Total: 42
The task of event extraction has long been investigated in a supervised learning paradigm, which is bound by the number and the quality of the training instances. Existing training data must be manually generated through a combination of expert domain knowledge and extensive human involvement. However, due to drastic efforts required in annotating text, the resultant datasets are usually small, which severally affects the quality of the learned model, making it hard to generalize. Our work develops an automatic approach for generating training data for event extraction. Our approach allows us to scale up event extraction training instances from thousands to hundreds of thousands, and it does this at a much lower cost than a manual approach. We achieve this by employing distant supervision to automatically create event annotations from unlabelled text using existing structured knowledge bases or tables.We then develop a neural network model with post inference to transfer the knowledge extracted from structured knowledge bases to automatically annotate typed events with corresponding arguments in text.We evaluate our approach by using the knowledge extracted from Freebase to label texts from Wikipedia articles. Experimental results show that our approach can generate a large number of highquality training instances. We show that this large volume of training data not only leads to a better event extractor, but also allows us to detect multiple typed events.
Multimodal models have been proven to outperform text-based models on learning semantic word representations. Almost all previous multimodal models typically treat the representations from different modalities equally. However, it is obvious that information from different modalities contributes differently to the meaning of words. This motivates us to build a multimodal model that can dynamically fuse the semantic representations from different modalities according to different types of words. To that end, we propose three novel dynamic fusion methods to assign importance weights to each modality, in which weights are learned under the weak supervision of word association pairs. The extensive experiments have demonstrated that the proposed methods outperform strong unimodal baselines and state-of-the-art multimodal models.
Multimodal models have been proven to outperform text-based approaches on learning semantic representations. However, it still remains unclear what properties are encoded in multimodal representations, in what aspects do they outperform the single-modality representations, and what happened in the process of semantic compositionality in different input modalities. Considering that multimodal models are originally motivated by human concept representations, we assume that correlating multimodal representations with brain-based semantics would interpret their inner properties to answer the above questions. To that end, we propose simple interpretation methods based on brain-based componential semantics. First we investigate the inner properties of multimodal representations by correlating them with corresponding brain-based property vectors. Then we map the distributed vector space to the interpretable brain-based componential space to explore the inner properties of semantic compositionality. Ultimately, the present paper sheds light on the fundamental questions of natural language understanding, such as how to represent the meaning of words and how to combine word meanings into larger units.
Bayesian inference methods for probabilistic topic models can quantify uncertainty in the parameters, which has primarily been used to increase the robustness of parameter estimates. In this work, we explore other rich information that can be obtained by analyzing the posterior distributions in topic models. Experimenting with latent Dirichlet allocation on two datasets, we propose ideas incorporating information about the posterior distributions at the topic level and at the word level. At the topic level, we propose a metric called topic stability that measures the variability of the topic parameters under the posterior. We show that this metric is correlated with human judgments of topic quality as well as with the consistency of topics appearing across multiple models. At the word level, we experiment with different methods for adjusting individual word probabilities within topics based on their uncertainty. Humans prefer words ranked by our adjusted estimates nearly twice as often when compared to the traditional approach. Finally, we describe how the ideas presented in this work could potentially applied to other predictive or exploratory models in future work.
Event extraction plays an important role in natural language processing (NLP) applications including question answering and information retrieval. Traditional event extraction relies heavily on lexical and syntactic features, which require intensive human engineering and may not generalize to different datasets. Deep neural networks, on the other hand, are able to automatically learn underlying features, but existing networks do not make full use of syntactic relations. In this paper, we propose a novel dependency bridge recurrent neural network (dbRNN) for event extraction. We build our model upon a recurrent neural network, but enhance it with dependency bridges, which carry syntactically related information when modeling each word.We illustrates that simultaneously applying tree structure and sequence structure in RNN brings much better performance than only uses sequential RNN. In addition, we use a tensor layer to simultaneously capture the various types of latent interaction between candidate arguments as well as identify/classify all arguments of an event. Experiments show that our approach achieves competitive results compared with previous work.
In this paper, we present a novel approach to machine reading comprehension for the MS-MARCO dataset. Unlike the SQuAD dataset that aims to answer a question with exact text spans in a passage, the MS-MARCO dataset defines the task as answering a question from multiple passages and the words in the answer are not necessary in the passages. We therefore develop an extraction-then-synthesis framework to synthesize answers from extraction results. Specifically, the answer extraction model is first employed to predict the most important sub-spans from the passage as evidence, and the answer synthesis model takes the evidence as additional features along with the question and passage to further elaborate the final answers. We build the answer extraction model with state-of-the-art neural networks for single passage reading comprehension, and propose an additional task of passage ranking to help answer extraction in multiple passages. The answer synthesis model is based on the sequence-to-sequence neural networks with extracted evidences as features. Experiments show that our extraction-then-synthesis method outperforms state-of-the-art methods.
There are two major problems in duplicate question identification, namely lexical gap and essential constituents matching. Previous methods either design various similarity features or learn representations via neural networks, which try to solve the lexical gap but neglect the essential constituents matching. In this paper, we focus on the essential constituents matching problem and use FrameNet-style semantic parsing to tackle it. Two approaches are proposed to integrate FrameNet parsing with neural networks. An ensemble approach combines a traditional model with manually designed features and a neural network model. An embedding approach converts frame parses to embeddings, which are combined with word embeddings at the input of neural networks. Experiments on Quora question pairs dataset demonstrate that the ensemble approach is more effective and outperforms all baselines.
Network representation has been recently exploited for many applications, such as citation recommendation, multi-label classification and link prediction. It learns low-dimensional vector representation for each vertex in networks. Existing network representation methods only focus on incomplete aspects of vertex information (i.e., vertex content, network structure or partial integration), moreover they are commonly designed for homogeneous information networks where all the vertices of a network are of the same type. In this paper, we propose a deep network representation model that integrates network structure and the vertex content information into a unified framework by exploiting generative adversarial network, and represents different types of vertices in the heterogeneous network in a continuous and common vector space. Based on the proposed model, we can obtain heterogeneous bibliographic network representation for efficient citation recommendation. The proposed model also makes personalized citation recommendation possible, which is a new issue that a few papers addressed in the past. When evaluated on the AAN and DBLP datasets, the performance of the proposed heterogeneous bibliographic network based citation recommendation approach is comparable with that of the other network representation based citation recommendation approaches. The results also demonstrate that the personalized citation recommendation approach is more effective than the non-personalized citation recommendation approach.
Fine-grained entity typing aims to identify the semantic type of an entity in a particular plain text. It is an important task which can be helpful for a lot of natural language processing (NLP) applications. Most existing methods typically extract features separately from the entity mention and context words for type classification. These methods inevitably fail to model complex correlations between entity mentions and context words. They also neglect rich background information about these entities in knowledge bases (KBs). To address these issues, we take information from KBs into consideration to bridge entity mentions and their context together, and thereby propose Knowledge-Attention Neural Fine-Grained Entity Typing. Experimental results and case studies on real-world datasets demonstrate that our model significantly outperforms other state-of-the-art methods, revealing the effectiveness of incorporating KB information for entity typing. Code and data for this paper can be found at https://github.com/thunlp/KNET.
The current neural network models for event detection have only considered the sequential representation of sentences. Syntactic representations have not been explored in this area although they provide an effective mechanism to directly link words to their informative context for event detection in the sentences. In this work, we investigate a convolutional neural network based on dependency trees to perform event detection. We propose a novel pooling method that relies on entity mentions to aggregate the convolution vectors. The extensive experiments demonstrate the benefits of the dependency-based convolutional neural networks and the entity mention-based pooling method for event detection. We achieve the state-of-the-art performance on widely used datasets with both perfect and predicted entity mentions.
In this paper, we focus on multiple-choice reading comprehension which aims to answer a question given a passage and multiple candidate options. We present the hierarchical attention flow to adequately leverage candidate options to model the interactions among passages, questions and candidate options. We observe that leveraging candidate options to boost evidence gathering from the passages play a vital role in this task, which is ignored in previous works. In addition, we explicitly model the option correlations with attention mechanism to obtain better option representations, which are further fed into a bilinear layer to obtain the ranking score for each option. On a large-scale multiple-choice reading comprehension dataset (i.e. the RACE dataset), the proposed model outperforms two previous neural network baselines on both RACE-M and RACE-H subsets and yields the state-of-the-art overall results.
Hidden variable models are important tools for solving open domain machine comprehension tasks and have achieved remarkable accuracy in many question answering benchmark datasets. Existing models impose strong independence assumptions on hidden variables, which leaves the interaction among them unexplored. Here we introduce linguistic structures to help capturing global evidence in hidden variable modeling. In the proposed algorithms, question-answer pairs are scored based on structured inference results on parse trees and semantic frames, which aims to assign hidden variables in a global optimal way. Experiments on the MCTest dataset demonstrate that the proposed models are highly competitive with state-of-the-art machine comprehension systems.
Distant supervised relation extraction is an efficient approach to scale relation extraction to very large corpora, and has been widely used to find novel relational facts from plain text. Recent studies on neural relation extraction have shown great progress on this task via modeling the sentences in low-dimensional spaces, but seldom considered syntax information to model the entities. In this paper, we propose to learn syntax-aware entity embedding for neural relation extraction. First, we encode the context of entities on a dependency tree as sentence-level entity embedding based on tree-GRU. Then, we utilize both intra-sentence and inter-sentence attentions to obtain sentence set-level entity embedding over all sentences containing the focus entity pair. Finally, we combine both sentence embedding and entity embedding for relation classification. We conduct experiments on a widely used real-world dataset and the experimental results show that our model can make full use of all informative instances and achieve state-of-the-art performance of relation extraction.
For the task of entity disambiguation, mention contexts and entity descriptions both contain various kinds of information content while only a subset of them are helpful for disambiguation. In this paper, we propose a type-aware co-attention model for entity disambiguation, which tries to identify the most discriminative words from mention contexts and most relevant sentences from corresponding entity descriptions simultaneously. To bridge the semantic gap between mention contexts and entity descriptions, we further incorporate entity type information to enhance the co-attention mechanism. Our evaluation shows that the proposed model outperforms the state-of-the-arts on three public datasets. Further analysis also confirms that both the co-attention mechanism and the type-aware mechanism are effective.
Word embedding has been widely used in many natural language processing tasks. In this paper, we focus on learning word embeddings through selective higher-order relationships in sentences to improve the embeddings to be less sensitive to local context and more accurate in capturing semantic compositionality. We present a novel multi-order dependency-based strategy to composite and represent the context under several essential constraints. In order to realize selective learning from the word contexts, we automatically assign the strengths of different dependencies between co-occurred words in the stochastic gradient descent process. We evaluate and analyze our proposed approach using several direct and indirect tasks for word embeddings. Experimental results demonstrate that our embeddings are competitive to or better than state-of-the-art methods and significantly outperform other methods in terms of context stability. The output weights and representations of dependencies obtained in our embedding model conform to most of the linguistic characteristics and are valuable for many downstream tasks.
Deep learning has demonstrated tremendous potential for Automatic Text Scoring (ATS) tasks. In this paper, we describe a new neural architecture that enhances vanilla neural network models with auxiliary neural coherence features. Our new method proposes a new SkipFlow mechanism that models relationships between snapshots of the hidden representations of a long short-term memory (LSTM) network as it reads. Subsequently, the semantic relationships between multiple snapshots are used as auxiliary features for prediction. This has two main benefits. Firstly, essays are typically long sequences and therefore the memorization capability of the LSTM network may be insufficient. Implicit access to multiple snapshots can alleviate this problem by acting as a protection against vanishing gradients. The parameters of the SkipFlow mechanism also acts as an auxiliary memory. Secondly, modeling relationships between multiple positions allows our model to learn features that represent and approximate textual coherence. In our model, we call this neural coherence features. Overall, we present a unified deep learning architecture that generates neural coherence features as it reads in an end-to-end fashion. Our approach demonstrates state-of-the-art performance on the benchmark ASAP dataset, outperforming not only feature engineering baselines but also other deep learning models.
End-to-end argument mining has enabled the development of new automated essay scoring (AES) systems that use argumentative features (e.g., number of claims, number of support relations) in addition to traditional legacy features (e.g., grammar, discourse structure) when scoring persuasive essays. While prior research has proposed different argumentative features as well as empirically demonstrated their utility for AES, these studies have all had important limitations. In this paper we identify a set of desiderata for evaluating the use of argument mining for AES, introduce an end-to-end argument mining system and associated argumentative feature sets, and present the results of several studies that both satisfy the desiderata and demonstrate the value-added of argument mining for scoring persuasive essays.
Representation learning is a fundamental problem in natural language processing. This paper studies how to learn a structured representation for text classification. Unlike most existing representation models that either use no structure or rely on pre-specified structures, we propose a reinforcement learning (RL) method to learn sentence representation by discovering optimized structures automatically. We demonstrate two attempts to build structured representation: Information Distilled LSTM (ID-LSTM) and Hierarchically Structured LSTM (HS-LSTM). ID-LSTM selects only important, task-relevant words, and HS-LSTM discovers phrase structures in a sentence. Structure discovery in the two representation models is formulated as a sequential decision problem: current decision of structure discovery affects following decisions, which can be addressed by policy gradient RL. Results show that our method can learn task-friendly representations by identifying important words or task-relevant structures without explicit structure annotations, and thus yields competitive performance.
Analyzing people’s opinions and sentiments towards certain aspects is an important task of natural language understanding. In this paper, we propose a novel solution to targeted aspect-based sentiment analysis, which tackles the challenges of both aspect-based sentiment analysis and targeted sentiment analysis by exploiting commonsense knowledge. We augment the long short-term memory (LSTM) network with a hierarchical attention mechanism consisting of a target-level attention and a sentence-level attention. Commonsense knowledge of sentiment-related concepts is incorporated into the end-to-end training of a deep neural network for sentiment classification. In order to tightly integrate the commonsense knowledge into the recurrent encoder, we propose an extension of LSTM, termed Sentic LSTM. We conduct experiments on two publicly released datasets, which show that the combination of the proposed attention architecture and Sentic LSTM can outperform state-of-the-art methods in targeted aspect sentiment tasks.
Aspect-based sentiment analysis (ABSA) tries to predict the polarity of a given document with respect to a given aspect entity. While neural network architectures have been successful in predicting the overall polarity of sentences, aspect-specific sentiment analysis still remains as an open problem. In this paper, we propose a novel method for integrating aspect information into the neural model. More specifically, we incorporate aspect information into the neural model by modeling word-aspect relationships. Our novel model, Aspect Fusion LSTM (AF-LSTM) learns to attend based on associative relationships between sentence words and aspect which allows our model to adaptively focus on the correct words given an aspect term. This ameliorates the flaws of other state-of-the-art models that utilize naive concatenations to model word-aspect similarity. Instead, our model adopts circular convolution and circular correlation to model the similarity between aspect and words and elegantly incorporates this within a differentiable neural attention framework. Finally, our model is end-to-end differentiable and highly related to convolution-correlation (holographic like) memories. Our proposed neural model achieves state-of-the-art performance on benchmark datasets, outperforming ATAE-LSTM by 4%-5% on average across multiple datasets.
The machine reading task, where a computer reads a document and answers questions about it, is important in artificial intelligence research. Recently, many models have been proposed to address it. Word-level models, which have words as units of input and output, have proven to yield state-of-the-art results when evaluated on English datasets. However, in morphologically richer languages, many more unique words exist than in English due to highly productive prefix and suffix mechanisms. This may set back word-level models, since vocabulary sizes too big to allow for efficient computing may have to be employed. Multiple alternative input granularities have been proposed to avoid large input vocabularies, such as morphemes, character n-grams, and bytes. Bytes are advantageous as they provide a universal encoding format across languages, and allow for a small vocabulary size, which, moreover, is identical for every input language. In this work, we investigate whether bytes are suitable as input units across morphologically varied languages. To test this, we introduce two large-scale machine reading datasets in morphologically rich languages, Turkish and Russian. We implement 4 byte-level models, representing the major types of machine reading models and introduce a new seq2seq variant, called encoder-transformer-decoder. We show that, for all languages considered, there are models reading bytes outperforming the current state-of-the-art word-level baseline. Moreover, the newly introduced encoder-transformer-decoder performs best on the morphologically most involved dataset, Turkish. The large-scale Turkish and Russian machine reading datasets are released to public.
In this paper, we aim at tackling the problem of dynamic user profiling in the context of streams of short texts. Profiling users' expertise in such context is more challenging than in the case of long documents in static collection as it is difficult to track users' dynamic expertise in streaming sparse data. To obtain better profiling performance, we propose a streaming profiling algorithm (SPA). SPA first utilizes the proposed user expertise tracking topic model (UET) to track the changes of users' dynamic expertise and then utilizes the proposed streaming keyword diversification algorithm (SKDA) to produce top-k diversified keywords for profiling users' dynamic expertise at a specific point in time. Experimental results validate the effectiveness of the proposed algorithms.
We present assertion based question answering (ABQA), an open domain question answering task that takes a question and a passage as inputs, and outputs a semi-structured assertion consisting of a subject, a predicate and a list of arguments. An assertion conveys more evidences than a short answer span in reading comprehension, and it is more concise than a tedious passage in passage-based QA. These advantages make ABQA more suitable for human-computer interaction scenarios such as voice-controlled speakers. Further progress towards improving ABQA requires richer supervised dataset and powerful models of text understanding. To remedy this, we introduce a new dataset called WebAssertions, which includes hand-annotated QA labels for 358,427 assertions in 55,960 web passages. To address ABQA, we develop both generative and extractive approaches. The backbone of our generative approach is sequence to sequence learning. In order to capture the structure of the output assertion, we introduce a hierarchical decoder that first generates the structure of the assertion and then generates the words of each field. The extractive approach is based on learning to rank. Features at different levels of granularity are designed to measure the semantic relevance between a question and an assertion. Experimental results show that our approaches have the ability to infer question-aware assertions from a passage. We further evaluate our approaches by incorporating the ABQA results as additional features in passage-based QA. Results on two datasets show that ABQA features significantly improve the accuracy on passage-based QA.
In recent years researchers have achieved considerable success applying neural network methods to question answering (QA). These approaches have achieved state of the art results in simplified closed-domain settings such as the SQuAD (Rajpurkar et al. 2016) dataset, which provides a pre-selected passage, from which the answer to a given question may be extracted. More recently, researchers have begun to tackle open-domain QA, in which the model is given a question and access to a large corpus (e.g., wikipedia) instead of a pre-selected passage (Chen et al. 2017a). This setting is more complex as it requires large-scale search for relevant passages by an information retrieval component, combined with a reading comprehension model that “reads” the passages to generate an answer to the question. Performance in this setting lags well behind closed-domain performance. In this paper, we present a novel open-domain QA system called Reinforced Ranker-Reader (R3), based on two algorithmic innovations. First, we propose a new pipeline for open-domain QA with a Ranker component, which learns to rank retrieved passages in terms of likelihood of extracting the ground-truth answer to a given question. Second, we propose a novel method that jointly trains the Ranker along with an answer-extraction Reader model, based on reinforcement learning. We report extensive experimental results showing that our method significantly improves on the state of the art for multiple open-domain QA datasets.
Neural network methods have achieved great success in reviews sentiment classification. Recently, some works achieved improvement by incorporating user and product information to generate a review representation. However, in reviews, we observe that some words or sentences show strong user's preference, and some others tend to indicate product's characteristic. The two kinds of information play different roles in determining the sentiment label of a review. Therefore, it is not reasonable to encode user and product information together into one representation. In this paper, we propose a novel framework to encode user and product information. Firstly, we apply two individual hierarchical neural networks to generate two representations, with user attention or with product attention. Then, we design a combined strategy to make full use of the two representations for training and final prediction. The experimental results show that our model obviously outperforms other state-of-the-art methods on IMDB and Yelp datasets. Through the visualization of attention over words related to user or product, we validate our observation mentioned above.