paper-with-me

홈 › Papers

An Analysis of Attention Mechanisms: The Case of Word Sense Disambiguation in Neural Machine Translation

2018-10-17 · WS 2018 10 · Gongbo Tang, Rico Sennrich, Joakim Nivre

Recent work has shown that the encoder-decoder attention mechanisms in neural machine translation (NMT) are different from the word alignment in statistical machine translation. In this paper, we focus on analyzing encoder-decoder attention mechanisms, in the case of word sense disambiguation (WSD) in NMT models. We hypothesize that attention mechanisms pay more attention to context tokens when translating ambiguous words. We explore the attention distribution patterns when translating ambiguous nouns. Counter-intuitively, we find that attention mechanisms are likely to distribute more attention to the ambiguous noun itself rather than context tokens, in comparison to other nouns. We conclude that attention mechanism is not the main mechanism used by NMT models to incorporate contextual information for WSD. The experimental results suggest that NMT models learn to encode contextual information necessary for WSD in the encoder hidden states. For the attention mechanism in Transformer models, we reveal that the first few layers gradually learn to "align" source and target tokens and the last few layers learn to extract features from the related but unaligned context tokens.

📄 PDF Abstract BibTeX arXiv:1810.07595

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderMachine TranslationNMTTranslationWord AlignmentWord Sense Disambiguation

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Residual Connection 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

Start Making Sense(s): A Developmental Probe of Attention Specialization Using Lexical Ambiguity

2025-11-26 · Pamela D. Rivière, Sean Trott arxiv

Despite an in-principle understanding of self-attention matrix operations in Transformer language models (LMs), it remains unclear precisely how these operations map onto interpretable computations or functions--and how …

Word Sense Disambiguation

Using Multi-Sense Vector Embeddings for Reverse Dictionaries

2019-04-02 · WS 2019 5 · Michael A. Hedderich, Andrew Yates, Dietrich Klakow, Gerard de Melo

Popular word embedding methods such as word2vec and GloVe assign a single vector representation to each word, even if a word has multiple distinct meanings. Multi-sense embeddings instead provide different vectors for ea…

That's sick dude!: Automatic identification of word sense change across different timescales

2014-05-17 · ACL 2014 6 · Sunny Mitra, Ritwik Mitra, Martin Riedl, Chris Biemann 외

In this paper, we propose an unsupervised method to identify noun sense changes based on rigorous analysis of time-varying text data available in the form of millions of digitized books. We construct distributional thesa…

Word Sense Disambiguation

Comparison of the effects of attention mechanism on translation tasks of different lengths of ambiguous words

2020-12-01 · AACL (iwdp) 2020 12 · Yue Hu, Jiahao Qin, Zemeiqi Chen, Jingshi Zhou 외

In recent years, attention mechanism has been widely used in various neural machine translation tasks based on encoder decoder. This paper focuses on the performance of encoder decoder attention mechanism in word sense d…

DecoderMachine TranslationNMTTranslation+1

Understanding Pure Character-Based Neural Machine Translation: The Case of Translating Finnish into English

2020-11-06 · COLING 2020 8 · Gongbo Tang, Rico Sennrich, Joakim Nivre

Recent work has shown that deeper character-based neural machine translation (NMT) models can outperform subword-based models. However, it is still unclear what makes deeper character-based models successful. In this pap…

Machine TranslationNMTTranslation