paper-with-me

홈 › Papers

Putting words in context: LSTM language models and lexical ambiguity

2019-06-12 · ACL 2019 7 · Laura Aina, Kristina Gulordava, Gemma Boleda

In neural network models of language, words are commonly represented using context-invariant representations (word embeddings) which are then put in context in the hidden layers. Since words are often ambiguous, representing the contextually relevant information is not trivial. We investigate how an LSTM language model deals with lexical ambiguity in English, designing a method to probe its hidden representations for lexical and contextual information about words. We find that both types of information are represented to a large extent, but also that there is room for improvement for contextual information.

📄 PDF Abstract BibTeX arXiv:1906.05149

Code (1)

amore-upf/LSTM_ambiguity 공식 구현 pytorch

Tasks

Language ModelingLanguage ModellingWord Embeddings

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…

Similar Papers 제목 키워드 기반

Fast and Accurate Recurrent Neural Network Acoustic Models for Speech Recognition

2015-07-24 · Haşim Sak, Andrew Senior, Kanishka Rao, Françoise Beaufays

We have recently shown that deep Long Short-Term Memory (LSTM) recurrent neural networks (RNNs) outperform feed forward deep neural networks (DNNs) as acoustic models for speech recognition. More recently, we have shown …

General Classificationspeech-recognitionSpeech Recognition

Head-Lexicalized Bidirectional Tree LSTMs

2017-01-01 · TACL 2017 1 · Zhiyang Teng, Yue Zhang

Sequential LSTMs have been extended to model tree structures, giving competitive results for a number of tasks. Existing methods model constituent trees by bottom-up combinations of constituent nodes, making direct use o…

Language ModelingLanguage ModellingRelation ExtractionSentiment Analysis

Bidirectional Tree-Structured LSTM with Head Lexicalization

2016-11-21 · Zhiyang Teng, Yue Zhang

Sequential LSTM has been extended to model tree structures, giving competitive results for a number of tasks. Existing methods model constituent trees by bottom-up combinations of constituent nodes, making direct use of …

General Classification

Learning to Represent Words in Context with Multilingual Supervision

2015-11-14 · Kazuya Kawakami, Chris Dyer

We present a neural network architecture based on bidirectional LSTMs to compute representations of words in the sentential contexts. These context-sensitive word representations are suitable for, e.g., distinguishing di…

Machine TranslationTranslation

Semantic Modelling with Long-Short-Term Memory for Information Retrieval

2014-12-20 · H. Palangi, L. Deng, Y. Shen, J. Gao 외

In this paper we address the following problem in web document and information retrieval (IR): How can we use long-term context information to gain better IR performance? Unlike common IR methods that use bag of words re…

Information RetrievalRetrieval