Word similarity and word relatedness are fundamental to natural language processing and more generally, understanding how humans relate concepts in semantic memory. A growing number of datasets are being proposed as evaluation benchmarks,however, the heterogeneity and focus of each respective dataset makes it difficult to draw plausible conclusions as to how a unified semantic model would perform. Additionally, we want to identify the transferability of knowledge obtained from one task to another, within the same domain and across domains. Hence, this paper first presents an evaluation and comparison of eight chosen datasets tested using the best performing regression models. As a baseline, we present regression models that incorporate both lexical featuresand word embeddings to produce consistent and competitive results compared to the state of the art.We present our main contribution, the best performing model across seven of the eight datasets - a Gated Recurrent Siamese Networkthat learns relationships between lexical word definitions.A parameter transfer learning strategy is employed for theSiamese Network. Subsequently, we present a secondary contribution which is the best performing non-sequential model:an Inductive and Transductive Transfer Learning strategy fortransferring decision trees within a Random Forest to a target task that is learned from only few instances. The method involves measuring semantic distance between hidden factored matrix representations of decision tree traversal matrices.

Community Question Answering (cQA) forums are very popular nowadays, as they represent effective means for communities around particular topics to share information. Unfortunately, this information is not always factual. Thus, here we explore a new dimension in the context of cQA, which has been ignored so far: checking the veracity of answers to particular questions in cQA forums. As this is a new problem, we create a specialized dataset for it. We further propose a novel multi-faceted model, which captures information from the answer content (what is said and how), from the author profile (who says it), from the rest of the community forum (where it is said), and from external authoritative sources of information (external support). Evaluation results show a MAP value of 86.54, which is 21 points absolute above the baseline.

While the incipient internet was largely text-based, the modern digital world is becoming increasingly multi-modal. Here, we examine multi-modal classification where one modality is discrete, e.g. text, and the other is continuous, e.g. visual representations transferred from a convolutional neural network. In particular, we focus on scenarios where we have to be able to classify large quantities of data quickly. We investigate various methods for performing multi-modal fusion and analyze their trade-offs in terms of classification accuracy and computational efficiency. Our findings indicate that the inclusion of continuous information improves performance over text-only on a range of multi-modal classification tasks, even with simple fusion methods. In addition, we experiment with discretizing the continuous features in order to speed up and simplify the fusion process even further. Our results show that fusion with discretized features outperforms text-only classification, at a fraction of the computational cost of full multi-modal fusion, with the additional benefit of improved interpretability.

Automatic detection of persuasion in online discussion is key to understanding how social media is used. Predicting persuasiveness is difficult, however, due to the need to model world knowledge, dialogue, and sequential reasoning. We focus on modeling the sequence of arguments in social media posts using neural models with embeddings for words, discourse relations, and semantic frames. We demonstrate significant improvement over prior work in detecting successful arguments. We also present an error analysis assessing novice human performance at predicting persuasiveness.

Dynamic topic models (DTM) are commonly used for mining latent topics in evolving web corpora. In this paper, we note that a major limitation of the conventional DTM based models is that they assume a predetermined and fixed scale of topics. In reality, however, topics may have varying spans and topics of multiple scales can co-exist in a single web or social media data stream. Therefore, DTMs that assume a fixed epoch length may not be able to effectively capture latent topics and thus negatively affect accuracy. In this paper, we propose a Multi-Scale Dynamic Topic Model (MS-DTM) and a complementary Incremental Multi-Scale Dynamic Topic Model (IMS-DTM) inference method that can be used to capture latent topics and their dynamics simultaneously, at different scales. In this model, topic specific feature distributions are generated based on a multi-scale feature distribution of the previous epochs; moreover, multiple scales of the current epoch are analyzed together through a novel multi-scale incremental Gibbs sampling technique. We show that the proposed model significantly improves efficiency and effectiveness compared to the single scale dynamic DTMs and prior models that consider only multiple scales of the past.

Using a dictionary to map independently trained word embeddings to a shared space has shown to be an effective approach to learn bilingual word embeddings. In this work, we propose a multi-step framework of linear transformations that generalizes a substantial body of previous work. The core step of the framework is an orthogonal transformation, and existing methods can be explained in terms of the additional normalization, whitening, re-weighting, de-whitening and dimensionality reduction steps. This allows us to gain new insights into the behavior of existing methods, including the effectiveness of inverse regression, and design a novel variant that obtains the best published results in zero-shot bilingual lexicon extraction. The corresponding software is released as an open source project.

Word sense induction is the most prominent unsupervised approach to lexical disambiguation. It clusters word instances, typically represented by their bag-of-words contexts. Therefore, uninformative and ambiguous contexts present a major challenge. In this paper, we investigate the use of an alternative instance representation based on lexical substitutes , i.e., contextually suitable, meaning-preserving replacements. Using lexical substitutes predicted by a state-of-the-art automatic system and a simple clustering algorithm, we outperform bag-of-words instance representations and compete with much more complex structured probabilistic models. Furthermore, we show that an oracle based on manually-labeled lexical substitutes yields yet substantially higher performance. Taken together, this provides evidence for a complementarity between word sense induction and lexical substitution that has not been given much consideration before.

Semantic Role Labeling (SRL) is believed to be a crucial step towards natural language understanding and has been widely studied. Recent years, end-to-end SRL with recurrent neural networks (RNN) has gained increasing attention. However, it remains a major challenge for RNNs to handle structural information and long range dependencies. In this paper, we present a simple and effective architecture for SRL which aims to address these problems. Our model is based on self-attention which can directly capture the relationships between two tokens regardless of their distance. Our single model achieves F1=83.4 on the CoNLL-2005 shared task dataset and F1=82.7 on the CoNLL-2012 shared task dataset, which outperforms the previous state-of-the-art results by 1.8 and 1.0 F1 score respectively. Besides, our model is computationally efficient, and the parsing speed is 50K tokens per second on a single Titan X GPU.

Statistical script learning is an effective way to acquire world knowledge which can be used for commonsense reasoning. Statistical script learning induces this knowledge by observing event sequences generated from texts. The learned model thus can predict subsequent events, given earlier events. Recent approaches rely on learning event embeddings which capture script knowledge. In this work, we suggest a general learning model–Featured Event Embedding Learning (FEEL)–for injecting event embeddings with fine grained information. In addition to capturing the dependencies between subsequent events, our model can take into account higher level abstractions of the input event which help the model generalize better and account for the global context in which the event appears. We evaluated our model over three narrative cloze tasks, and showed that our model is competitive with the most recent state-of-the-art. We also show that our resulting embedding can be used as a strong representation for advanced semantic tasks such as discourse parsing and sentence semantic relatedness.

Context-based word embedding learning approaches can model rich semantic and syntactic information. However, it is problematic for sentiment analysis because the words with similar contexts but opposite sentiment polarities, such as good and bad, are mapped into close word vectors in the embedding space. Recently, some sentiment embedding learning methods have been proposed, but most of them are designed to work well on sentence-level texts. Directly applying those models to document-level texts often leads to unsatisfied results. To address this issue, we present a sentiment-specific word embedding learning architecture that utilizes local context informationas well as global sentiment representation. The architecture is applicable for both sentence-level and document-level texts. We take global sentiment representation as a simple average of word embeddings in the text, and use a corruption strategy as a sentiment-dependent regularization. Extensive experiments conducted on several benchmark datasets demonstrate that the proposed architecture outperforms the state-of-the-art methods for sentiment classification.