Papers with News

11 papers
Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answering (2023.tacl-1)

Copied to clipboard

Challenge: Retrieval Augment Generation (RAG) has been developed for use in open-domain question answering (ODQA) but it is not optimized for use with other specialized domains such as healthcare and news.
Approach: They propose an extension to RAG that can adapt to a domain-specific knowledge base by updating all components of the external knowledge base during training.
Outcome: The proposed extension can adapt to a domain-specific knowledge base by updating all components of the external knowledge base during training.
Simple Neologism Based Domain Independent Models to Predict Year of Authorship (C18-1)

Copied to clipboard

Challenge: Using domain independent models, we date documents based only on neologism usage patterns . nasa models use only 200 input features, compared to state of the art models using 200K features.
Approach: They propose domain independent models to date documents based only on neologism usage patterns.
Outcome: The proposed models can generalize to various domains like News, Fiction, and Non-Fiction with competitive performance.
Revamping Multilingual Agreement Bidirectionally via Switched Back-translation for Multilingual Neural Machine Translation (2024.findings-eacl)

Copied to clipboard

Challenge: Current multilingual agreement (MA) methods require parallel data between multiple language pairs, which is not always realistic and optimize the agreement in an ambiguous direction, which hampers the translation performance.
Approach: They propose a novel multilingual agreement framework that optimizes agreement bidirectionally with the Kullback-Leibler Divergence loss.
Outcome: The proposed method improves strong baselines on the task of multilingual neural machine translation with three benchmarks: TED Talks, News, and Europarl.
Improving Topic Quality by Promoting Named Entities in Topic Modeling (P18-2)

Copied to clipboard

Challenge: Using named entities as domain-specific terms for news-centric content has not been studied extensively.
Approach: They propose to use named entities as domain-specific terms for news-centric content . they propose a weighting model that incorporates more named entities in topic descriptors .
Outcome: The proposed model improves the quality of news-centric topics by including more named entities in the topic descriptors.
Exploring Paracrawl for Document-level Neural Machine Translation (2023.eacl-main)

Copied to clipboard

Challenge: Document-level neural machine translation (NMT) has outperformed sentence-level NMT on a number of datasets.
Approach: They use Paracrawl to extract parallel paragraphs from Paracral webpages . they also use the extracted parallel paragraph as parallel documents for training .
Outcome: The proposed model outperforms sentence-level NMT on a number of datasets.
Learn To Remember: Transformer with Recurrent Memory for Document-Level Machine Translation (2022.findings-naacl)

Copied to clipboard

Challenge: Recent studies have shown that the effective use of contextual information between sentences can achieve better performance in document-level machine translation.
Approach: They propose a recurrent memory unit to the Transformer to support the information exchange between the sentence and previous context.
Outcome: The proposed model outperforms the previous work on TED and News by 0.91 s-BLEU and 1.49 d-BLUE on average.
TADPOLE: Task ADapted Pre-Training via AnOmaLy DEtection (2021.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to solve domain shifts in NLP tasks require additional pre-training . current approaches focus on the downstream corpus when it is small, but are not effective .
Approach: They propose a task-adapted pre-training framework that can be used when the downstream corpus is too small for additional pre-tuning.
Outcome: The proposed framework outperforms baseline methods on biomedical, computer science, news, and movie reviews tasks.
My side, your side and the evidence: Discovering aligned actor groups and the narratives they weave (2023.acl-long)

Copied to clipboard

Challenge: Identify distinct sets of aligned story actors responsible for sustaining issue-specific narratives . authors propose a novel two-step graph-based framework that identifies alignments between actors .
Approach: They propose a proxy task to identify the distinct sets of aligned story actors . they propose identifying alignments between actors and extracting alignes using TAMPA .
Outcome: The proposed framework is based on a corpus of text segments associated with six issues . it identifies aligned actors and extracts alignable actor groups from the network structure .
Target-Side Augmentation for Document-Level Machine Translation (2023.acl-long)

Copied to clipboard

Challenge: Document-level machine translation faces the challenge of data sparsity due to its long input length and a small amount of training data.
Approach: They propose a document-level machine translation model that generates many potential translations for each source document and smoothes the distribution.
Outcome: The proposed method outperforms the previous best system by 2.30 s-BLEU on News and achieves new state-of-the-art on News .
POINTER: Constrained Progressive Text Generation via Insertion-based Generative Pre-training (2020.emnlp-main)

Copied to clipboard

Challenge: Existing pre-trained language models cannot be directly employed to generate text under specified lexical constraints.
Approach: They propose a method for insertion-based text generation that inserts tokens between existing tokens in a parallel manner.
Outcome: The proposed method is intuitive and interpretable on Wikipedia and Yelp datasets.
Multi-Label and Multilingual News Framing Analysis (2020.acl-main)

Copied to clipboard

Challenge: Recent studies have focused on news framing in English, but few studies have explored how it can be extended to other languages and in multi-label settings.
Approach: They propose a method that leverages dictionary and few annotations to detect frames from just the headline in a low-resource context.
Outcome: The proposed method performs better than translating the entire headline to the source language . it can be scaled up to many languages, even those without existing translation technologies .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations