paper-with-me

Papers

Embedding Time Differences in Context-sensitive Neural Networks for Learning Time to Event

2021-08-01 · ACL 2021 5 · Nazanin Dehghani, Hassan Hajipoor, Hadi Amiri

We propose an effective context-sensitive neural model for time to event (TTE) prediction task, which aims to predict the amount of time to/from the occurrence of given events in streaming content. We investigate this problem in the context of a multi-task learning framework, which we enrich with time difference embeddings. In addition, we develop a multi-genre dataset of English events about soccer competitions and academy awards ceremonies, and their relevant tweets obtained from Twitter. Our model is 1.4 and 3.3 hours more accurate than the current state-of-the-art model in estimating TTE on English and Dutch tweets respectively. We examine different aspects of our model to illustrate its source of improvement.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Task Learning

Similar Papers 제목 키워드 기반

Word Sense Distance in Human Similarity Judgements and Contextualised Word Embeddings

2020-06-01 · PaM 2020 6 · Janosch Haber, Massimo Poesio

Homonymy is often used to showcase one of the advantages of context-sensitive word embedding techniques such as ELMo and BERT. In this paper we want to shift the focus to the related but less exhaustively explored phenom…

Word Embeddings

Learning Domain-Sensitive and Sentiment-Aware Word Embeddings

2018-05-10 · ACL 2018 7 · Bei Shi, Zihao Fu, Lidong Bing, Wai Lam

Word embeddings have been widely used in sentiment classification because of their efficacy for semantic representations of words. Given reviews from different domains, some existing methods for word embeddings exploit s…

Data AugmentationGeneral ClassificationSentenceSentiment Analysis+2

Discovering Differences in the Representation of People using Contextualized Semantic Axes

2022-10-21 · Li Lucy, Divya Tadimeti, David Bamman

A common paradigm for identifying semantic differences across social and temporal contexts is the use of static word embeddings and their distances. In particular, past work has compared embeddings against "semantic axes…

Word Embeddings

A Dynamic Speaker Model for Conversational Interactions

2019-06-01 · NAACL 2019 6 · Hao Cheng, Hao Fang, Mari Ostendorf

Individual differences in speakers are reflected in their language use as well as in their interests and opinions. Characterizing these differences can be useful in human-computer interaction, as well as analysis of huma…

modelText Generation

NORMA: Neighborhood Sensitive Maps for Multilingual Word Embeddings

2018-10-01 · EMNLP 2018 10 · Ndapa Nakashole

Inducing multilingual word embeddings by learning a linear map between embedding spaces of different languages achieves remarkable accuracy on related languages. However, accuracy drops substantially when translating bet…

Machine TranslationMultilingual Word EmbeddingsTranslationWord Embeddings+1