Language grounding is an active field aiming at enriching textual representations with visual information. Generally, textual and visual elements are embedded in the same representation space, which implicitly assumes a one-to-one correspondence between modalities. This hypothesis does not hold when representing words, and becomes problematic when used to learn sentence representations --- the focus of this paper --- as a visual scene can be described by a wide variety of sentences. To overcome this limitation, we propose to transfer visual information to textual representations by learning an intermediate representation space: the grounded space. We further propose two new complementary objectives ensuring that (1) sentences associated with the same visual content are close in the grounded space and (2) similarities between related elements are preserved across modalities. We show that this model outperforms the previous state-of-the-art on classification and semantic relatedness tasks.
Abstractive summarization approaches based on Reinforcement Learning (RL) have recently been proposed to overcome classical likelihood maximization. RL enables to consider complex, possibly non-differentiable, metrics that globally assess the quality and relevance of the generated outputs. ROUGE, the most used summarization metric, is known to suffer from bias towards lexical similarity as well as from suboptimal accounting for fluency and readability of the generated abstracts. We thus explore and propose alternative evaluation measures: the reported human-evaluation analysis shows that the proposed metrics, based on Question Answering, favorably compares to ROUGE -- with the additional property of not requiring reference summaries. Training a RL-based model on these metrics leads to improvements (both in terms of human or automated metrics) over current approaches that use ROUGE as a reward.
Zero-Shot Learning (ZSL) aims at classifying unlabeled objects by leveraging auxiliary knowledge, such as semantic representations. A limitation of previous approaches is that only intrinsic properties of objects, e.g. their visual appearance, are taken into account while their context, e.g. the surrounding objects in the image, is ignored. Following the intuitive principle that objects tend to be found in certain contexts but not others, we propose a new and challenging approach, context-aware ZSL, that leverages semantic representations in a new way to model the conditional likelihood of an object to appear in a given context. Finally, through extensive experiments conducted on Visual Genome, we show that contextual information can substantially improve the standard ZSL approach and is robust to unbalanced classes.
Representing the semantics of words is a long-standing problem for the natural language processing community. Most methods compute word semantics given their textual context in large corpora. More recently, researchers attempted to integrate perceptual and visual features. Most of these works consider the visual appearance of objects to enhance word representations but they ignore the visual environment and context in which objects appear. We propose to unify text-based techniques with vision-based techniques by simultaneously leveraging textual and visual context to learn multimodal word embeddings. We explore various choices for what can serve as a visual context and present an end-to-end method to integrate visual context elements in a multimodal skip-gram model. We provide experiments and extensive analysis of the obtained results.
We present a novel method for efficiently searching top-k neighbors for documents represented in high dimensional space of terms based on the cosine similarity. Mostly, documents are stored as bag-of-words tf-idf representation. One of the most used ways of computing similarity between a pair of documents is cosine similarity between the vector representations, but cosine similarity is not a metric distance measure as it doesn't follow triangle inequality, therefore most metric searching methods can not be applied directly. We propose an efficient method for indexing documents using a pivot tree that leads to efficient retrieval. We also study the relation between precision and efficiency for the proposed method and compare it with a state of the art in the area of document searching based on inner product.
Information Retrieval (IR) models need to deal with two difficult issues, vocabulary mismatch and term dependencies. Vocabulary mismatch corresponds to the difficulty of retrieving relevant documents that do not contain exact query terms but semantically related terms. Term dependencies refers to the need of considering the relationship between the words of the query when estimating the relevance of a document. A multitude of solutions has been proposed to solve each of these two problems, but no principled model solve both. In parallel, in the last few years, language models based on neural networks have been used to cope with complex natural language processing tasks like emotion and paraphrase detection. Although they present good abilities to cope with both term dependencies and vocabulary mismatch problems, thanks to the distributed representation of words they are based upon, such models could not be used readily in IR, where the estimation of one language model per document (or query) is required. This is both computationally unfeasible and prone to over-fitting. Based on a recent work that proposed to learn a generic language model that can be modified through a set of document-specific parameters, we explore use of new neural network models that are adapted to ad-hoc IR tasks. Within the language model IR framework, we propose and study the use of a generic language model as well as a document-specific language model. Both can be used as a smoothing component, but the latter is more adapted to the document at hand and has the potential of being used as a full document language model. We experiment with such models and analyze their results on TREC-1 to 8 datasets.