paper-with-me

Papers

Enforcing Encoder-Decoder Modularity in Sequence-to-Sequence Models

2019-11-09 · Siddharth Dalmia, Abdel-rahman Mohamed, Mike Lewis, Florian Metze, Luke Zettlemoyer

Inspired by modular software design principles of independence, interchangeability, and clarity of interface, we introduce a method for enforcing encoder-decoder modularity in seq2seq models without sacrificing the overall model quality or its full differentiability. We discretize the encoder output units into a predefined interpretable vocabulary space using the Connectionist Temporal Classification (CTC) loss. Our modular systems achieve near SOTA performance on the 300h Switchboard benchmark, with WER of 8.3% and 17.6% on the SWB and CH subsets, using seq2seq models with encoder and decoder modules which are independent and interchangeable.

📄 PDF Abstract BibTeX arXiv:1911.03782

Code (0)

등록된 구현이 없습니다.

Tasks

Decoder

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
Seq2Seq Seq2Seq, or Sequence To Sequence, is a model used in sequence prediction tasks, such as language modelling and machine translation. The idea is to use one…

Similar Papers 제목 키워드 기반

Understanding How Encoder-Decoder Architectures Attend

2021-10-28 · NeurIPS 2021 12 · Kyle Aitken, Vinay V Ramasesh, Yuan Cao, Niru Maheswaranathan

Encoder-decoder networks with attention have proven to be a powerful way to solve many sequence-to-sequence tasks. In these networks, attention aligns encoder and decoder states and is often used for visualizing network …

Decoder

Decoder-Only or Encoder-Decoder? Interpreting Language Model as a Regularized Encoder-Decoder

2023-04-08 · Zihao Fu, Wai Lam, Qian Yu, Anthony Man-Cho So 외

The sequence-to-sequence (seq2seq) task aims at generating the target sequence based on the given input source sequence. Traditionally, most of the seq2seq task is resolved by the Encoder-Decoder framework which requires…

Data-to-Text GenerationDecoderLanguage ModelingLanguage Modelling+2

Encoder-decoder with Focus-mechanism for Sequence Labelling Based Spoken Language Understanding

2016-08-06 · Su Zhu, Kai Yu

This paper investigates the framework of encoder-decoder with attention for sequence labelling based spoken language understanding. We introduce Bidirectional Long Short Term Memory - Long Short Term Memory networks (BLS…

Decoderspeech-recognitionSpeech RecognitionSpoken Language Understanding

Neural Machine Transliteration: Preliminary Results

2016-09-14 · Amir H. Jadidinejad

Machine transliteration is the process of automatically transforming the script of a word from a source language to a target language, while preserving pronunciation. Sequence to sequence learning has recently emerged as…

DecoderTransliteration

Length bias in Encoder Decoder Models and a Case for Global Conditioning

2016-06-10 · EMNLP 2016 11 · Pavel Sountsov, Sunita Sarawagi

Encoder-decoder networks are popular for modeling sequences probabilistically in many applications. These models use the power of the Long Short-Term Memory (LSTM) architecture to capture the full dependence among variab…

Decoder