Results 1 - 10
of
79
Deep fragment embeddings for bidirectional image sentence mapping
- In arXiv:1406.5679
, 2014
"... We introduce a model for bidirectional retrieval of images and sentences through a deep, multi-modal embedding of visual and natural language data. Unlike pre-vious models that directly map images or sentences into a common embedding space, our model works on a finer level and embeds fragments of im ..."
Abstract
-
Cited by 29 (2 self)
- Add to MetaCart
(Show Context)
We introduce a model for bidirectional retrieval of images and sentences through a deep, multi-modal embedding of visual and natural language data. Unlike pre-vious models that directly map images or sentences into a common embedding space, our model works on a finer level and embeds fragments of images (ob-jects) and fragments of sentences (typed dependency tree relations) into a com-mon space. We then introduce a structured max-margin objective that allows our model to explicitly associate these fragments across modalities. Extensive exper-imental evaluation shows that reasoning on both the global level of images and sentences and the finer level of their respective fragments improves performance on image-sentence retrieval tasks. Additionally, our model provides interpretable predictions for the image-sentence retrieval task since the inferred inter-modal alignment of fragments is explicit. 1
Improved semantic representations from treestructured long short-term memory networks
- In Proc. ACL
, 2015
"... Because of their superior ability to pre-serve sequence information over time, Long Short-Term Memory (LSTM) net-works, a type of recurrent neural net-work with a more complex computational unit, have obtained strong results on a va-riety of sequence modeling tasks. The only underlying LSTM structur ..."
Abstract
-
Cited by 14 (1 self)
- Add to MetaCart
(Show Context)
Because of their superior ability to pre-serve sequence information over time, Long Short-Term Memory (LSTM) net-works, a type of recurrent neural net-work with a more complex computational unit, have obtained strong results on a va-riety of sequence modeling tasks. The only underlying LSTM structure that has been explored so far is a linear chain. However, natural language exhibits syn-tactic properties that would naturally com-bine words to phrases. We introduce the Tree-LSTM, a generalization of LSTMs to tree-structured network topologies. Tree-LSTMs outperform all existing systems and strong LSTM baselines on two tasks: predicting the semantic relatedness of two
Efficient Non-parametric Estimation of Multiple Embeddings per Word in Vector Space
"... There is rising interest in vector-space word embeddings and their use in NLP, especially given recent methods for their fast estimation at very large scale. Nearly all this work, however, assumes a sin-gle vector per word type—ignoring poly-semy and thus jeopardizing their useful-ness for downstrea ..."
Abstract
-
Cited by 11 (1 self)
- Add to MetaCart
There is rising interest in vector-space word embeddings and their use in NLP, especially given recent methods for their fast estimation at very large scale. Nearly all this work, however, assumes a sin-gle vector per word type—ignoring poly-semy and thus jeopardizing their useful-ness for downstream tasks. We present an extension to the Skip-gram model that efficiently learns multiple embeddings per word type. It differs from recent related work by jointly performing word sense discrimination and embedding learning, by non-parametrically estimating the num-ber of senses per word type, and by its ef-ficiency and scalability. We present new state-of-the-art results in the word similar-ity in context task and demonstrate its scal-ability by training with one machine on a corpus of nearly 1 billion tokens in less than 6 hours. 1
A Neural Network for Factoid Question Answering over Paragraphs
"... Text classification methods for tasks like factoid question answering typi-cally use manually defined string match-ing rules or bag of words representa-tions. These methods are ineffective when question text contains very few individual words (e.g., named entities) that are indicative of the answer. ..."
Abstract
-
Cited by 9 (1 self)
- Add to MetaCart
Text classification methods for tasks like factoid question answering typi-cally use manually defined string match-ing rules or bag of words representa-tions. These methods are ineffective when question text contains very few individual words (e.g., named entities) that are indicative of the answer. We introduce a recursive neural network (rnn) model that can reason over such input by modeling textual composition-ality. We apply our model, qanta, to a dataset of questions from a trivia competition called quiz bowl. Unlike previous rnn models, qanta learns word and phrase-level representations that combine across sentences to reason about entities. The model outperforms multiple baselines and, when combined with information retrieval methods, ri-vals the best human players. 1
A Multiplicative Model for Learning Distributed Text-Based Attribute Representations
"... In this paper we propose a general framework for learning distributed represen-tations of attributes: characteristics of text whose representations can be jointly learned with word embeddings. Attributes can correspond to a wide variety of concepts, such as document indicators (to learn sentence vec ..."
Abstract
-
Cited by 7 (1 self)
- Add to MetaCart
(Show Context)
In this paper we propose a general framework for learning distributed represen-tations of attributes: characteristics of text whose representations can be jointly learned with word embeddings. Attributes can correspond to a wide variety of concepts, such as document indicators (to learn sentence vectors), language in-dicators (to learn distributed language representations), meta-data and side infor-mation (such as the age, gender and industry of a blogger) or representations of authors. We describe a third-order model where word context and attribute vectors interact multiplicatively to predict the next word in a sequence. This leads to the notion of conditional word similarity: how meanings of words change when con-ditioned on different attributes. We perform several experimental tasks including sentiment classification, cross-lingual document classification, and blog author-ship attribution. We also qualitatively evaluate conditional word neighbours and attribute-conditioned text generation. 1
Factor-based compositional embedding models
- In NIPS Workshop on Learning Semantics
, 2014
"... Introduction Word embeddings, which are distributed word representations learned by neural language models [1, 2, 3], have been shown to be powerful word representations. They have been successfully applied to a range of NLP tasks, including syntax [2, 4, 5] and semantics [6, 7, 8]. Information abou ..."
Abstract
-
Cited by 7 (2 self)
- Add to MetaCart
(Show Context)
Introduction Word embeddings, which are distributed word representations learned by neural language models [1, 2, 3], have been shown to be powerful word representations. They have been successfully applied to a range of NLP tasks, including syntax [2, 4, 5] and semantics [6, 7, 8]. Information about language structure is critical in many NLP tasks, where substructures of a sen-tence and its annotations inform downstream NLP task. Yet word representations alone do not
Deep recursive neural networks for compositionality in language
- In Advances in Neural Information Processing Systems
, 2014
"... Recursive neural networks comprise a class of architecture that can operate on structured input. They have been previously successfully applied to model com-positionality in natural language using parse-tree-based structural representations. Even though these architectures are deep in structure, the ..."
Abstract
-
Cited by 5 (0 self)
- Add to MetaCart
(Show Context)
Recursive neural networks comprise a class of architecture that can operate on structured input. They have been previously successfully applied to model com-positionality in natural language using parse-tree-based structural representations. Even though these architectures are deep in structure, they lack the capacity for hierarchical representation that exists in conventional deep feed-forward networks as well as in recently investigated deep recurrent neural networks. In this work we introduce a new architecture — a deep recursive neural network (deep RNN) — constructed by stacking multiple recursive layers. We evaluate the proposed model on the task of fine-grained sentiment classification. Our results show that deep RNNs outperform associated shallow counterparts that employ the same number of parameters. Furthermore, our approach outperforms previous baselines on the sentiment analysis task, including a multiplicative RNN variant as well as the re-cently introduced paragraph vectors, achieving new state-of-the-art results. We provide exploratory analyses of the effect of multiple layers and show that they capture different aspects of compositionality in language. 1
Modelling, visualising and summarising documents with a single convolutional neural network
, 2014
"... Capturing the compositional process which maps the meaning of words to that of documents is a central challenge for researchers in Natural Language Process-ing and Information Retrieval. We introduce a model that is able to represent the meaning of documents by embedding them in a low dimensional ve ..."
Abstract
-
Cited by 5 (0 self)
- Add to MetaCart
(Show Context)
Capturing the compositional process which maps the meaning of words to that of documents is a central challenge for researchers in Natural Language Process-ing and Information Retrieval. We introduce a model that is able to represent the meaning of documents by embedding them in a low dimensional vector space, while preserving distinctions of word and sentence order crucial for capturing nu-anced semantics. Our model is based on an extended Dynamic Convolution Neu-ral Network, which learns convolution filters at both the sentence and document level, hierarchically learning to capture and compose low level lexical features into high level semantic concepts. We demonstrate the effectiveness of this model on a range of document modelling tasks, achieving strong results with no fea-ture engineering and with a more compact model. Inspired by recent advances in visualising deep convolution networks for computer vision, we present a novel vi-sualisation technique for our document networks which not only provides insight into their learning process, but also can be interpreted to produce a compelling automatic summarisation system for texts. 1
A Model of Coherence Based on Distributed Sentence Representation
"... Coherence is what makes a multi-sentence text meaningful, both logically and syn-tactically. To solve the challenge of or-dering a set of sentences into coherent or-der, existing approaches focus mostly on defining and using sophisticated features to capture the cross-sentence argumenta-tion logic a ..."
Abstract
-
Cited by 4 (2 self)
- Add to MetaCart
(Show Context)
Coherence is what makes a multi-sentence text meaningful, both logically and syn-tactically. To solve the challenge of or-dering a set of sentences into coherent or-der, existing approaches focus mostly on defining and using sophisticated features to capture the cross-sentence argumenta-tion logic and syntactic relationships. But both argumentation semantics and cross-sentence syntax (such as coreference and tense rules) are very hard to formalize. In this paper, we introduce a neural network model for the coherence task based on distributed sentence representation. The proposed approach learns a syntactico-semantic representation for sentences au-tomatically, using either recurrent or re-cursive neural networks. The architecture obviated the need for feature engineering, and learns sentence representations, which are to some extent able to capture the ‘rules ’ governing coherent sentence struc-ture. The proposed approach outperforms existing baselines and generates the state-of-art performance in standard coherence evaluation tasks1. 1
Ebiquity: Paraphrase and semantic similarity in Twitter using skipgrams
- In Proceedings of SemEval
, 2015
"... We describe the system we developed to partic-ipate in SemEval 2015 Task 1, Paraphrase and Semantic Similarity in Twitter. We create simi-larity vectors from two-skip trigrams of prepro-cessed tweets and measure their semantic simi-larity using our UMBC-STS system. We sub-mit two runs. The best resu ..."
Abstract
-
Cited by 3 (0 self)
- Add to MetaCart
(Show Context)
We describe the system we developed to partic-ipate in SemEval 2015 Task 1, Paraphrase and Semantic Similarity in Twitter. We create simi-larity vectors from two-skip trigrams of prepro-cessed tweets and measure their semantic simi-larity using our UMBC-STS system. We sub-mit two runs. The best result is ranked eleventh out of eighteen teams with F1 score of 0.599. 1.
