Research Area
Year Published

851 Results

August 2, 2019

Low-Resource Corpus Filtering using Multilingual Sentence Embeddings

Association for Computational Linguistics (ACL)

In this paper, we describe our submission to the WMT19 low-resource parallel corpus filtering shared task. Our main approach is based on the LASER toolkit (Language-Agnostic SEntence Representations), which uses an encoder-decoder architecture trained on a parallel corpus to obtain multilingual sentence representations.

By: Vishrav Chaudhary, Yuqing Tang, Francisco (Paco) Guzman, Holger Schwenk, Philipp Koehn

August 1, 2019

Lightweight and Efficient Neural Natural Language Processing with Quaternion Networks

Annual Meeting of the Association for Computational Linguistics (ACL)

Many state-of-the-art neural models for NLP are heavily parameterized and thus memory inefficient. This paper proposes a series of lightweight and memory efficient neural architectures for a potpourri of natural language processing (NLP) tasks.

By: Yi Tay, Aston Zhang, Luu Anh Tuan, Jinfeng Rao, Shuai Zhang, Shuohang Wang, Jie Fu, Siu Cheung Hui

August 1, 2019

Simple and Effective Curriculum Pointer-Generator Networks for Reading Comprehension over Long Narratives

Annual Meeting of the Association for Computational Linguistics (ACL)

This paper tackles the problem of reading comprehension over long narratives where documents easily span over thousands of tokens. We propose a curriculum learning (CL) based Pointer-Generator framework for reading/sampling over large documents, enabling diverse training of the neural model based on the notion of alternating contextual difficulty.

By: Yi Tay, Shuohang Wang, Luu Anh Tuan, Jie Fu, Minh C. Phan, Xingdi Yuan, Jinfeng Rao, Siu Cheung Hui, Aston Zhang

August 1, 2019

Constrained Decoding for Neural NLG from Compositional Representations in Task-Oriented Dialogue

Annual Meeting of the Association for Computational Linguistics (ACL)

In this paper, we (1) propose using tree-structured semantic representations, like those used in traditional rule-based NLG systems, for better discourse-level structuring and sentence-level planning; (2) introduce a challenging dataset using this representation for the weather domain; (3) introduce a constrained decoding approach for Seq2Seq models that leverages this representation to improve semantic correctness; and (4) demonstrate promising results on our dataset and the E2E dataset.

By: Anusha Balakrishnan, Jinfeng Rao, Kartikeya Upasani, Michael White, Rajen Subba

August 1, 2019

Exploring Deep Multimodal Fusion of Text and Photo for Hate Speech Classification

Workshop on Abusive Language Online

We present a number of fusion approaches to integrate text and photo signals. We show that augmenting text with image embedding information immediately leads to a boost in performance, while applying additional attention fusion methods brings further improvement.

By: Fan Yang, Xiaochang Peng, Gargi Ghosh, Reshef Shilon, Hao Ma, Eider Moore, Goran Predovic

July 31, 2019

Neural Volumes: Learning Dynamic Renderable Volumes from Images

SIGGRAPH

To overcome memory limitations of voxel-based representations, we learn a dynamic irregular grid structure implemented with a warp field during ray-marching. This structure greatly improves the apparent resolution and reduces grid-like artifacts and jagged motion. Finally, we demonstrate how to incorporate surface-based representations into our volumetric-learning framework for applications where the highest resolution is required, using facial performance capture as a case in point.

By: Stephen Lombardi, Tomas Simon, Jason Saragih, Gabriel Schwartz, Andreas Lehrmann, Yaser Sheikh

July 29, 2019

Improved Zero-shot Neural Machine Translation via Ignoring Spurious Correlations

Association for Computational Linguistics (ACL)

Zero-shot translation, translating between language pairs on which a Neural Machine Translation (NMT) system has never been trained, is an emergent property when training the system in multilingual settings. However, naïve training for zero-shot NMT easily fails, and is sensitive to hyper-parameter setting. The performance typically lags far behind the more conventional pivot-based approach which translates twice using a third language as a pivot.

By: Jiatao Gu, Yong Wang, Kyunghyun Cho, Victor O.K. Li

July 29, 2019

Scaling Static Analyses at Facebook

Communications of the ACM (CACM)

Static analysis tools are programs that examine, and attempt to draw conclusions about, the source of other programs, without running them. At Facebook we have been investing in advanced static analysis tools that employ reasoning techniques similar to those from program verification.

By: Dino Distefano, Manuel Fahndrich, Francesco Logozzo, Peter O'Hearn

July 29, 2019

Low Level Control of a Quadrotor with Deep Model-Based Reinforcement Learning

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

To address the challenge of rapidly generating low-level controllers, we argue for using model-based reinforcement learning (MBRL) trained on relatively small amounts of automatically generated (i.e., without system simulation) data. In this paper, we explore the capabilities of MBRL on a Crazyflie centimeter-scale quadrotor with rapid dynamics to predict and control at ≤ 50Hz.

By: Nathan O. Lambert, Daniel S. Drew, Joseph Yaconelli, Sergey Levine, Roberto Calandra, Kristofer S. J. Pister

July 29, 2019

Word-order biases in deep-agent emergent communication

Association for Computational Linguistics (ACL)

Sequence-processing neural networks led to remarkable progress on many NLP tasks. As a consequence, there has been increasing interest in understanding to what extent they process language as humans do. We aim here to uncover which biases such models display with respect to “natural” word-order constraints.

By: Rahma Chaabouni, Eugene Kharitonov, Alessandro Lazaric, Emmanuel Dupoux, Marco Baroni