All Research Areas
Research Areas
Year Published

33 Results

August 10, 2016

Neural Network-Based Word Alignment through Score Aggregation

Association for Computational Linguistics Conference on Machine Translation

We present a simple neural network for word alignment that builds source and target word window representations to compute alignment scores for sentence pairs.

By: Joel Legrand, Michael Auli, Ronan Collobert
August 7, 2016

Strategies for Training Large Vocabulary Neural Language Models

Association for Computational Linguistics (ACL 2016)

We present a systematic comparison of neural strategies to represent and train large vocabularies, including softmax, hierarchical softmax, target sampling, noise contrastive estimation and self normalization.

By: Wenlin Chen, David Grangier, Michael Auli
June 8, 2016

Key-Value Memory Networks for Directly Reading Documents

EMNLP 2016

This paper introduces a new method, Key-Value Memory Networks, that makes reading documents more viable by utilizing different encodings in the addressing and output stages of the memory read operation.

By: Alexander Miller, Adam Fisch, Jesse Dodge, Amir-Hossein Karimi, Antoine Bordes, Jason Weston
April 13, 2016

Abstractive Summarization with Attentive RNN

NAACL 2016

Abstractive sentence summarization generates a shorter version of a given sentence while attempting to preserve its meaning. We introduce a conditional recurrent neural network (RNN) which generates a summary of an input sentence.

By: Sumit Chopra, Michael Auli, Alexander M. Rush
April 1, 2016

The Goldilocks Principle: Reading Children’s Books with Explicit Memory Representations

ICLR 2016

We introduce a new test of how well language models capture meaning in children’s books.

By: Felix Hill, Antoine Bordes, Sumit Chopra, Jason Weston
September 17, 2015

Improved Arabic Dialect Classification with Social Media Data

Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

Arabic dialect classification has been an important and challenging problem for Arabic language processing, especially for social media text analysis and machine translation. In this paper we propose an approach to improving Arabic dialect classification with semi-supervised learning: multiple classifiers are trained with weakly supervised, strongly supervised, and unsupervised data. Their combination yields significant and consistent improvement on two different test sets.

By: Fei Huang
December 4, 2014

Extracting Translation Pairs from Social Network Content

International Workshop on Spoken Language Translation

We describe two methods to collect translation pairs from public Facebook content. We use the extracted translation pairs as additional training data for machine translation systems and we can show significant improvements.

By: Matthias Eck, Yury Zemlyanskiy, Joy Zhang, Alex Waibel
September 4, 2014

Question Answering with Subgraph Embeddings

Empirical Methods in Natural Language Processing

This paper presents a system which learns to answer questions on a broad range of topics from a knowledge base using few handcrafted features. Our model learns low-dimensional embeddings of words and knowledge base constituents; these representations are used to score natural language questions against candidate answers.

By: Antoine Bordes, Jason Weston, Sumit Chopra
September 4, 2014

#TagSpace: Semantic Embeddings from Hashtags

Empirical Methods in Natural Language Processing

We describe a convolutional neural network that learns feature representations for short textual posts using hashtags as a supervised signal. The proposed approach is trained on up to 5.5 billion words predicting 100,000 possible hashtags.

By: Jason Weston, Sumit Chopra, Keith Adams
December 8, 2013

Using Web Text to Improve Keyword Spotting in Speech

Automatic Speech Recognition and Understanding Workshop (ASRU)

For low resource languages, collecting sufficient training data to build acoustic and language models is time consuming and often expensive. In this paper, we investigate the use of online text resour…

By: Ankur Gandhe, Long Qin, Florian Metze, Alexander Rudnicky, Ian Lane, Matthias Eck