Sun. Representation Learning of Knowledge Graphs with Hierarchical Types. IJCAI2016.

Representation learning of knowledge graphs aims to encode both entities and relations into a continuous low-dimensional vector space. Most existing methods only concentrate on learning representations with structured information located in triples, regardless of the rich information located in hierarchical types of entities, which could be collected in most knowledge graphs. In this paper, we propose a novel method named Type-embodied Knowledge Representation Learning (TKRL) to take advantages of hierarchical entity types. We suggest that entities should have multiple representations in different types. More specifically, we consider hierarchical types as projection matrices for entities, with two type encoders designed to model hierarchical structures. Meanwhile, type information is also utilized as relation-specific type constraints. We evaluate our models on two tasks including knowledge graph completion and triple classification, and further explore the performances on long-tail dataset. Experimental results show that our models significantly outperform all baselines on both tasks, especially with long-tail distribution. It indicates that our models are capable of capturing hierarchical type information which is significant when constructing representations of knowledge graphs.

4. Ruobing Xie, Zhiyuan Liu, Jia Jia, Huanbo Luan, Maosong Sun. Representation Learning of Knowledge Graphs with Entity Descriptions. AAAI2016.

Representation learning (RL) of knowledge graphs aims to project both entities and relations into a continuous low-dimensional space. Most methods concentrate on learning representations with knowledge triples indicating relations between entities. In fact, in most knowledge graphs there are usually concise descriptions for entities, which cannot be well utilized by existing methods. In this paper, we propose a novel RL method for knowledge graphs taking advantages of entity descriptions. More specifically, we explore two encoders, including continuous bag-of-words and deep convolutional neural models to encode semantics of entity descriptions. We further learn knowledge representations with both triples and descriptions. We evaluate our method on two tasks, including knowledge graph completion and entity classification. Experimental results on realworld datasets show that, our method outperforms other baselines on the two tasks, especially under the zeroshot setting, which indicates that our method is capable of building representations for novel entities according to their descriptions. The source code of this paper can be obtained from https://github.com/xrb92/ DKRL.

5. Yu Zhao, Zhiyuan Liu, Maosong Sun. Representation Learning for Measuring Entity Relatedness with Rich Information. IJCAI2015.

Incorporating multiple types of relational information from heterogeneous networks has been proved effective in data mining. Although Wikipedia is one of the most famous heterogeneous network, previous works of semantic analysis on Wikipedia are mostly limited on single type of relations. In this paper, we aim at incorporating multiple types of relations to measure the semantic relatedness between Wikipedia entities. We propose a framework of coordinate matrix factorization to construct lowdimensional continuous representation for entities, categories and words in the same semantic space. We formulate this task as the completion of a sparse entity-entity association matrix, in which each entry quantifies the strength of relatedness between corresponding entities. We evaluate our model on the task of judging pair-wise word similarity. Experiment result shows that our model outperforms both traditional entity relatedness algorithms and other representation learning models.

6. Yan Wang, Zhiyuan Liu, Maosong Sun. Incorporating Linguistic Knowledge for Learning Distributed Word Representations

Combined with neural language models, distributed word representations achieve significant advantages in computational linguistics and text mining. Most existing models estimate distributed word vectors from large-scale data in an unsupervised fashion, which, however, do not take rich linguistic knowledge into consideration. Linguistic knowledge can be represented as either link-based knowledge or preference-based knowledge, and we propose knowledge regularized word representation models (KRWR) to incorporate these prior knowledge for learning distributed word representations. Experiment results demonstrate that our estimated word representation achieves better performance in task of semantic relatedness ranking. This indicates that our methods can efficiently encode both prior knowledge from knowledge bases and statistical knowledge from large-scale text corpora into a unified word representation model, which will benefit many tasks in text mining PLOS ONE.

7. Wanyun Cui, Xiyou Zhou, et al. Verb Pattern: A Probabilistic Semantic Representation on Verbs. AAAI2016

Verbs are important in semantic understanding of natural language. Traditional verb representations, such as FrameNet, PropBank, VerbNet, focus on verbs’ roles. These roles are too coarse to represent verbs’ semantics. In this paper, we introduce verb patterns to represent verbs’ semantics, such that each pattern corresponds to a single semantic of the verb. First we analyze the principles for verb patterns: generality and specificity. Then we propose a nonparametric model based on description length. Experimental results prove the high effectiveness of verb patterns. We further apply verb patterns to context-aware conceptualization, to show that verb patterns are helpful in semantic-related tasks.

Others

1. Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, Percy Liang. SQuAD: 100,000+ Questions for Machine Comprehension of Text, EMNLP2016

We present a new reading comprehension dataset, SQuAD, consisting of 100,000+ questions posed by crowdworkers on a set of Wikipedia articles, where the answer to each question is a segment of text from the corresponding reading passage. We analyze the dataset in both manual and automatic ways to understand the types of reasoning required to answer the questions, leaning heavily on dependency and constituency trees. We built a strong logistic regression model, which achieves an F1 score of 51.0%, a significant improvement over a simple baseline (20%). However, human performance (86.8%) is much higher, indicating that the dataset presents a good challenge problem for future research.

2. Panupong Pasupat, Percy Liang. Zero-shot entity extraction from web pages. ACL2014.

In order to extract entities of a fine-grained category from semi-structured data in web pages, existing information extraction systems rely on seed examples or redundancy across multiple web pages. In this paper, we consider a new zero-shot learning task of extracting entities specified by a natural language query (in place of seeds) given only a single web page. Our approach de- fines a log-linear model over latent extraction predicates, which select lists of entities from the web page. The main challenge is to define features on widely varying candidate entity lists. We tackle this by abstracting list elements and using aggregate statistics to define features. Finally, we created a new dataset of diverse queries and web pages, and show that our system achieves significantly better accuracy than a natural baseline.

3. Gabor Angeli, Neha Nayak and Christopher D. Manning. Combining Natural Logic and Shallow Reasoning for Question Answering. ACL2016.

Broad domain question answering is often difficult in the absence of structured knowledge bases, and can benefit from shallow lexical methods (broad coverage) and logical reasoning (high precision). We propose an approach for incorporating both of these signals in a unified framework based on natural logic. We extend the breadth of inferences afforded by natural logic to include relational entailment (e.g., buy → own) and meronymy (e.g., a person born in a city is born the city’s country). Furthermore, we train an evaluation function – akin to gameplaying – to evaluate the expected truth of candidate premises on the fly. We evaluate our approach on answering multiple choice science questions, achieving strong results on the dataset.

4. Tushar Khot, Niranjan Balasubramanian, et al. Exploring Markov Logic Networks for Question Answering. EMNLP2015.

Our goal is to answer elementary-level science questions using knowledge extracted automatically from textbooks, expressed in a subset of first-order logic. Such knowledge is incomplete and noisy. Markov Logic Networks (MLNs) seem a natural model for expressing such knowledge, but the exact way of leveraging MLNs is by no means obvious. We investigate three ways of applying MLNs to our task. First, we simply use the extracted science rules directly as MLN clauses and exploit the structure present in hard constraints to improve tractability. Second, we interpret science rules as describing prototypical entities, resulting in a drastically simplified but brittle network. Our third approach, called Praline, uses MLNs to align lexical elements as well as define and control how inference should be performed in this task. Praline demonstrates a 15% accuracy boost and a 10x reduction in runtime as compared to other MLN-based methods, and comparable accuracy to word-based baseline approaches.

5. Shuming Shi, Yuehui Wang, et al. Automatically Solving Number Word Problems by Semantic Parsing and Reasoning. EMNLP2015.

This paper presents a semantic parsing approach to automatically solving math word problems. A new meaning representation language is designed to bridge natural language text and math formulas. A CFG parser is implemented based on 9,600 semi-automatically created grammar rules. We conduct experiments on a test set of over 1000 number word problems and yield 96% precision and 62.5% recall.

6. Luheng He, Mike Lewis and Luke Zettlemoyer. Question-Answer Driven Semantic Role Labeling: Using Natural Language to Annotate Natural Language. EMNLP2015.

This paper introduces the task of question-answer driven semantic role labeling (QA-SRL), where question-answer pairs are used to represent predicate-argument structure. For example, the verb ``introduce’’ in the previous sentence would be labeled with the questions “What is introduced?”, and “What introduces something?”, each paired with the phrase from the sentence that gives the correct answer. Posing the problem this way allows the questions themselves to define the set of possible roles, without the need for predefined frame or thematic role ontologies. It also allows for scalable data collection by annotators with very little training and no linguistic expertise. We gather data in two domains, newswire text and Wikipedia articles, and introduce simple classifier-based models for predicting which questions to ask and what their answers should be. Our results show that non-expert annotators can produce high quality QA-SRL data, and also establish baseline performance levels for future work on this task.

7. Zhen Wang. Chinese Semantic Role Labeling with Bidirectional Recurrent Neural Networks. EMNLP2015.

Traditional approaches to Chinese Semantic Role Labeling (SRL) almost rely on feature engineering, which means their performances are highly dependent on a large number of handcrafted features. Even worse, the long-range dependencies in a sentence can hardly be modeled by these methods. In this paper, we introduce bidirectional recurrent neural network (RNN) with long-short-term memory (LSTM) to capture bidirectional and long-range dependencies in a sentence with minimal feature engineering. Experimental results on Chinese Proposition Bank (CPB) show a significant improvement over the state-of-the-art methods. Moreover, our model makes it convenient to introduce heterogeneous resource, which makes a further improvement to our experimental performance. Despite Chinese SRL being a specific case, our approach can be easily generalized to SRL in other languages.

8. Anders Søgaard, Barbara Plank, Hector Martinez Alonso. Using Frame Semantics for Knowledge Extraction from Twitter. AAAI2015.

Knowledge bases have the potential to advance artificial intelligence, but often suffer from recall problems, i.e., lack of knowledge of new entities and relations. On the contrary, social media such as Twitter provide abundance of data, in a timely manner: information spreads at an incredible pace and is posted long before it makes it into more commonly used resources for knowledge extraction. In this paper we address the question whether we can exploit social media to extract new facts, which may at first seem like finding needles in haystacks. We collect tweets about 60 entities in Freebase and compare four methods to extract binary relation candidates, based on syntactic and semantic parsing and simple mechanism for factuality scoring. The extracted facts are manually evaluated in terms of their correctness and relevance for search. We show that moving from bottom-up syntactic or semantic dependency parsing formalisms to top-down frame-semantic processing improves the robustness of knowledge extraction, producing more intelligible fact candidates of better quality. In order to evaluate the quality of frame semantic parsing on Twitter intrinsically, we make a multiply frame-annotated dataset of tweets publicly available.