Related papers: A Neural Network Architecture for Learning Word-Re…
Learning to rank has been intensively studied and widely applied in information retrieval. Typically, a global ranking function is learned from a set of labeled data, which can achieve good performance on average but may be suboptimal for…
Humans judge the similarity of two objects not just based on their visual appearance but also based on their semantic relatedness. However, it remains unclear how humans learn about semantic relationships between objects and categories. One…
Natural language processing (NLP) tasks tend to suffer from a paucity of suitably annotated training data, hence the recent success of transfer learning across a wide variety of them. The typical recipe involves: (i) training a deep,…
We propose two methods of learning vector representations of words and phrases that each combine sentence context with structural features extracted from dependency trees. Using several variations of neural network classifier, we show that…
We build a dual-way neural dictionary to retrieve words given definitions, and produce definitions for queried words. The model learns the two tasks simultaneously and handles unknown words via embeddings. It casts a word or a definition to…
Humans refer to objects in their environments all the time, especially in dialogue with other people. We explore generating and comprehending natural language referring expressions for objects in images. In particular, we focus on…
In this paper, we propose and investigate a new neural network architecture called Neural Random Access Machine. It can manipulate and dereference pointers to an external variable-size random-access memory. The model is trained from pure…
Textual network embeddings aim to learn a low-dimensional representation for every node in the network so that both the structural and textual information from the networks can be well preserved in the representations. Traditionally, the…
Language is crucial for human intelligence, but what exactly is its role? We take language to be a part of a system for understanding and communicating about situations. The human ability to understand and communicate about situations…
We present a context-aware neural ranking model to exploit users' on-task search activities and enhance retrieval performance. In particular, a two-level hierarchical recurrent neural network is introduced to learn search context…
We propose a principle for exploring context in machine learning models. Starting with a simple assumption that each observation may or may not depend on its context, a conditional probability distribution is decomposed into two parts:…
We present models for embedding words in the context of surrounding words. Such models, which we refer to as token embeddings, represent the characteristics of a word that are specific to a given context, such as word sense, syntactic…
The goal of language modeling techniques is to capture the statistical and structural properties of natural languages from training corpora. This task typically involves the learning of short range dependencies, which generally model the…
Word embeddings predict a word from its neighbours by learning small, dense embedding vectors. In practice, this prediction corresponds to a semantic score given to the predicted word (or term weight). We present a novel model that, given a…
We propose an architecture to jointly learn word and label embeddings for slot filling in spoken language understanding. The proposed approach encodes labels using a combination of word embeddings and straightforward word-label association…
Neural language models learn word representations, or embeddings, that capture rich linguistic and conceptual information. Here we investigate the embeddings learned by neural machine translation models, a recently-developed class of neural…
We address the problem of bootstrapping language acquisition for an artificial system similarly to what is observed in experiments with human infants. Our method works by associating meanings to words in manipulation tasks, as a robot…
Deep learning architectures based on convolutional neural networks tend to rely on continuous, smooth features. While this characteristics provides significant robustness and proves useful in many real-world tasks, it is strikingly…
We present a novel response generation system that can be trained end to end on large quantities of unstructured Twitter conversations. A neural network architecture is used to address sparsity issues that arise when integrating contextual…
Word embeddings, which represent a word as a point in a vector space, have become ubiquitous to several NLP tasks. A recent line of work uses bilingual (two languages) corpora to learn a different vector for each sense of a word, by…